from .distro import main

if __name__ == "__main__":
    main()

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)

import sys

from .compat import chardet

# This code exists for backwards compatibility reasons.
# I don't like it either. Just look the other way. :)

for package in ("urllib3", "idna"):
    vendored_package = "pip._vendor." + package
    locals()[package] = __import__(vendored_package)
    # This traversal is apparently necessary such that the identities are
    # preserved (requests.packages.urllib3.* is urllib3.*)
    for mod in list(sys.modules):
        if mod == vendored_package or mod.startswith(vendored_package + '.'):
            unprefixed_mod = mod[len("pip._vendor."):]
            sys.modules['pip._vendor.requests.packages.' + unprefixed_mod] = sys.modules[mod]

if chardet is not None:
    target = chardet.__name__
    for mod in list(sys.modules):
        if mod == target or mod.startswith(f"{target}."):
            imported_mod = sys.modules[mod]
            sys.modules[f"requests.packages.{mod}"] = imported_mod
            mod = mod.replace(target, "chardet")
            sys.modules[f"requests.packages.{mod}"] = imported_mod

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)

"""Download files with progress indicators.
"""

import email.message
import logging
import mimetypes
import os
from typing import Iterable, Optional, Tuple

from pip._vendor.requests.models import Response

from pip._internal.cli.progress_bars import get_download_progress_renderer
from pip._internal.exceptions import NetworkConnectionError
from pip._internal.models.index import PyPI
from pip._internal.models.link import Link
from pip._internal.network.cache import is_from_cache
from pip._internal.network.session import PipSession
from pip._internal.network.utils import HEADERS, raise_for_status, response_chunks
from pip._internal.utils.misc import format_size, redact_auth_from_url, splitext

logger = logging.getLogger(__name__)


def _get_http_response_size(resp: Response) -> Optional[int]:
    try:
        return int(resp.headers["content-length"])
    except (ValueError, KeyError, TypeError):
        return None


def _prepare_download(
    resp: Response,
    link: Link,
    progress_bar: str,
) -> Iterable[bytes]:
    total_length = _get_http_response_size(resp)

    if link.netloc == PyPI.file_storage_domain:
        url = link.show_url
    else:
        url = link.url_without_fragment

    logged_url = redact_auth_from_url(url)

    if total_length:
        logged_url = f"{logged_url} ({format_size(total_length)})"

    if is_from_cache(resp):
        logger.info("Using cached %s", logged_url)
    else:
        logger.info("Downloading %s", logged_url)

    if logger.getEffectiveLevel() > logging.INFO:
        show_progress = False
    elif is_from_cache(resp):
        show_progress = False
    elif not total_length:
        show_progress = True
    elif total_length > (512 * 1024):
        show_progress = True
    else:
        show_progress = False

    chunks = response_chunks(resp)

    if not show_progress:
        return chunks

    renderer = get_download_progress_renderer(bar_type=progress_bar, size=total_length)
    return renderer(chunks)


def sanitize_content_filename(filename: str) -> str:
    """
    Sanitize the "filename" value from a Content-Disposition header.
    """
    return os.path.basename(filename)


def parse_content_disposition(content_disposition: str, default_filename: str) -> str:
    """
    Parse the "filename" value from a Content-Disposition header, and
    return the default filename if the result is empty.
    """
    m = email.message.Message()
    m["content-type"] = content_disposition
    filename = m.get_param("filename")
    if filename:
        # We need to sanitize the filename to prevent directory traversal
        # in case the filename contains ".." path parts.
        filename = sanitize_content_filename(str(filename))
    return filename or default_filename


def _get_http_response_filename(resp: Response, link: Link) -> str:
    """Get an ideal filename from the given HTTP response, falling back to
    the link filename if not provided.
    """
    filename = link.filename  # fallback
    # Have a look at the Content-Disposition header for a better guess
    content_disposition = resp.headers.get("content-disposition")
    if content_disposition:
        filename = parse_content_disposition(content_disposition, filename)
    ext: Optional[str] = splitext(filename)[1]
    if not ext:
        ext = mimetypes.guess_extension(resp.headers.get("content-type", ""))
        if ext:
            filename += ext
    if not ext and link.url != resp.url:
        ext = os.path.splitext(resp.url)[1]
        if ext:
            filename += ext
    return filename


def _http_get_download(session: PipSession, link: Link) -> Response:
    target_url = link.url.split("#", 1)[0]
    resp = session.get(target_url, headers=HEADERS, stream=True)
    raise_for_status(resp)
    return resp


class Downloader:
    def __init__(
        self,
        session: PipSession,
        progress_bar: str,
    ) -> None:
        self._session = session
        self._progress_bar = progress_bar

    def __call__(self, link: Link, location: str) -> Tuple[str, str]:
        """Download the file given by link into location."""
        try:
            resp = _http_get_download(self._session, link)
        except NetworkConnectionError as e:
            assert e.response is not None
            logger.critical(
                "HTTP error %s while getting %s", e.response.status_code, link
            )
            raise

        filename = _get_http_response_filename(resp, link)
        filepath = os.path.join(location, filename)

        chunks = _prepare_download(resp, link, self._progress_bar)
        with open(filepath, "wb") as content_file:
            for chunk in chunks:
                content_file.write(chunk)
        content_type = resp.headers.get("Content-Type", "")
        return filepath, content_type


