"""distutils.util

Miscellaneous utility functions -- anything that doesn't fit into
one of the other *util.py modules.
"""

from __future__ import annotations

import functools
import importlib.util
import os
import pathlib
import re
import string
import subprocess
import sys
import sysconfig
import tempfile
from collections.abc import Callable, Iterable, Mapping
from typing import TYPE_CHECKING

from jaraco.functools import pass_none

from ._log import log
from ._modified import newer
from .compilers.platform import detect, macos
from .errors import DistutilsByteCompileError, DistutilsPlatformError
from .spawn import spawn

if TYPE_CHECKING:
    from typing_extensions import TypeVarTuple, Unpack

    _Ts = TypeVarTuple("_Ts")

# Platform and macOS helpers now live in the compilers package; these names are
# re-exported for backward compatibility.
get_host_platform = detect.get_host_platform
get_platform = detect.get_platform
is_mingw = detect.is_mingw
MACOSX_VERSION_VAR = macos.VERSION_VAR
get_macosx_target_ver = macos.target_ver
get_macosx_target_ver_from_syscfg = macos._target_ver_from_syscfg
_clear_cached_macosx_ver = macos._clear_cached_target_ver


def split_version(s: str) -> list[int]:
    """Convert a dot-separated string into a list of numbers for comparisons"""
    return [int(n) for n in s.split('.')]


@pass_none
def convert_path(pathname: str | os.PathLike[str]) -> str:
    r"""
    Allow for pathlib.Path inputs, coax to a native path string.

    If None is passed, will just pass it through as
    Setuptools relies on this behavior.

    >>> convert_path(None) is None
    True

    Removes empty paths.

    >>> convert_path('foo/./bar').replace('\\', '/')
    'foo/bar'
    """
    return os.fspath(pathlib.PurePath(pathname))


def change_root(
    new_root: str | os.PathLike[str],
    pathname: str | os.PathLike[str],
) -> str:
    """Return 'pathname' with 'new_root' prepended.  If 'pathname' is
    relative, this is equivalent to "os.path.join(new_root,pathname)".
    Otherwise, it requires making 'pathname' relative and then joining the
    two, which is tricky on DOS/Windows and Mac OS.
    """
    if os.name == 'posix':
        if not os.path.isabs(pathname):
            return os.path.join(new_root, pathname)
        else:
            # type-ignore: This makes bytes-based paths unsupported in this branch.
            # Either this or we don't support absolute os.Pathlike, or we complexify this branch.
            return os.path.join(new_root, str(pathname)[1:])

    elif os.name == 'nt':
        (_drive, path) = os.path.splitdrive(pathname)
        if path[0] == os.sep:
            path = path[1:]
        return os.path.join(new_root, path)

    raise DistutilsPlatformError(f"nothing known about platform '{os.name}'")


@functools.lru_cache
def check_environ() -> None:
    """Ensure that 'os.environ' has all the environment variables we
    guarantee that users can use in config files, command-line options,
    etc.  Currently this includes:
      HOME - user's home directory (Unix only)
      PLAT - description of the current platform, including hardware
             and OS (see 'get_platform()')
    """
    if os.name == 'posix' and 'HOME' not in os.environ:
        try:
            import pwd

            os.environ['HOME'] = pwd.getpwuid(os.getuid())[5]
        except (ImportError, KeyError):
            # bpo-10496: if the current user identifier doesn't exist in the
            # password database, do nothing
            pass

    if 'PLAT' not in os.environ:
        os.environ['PLAT'] = get_platform()


def subst_vars(s, local_vars: Mapping[str, object]) -> str:
    """
    Perform variable substitution on 'string'.
    Variables are indicated by format-style braces ("{var}").
    Variable is substituted by the value found in the 'local_vars'
    dictionary or in 'os.environ' if it's not in 'local_vars'.
    'os.environ' is first checked/augmented to guarantee that it contains
    certain values: see 'check_environ()'.  Raise ValueError for any
    variables not found in either 'local_vars' or 'os.environ'.
    """
    check_environ()
    lookup = dict(os.environ)
    lookup.update((name, str(value)) for name, value in local_vars.items())
    try:
        return _subst_compat(s).format_map(lookup)
    except KeyError as var:
        raise ValueError(f"invalid variable {var}")