class BatchDownloader:
    def __init__(
        self,
        session: PipSession,
        progress_bar: str,
    ) -> None:
        self._session = session
        self._progress_bar = progress_bar

    def __call__(
        self, links: Iterable[Link], location: str
    ) -> Iterable[Tuple[Link, Tuple[str, str]]]:
        """Download the files given by links into location."""
        for link in links:
            try:
                resp = _http_get_download(self._session, link)
            except NetworkConnectionError as e:
                assert e.response is not None
                logger.critical(
                    "HTTP error %s while getting %s",
                    e.response.status_code,
                    link,
                )
                raise

            filename = _get_http_response_filename(resp, link)
            filepath = os.path.join(location, filename)

            chunks = _prepare_download(resp, link, self._progress_bar)
            with open(filepath, "wb") as content_file:
                for chunk in chunks:
                    content_file.write(chunk)
            content_type = resp.headers.get("Content-Type", "")
            yield link, (filepath, content_type)

# -*- coding: utf-8 -*-
"""
backports.weakref_finalize
~~~~~~~~~~~~~~~~~~

Backports the Python 3 ``weakref.finalize`` method.
"""
from __future__ import absolute_import

import itertools
import sys
from weakref import ref

__all__ = ["weakref_finalize"]


class weakref_finalize(object):
    """Class for finalization of weakrefable objects
    finalize(obj, func, *args, **kwargs) returns a callable finalizer
    object which will be called when obj is garbage collected. The
    first time the finalizer is called it evaluates func(*arg, **kwargs)
    and returns the result. After this the finalizer is dead, and
    calling it just returns None.
    When the program exits any remaining finalizers for which the
    atexit attribute is true will be run in reverse order of creation.
    By default atexit is true.
    """

    # Finalizer objects don't have any state of their own.  They are
    # just used as keys to lookup _Info objects in the registry.  This
    # ensures that they cannot be part of a ref-cycle.

    __slots__ = ()
    _registry = {}
    _shutdown = False
    _index_iter = itertools.count()
    _dirty = False
    _registered_with_atexit = False

    class _Info(object):
        __slots__ = ("weakref", "func", "args", "kwargs", "atexit", "index")

    def __init__(self, obj, func, *args, **kwargs):
        if not self._registered_with_atexit:
            # We may register the exit function more than once because
            # of a thread race, but that is harmless
            import atexit

            atexit.register(self._exitfunc)
            weakref_finalize._registered_with_atexit = True
        info = self._Info()
        info.weakref = ref(obj, self)
        info.func = func
        info.args = args
        info.kwargs = kwargs or None
        info.atexit = True
        info.index = next(self._index_iter)
        self._registry[self] = info
        weakref_finalize._dirty = True

    def __call__(self, _=None):
        """If alive then mark as dead and return func(*args, **kwargs);
        otherwise return None"""
        info = self._registry.pop(self, None)
        if info and not self._shutdown:
            return info.func(*info.args, **(info.kwargs or {}))

    def detach(self):
        """If alive then mark as dead and return (obj, func, args, kwargs);
        otherwise return None"""
        info = self._registry.get(self)
        obj = info and info.weakref()
        if obj is not None and self._registry.pop(self, None):
            return (obj, info.func, info.args, info.kwargs or {})

    def peek(self):
        """If alive then return (obj, func, args, kwargs);
        otherwise return None"""
        info = self._registry.get(self)
        obj = info and info.weakref()
        if obj is not None:
            return (obj, info.func, info.args, info.kwargs or {})

    @property
    def alive(self):
        """Whether finalizer is alive"""
        return self in self._registry

    @property
    def atexit(self):
        """Whether finalizer should be called at exit"""
        info = self._registry.get(self)
        return bool(info) and info.atexit

    @atexit.setter
    def atexit(self, value):
        info = self._registry.get(self)
        if info:
            info.atexit = bool(value)

    def __repr__(self):
        info = self._registry.get(self)
        obj = info and info.weakref()
        if obj is None:
            return "<%s object at %#x; dead>" % (type(self).__name__, id(self))
        else:
            return "<%s object at %#x; for %r at %#x>" % (
                type(self).__name__,
                id(self),
                type(obj).__name__,
                id(obj),
            )

    @classmethod
    def _select_for_exit(cls):
        # Return live finalizers marked for exit, oldest first
        L = [(f, i) for (f, i) in cls._registry.items() if i.atexit]
        L.sort(key=lambda item: item[1].index)
        return [f for (f, i) in L]

    @classmethod
    def _exitfunc(cls):
        # At shutdown invoke finalizers for which atexit is true.
        # This is called once all other non-daemonic threads have been
        # joined.
        reenable_gc = False
        try:
            if cls._registry:
                import gc

                if gc.isenabled():
                    reenable_gc = True
                    gc.disable()
                pending = None
                while True:
                    if pending is None or weakref_finalize._dirty:
                        pending = cls._select_for_exit()
                        weakref_finalize._dirty = False
                    if not pending:
                        break
                    f = pending.pop()
                    try:
                        # gc is disabled, so (assuming no daemonic
                        # threads) the following is the only line in
                        # this function which might trigger creation
                        # of a new finalizer
                        f()
                    except Exception:
                        sys.excepthook(*sys.exc_info())
                    assert f not in cls._registry
        finally:
            # prevent any more finalizers from executing during shutdown
            weakref_finalize._shutdown = True
            if reenable_gc:
                gc.enable()