def _subst_compat(s):
    """
    Replace shell/Perl-style variable substitution with
    format-style. For compatibility.
    """

    def _subst(match):
        return f'{{{match.group(1)}}}'

    repl = re.sub(r'\$([a-zA-Z_][a-zA-Z_0-9]*)', _subst, s)
    if repl != s:
        import warnings

        warnings.warn(
            "shell/Perl-style substitutions are deprecated",
            DeprecationWarning,
        )
    return repl


def grok_environment_error(exc: object, prefix: str = "error: ") -> str:
    # Function kept for backward compatibility.
    # Used to try clever things with EnvironmentErrors,
    # but nowadays str(exception) produces good messages.
    return prefix + str(exc)


# Needed by 'split_quoted()'
_wordchars_re = re.compile(rf'[^\\\'\"{string.whitespace} ]*')
_squote_re = re.compile(r"'(?:[^'\\]|\\.)*'")
_dquote_re = re.compile(r'"(?:[^"\\]|\\.)*"')


def split_quoted(s: str) -> list[str]:
    """Split a string up according to Unix shell-like rules for quotes and
    backslashes.  In short: words are delimited by spaces, as long as those
    spaces are not escaped by a backslash, or inside a quoted string.
    Single and double quotes are equivalent, and the quote characters can
    be backslash-escaped.  The backslash is stripped from any two-character
    escape sequence, leaving only the escaped character.  The quote
    characters are stripped from any quoted string.  Returns a list of
    words.
    """

    # This is a nice algorithm for splitting up a single string, since it
    # doesn't require character-by-character examination.  It was a little
    # bit of a brain-bender to get it working right, though...

    s = s.strip()
    words = []
    pos = 0

    while s:
        m = _wordchars_re.match(s, pos)
        assert m is not None
        end = m.end()
        if end == len(s):
            words.append(s[:end])
            break

        if s[end] in string.whitespace:
            # unescaped, unquoted whitespace: now
            # we definitely have a word delimiter
            words.append(s[:end])
            s = s[end:].lstrip()
            pos = 0

        elif s[end] == '\\':
            # preserve whatever is being escaped;
            # will become part of the current word
            s = s[:end] + s[end + 1 :]
            pos = end + 1

        else:
            if s[end] == "'":  # slurp singly-quoted string
                m = _squote_re.match(s, end)
            elif s[end] == '"':  # slurp doubly-quoted string
                m = _dquote_re.match(s, end)
            else:
                raise RuntimeError(f"this can't happen (bad char '{s[end]}')")

            if m is None:
                raise ValueError(f"bad string (mismatched {s[end]} quotes?)")

            (beg, end) = m.span()
            s = s[:beg] + s[beg + 1 : end - 1] + s[end:]
            pos = m.end() - 2

        if pos >= len(s):
            words.append(s)
            break

    return words


def execute(
    func: Callable[[Unpack[_Ts]], object],
    args: tuple[Unpack[_Ts]],
    msg: object = None,
    verbose: bool = False,
) -> None:
    """
    Perform some action that affects the outside world (e.g. by
    writing to the filesystem). Was previously used to deal with
    "dry run" operations, but now runs unconditionally.
    """
    if msg is None:
        msg = f"{func.__name__}{args!r}"
        if msg[-2:] == ',)':  # correct for singleton tuple
            msg = msg[0:-2] + ')'

    log.info(msg)
    func(*args)


def strtobool(val: str) -> bool:
    """Convert a string representation of truth to true (1) or false (0).

    True values are 'y', 'yes', 't', 'true', 'on', and '1'; false values
    are 'n', 'no', 'f', 'false', 'off', and '0'.  Raises ValueError if
    'val' is anything else.
    """
    val = val.lower()
    if val in ('y', 'yes', 't', 'true', 'on', '1'):
        return True
    elif val in ('n', 'no', 'f', 'false', 'off', '0'):
        return False
    else:
        raise ValueError(f"invalid truth value {val!r}")


def byte_compile(  # noqa: C901
    py_files: Iterable[str],
    optimize: int = 0,
    force: bool = False,
    prefix: str | None = None,
    base_dir: str | None = None,
    verbose: bool = True,
    direct: bool | None = None,
) -> None:
    """Byte-compile a collection of Python source files to .pyc
    files in a __pycache__ subdirectory.  'py_files' is a list
    of files to compile; any files that don't end in ".py" are silently
    skipped.  'optimize' must be one of the following:
      0 - don't optimize
      1 - normal optimization (like "python -O")
      2 - extra optimization (like "python -OO")
    If 'force' is true, all files are recompiled regardless of
    timestamps.

    The source filename encoded in each bytecode file defaults to the
    filenames listed in 'py_files'; you can modify these with 'prefix' and
    'basedir'.  'prefix' is a string that will be stripped off of each
    source filename, and 'base_dir' is a directory name that will be
    prepended (after 'prefix' is stripped).  You can supply either or both
    (or neither) of 'prefix' and 'base_dir', as you wish.

    Byte-compilation is either done directly in this interpreter process
    with the standard py_compile module, or indirectly by writing a
    temporary script and executing it.  Normally, you should let
    'byte_compile()' figure out to use direct compilation or not (see
    the source for details).  The 'direct' flag is used by the script
    generated in indirect mode; unless you know what you're doing, leave
    it set to None.
    """

    # nothing is done if sys.dont_write_bytecode is True
    if sys.dont_write_bytecode:
        raise DistutilsByteCompileError('byte-compiling is disabled.')

    # First, if the caller didn't force us into direct or indirect mode,
    # figure out which mode we should be in.  We take a conservative
    # approach: choose direct mode *only* if the current interpreter is
    # in debug mode and optimize is 0.  If we're not in debug mode (-O
    # or -OO), we don't know which level of optimization this
    # interpreter is running with, so we can't do direct
    # byte-compilation and be certain that it's the right thing.  Thus,
    # always compile indirectly if the current interpreter is in either
    # optimize mode, or if either optimization level was requested by
    # the caller.
    if direct is None:
        direct = __debug__ and optimize == 0

    # "Indirect" byte-compilation: write a temporary script and then
    # run it with the appropriate flags.
    if not direct:
        (script_fd, script_name) = tempfile.mkstemp(".py")
        log.info("writing byte-compilation script '%s'", script_name)
        script = os.fdopen(script_fd, "w", encoding='utf-8')

        with script:
            script.write(
                """\
from distutils.util import byte_compile
files = [
"""
            )

            # XXX would be nice to write absolute filenames, just for
            # safety's sake (script should be more robust in the face of
            # chdir'ing before running it).  But this requires abspath'ing
            # 'prefix' as well, and that breaks the hack in build_lib's
            # 'byte_compile()' method that carefully tacks on a trailing
            # slash (os.sep really) to make sure the prefix here is "just
            # right".  This whole prefix business is rather delicate -- the
            # problem is that it's really a directory, but I'm treating it
            # as a dumb string, so trailing slashes and so forth matter.

            script.write(",\n".join(map(repr, py_files)) + "]\n")
            script.write(
                f"""
byte_compile(files, optimize={optimize!r}, force={force!r},
         prefix={prefix!r}, base_dir={base_dir!r},
         verbose={verbose!r},
         direct=True)
"""
            )

        cmd = [sys.executable]
        cmd.extend(subprocess._optim_args_from_interpreter_flags())
        cmd.append(script_name)
        spawn(cmd)
        execute(os.remove, (script_name,), f"removing {script_name}")

    # "Direct" byte-compilation: use the py_compile module to compile
    # right here, right now.  Note that the script generated in indirect
    # mode simply calls 'byte_compile()' in direct mode, a weird sort of
    # cross-process recursion.  Hey, it works!
    else:
        from py_compile import compile

        for file in py_files:
            if file[-3:] != ".py":
                # This lets us be lazy and not filter filenames in
                # the "install_lib" command.
                continue

            # Terminology from the py_compile module:
            #   cfile - byte-compiled file
            #   dfile - purported source filename (same as 'file' by default)
            if optimize >= 0:
                opt = '' if optimize == 0 else optimize
                cfile = importlib.util.cache_from_source(file, optimization=opt)
            else:
                cfile = importlib.util.cache_from_source(file)
            dfile = file
            if prefix:
                if file[: len(prefix)] != prefix:
                    raise ValueError(
                        f"invalid prefix: filename {file!r} doesn't start with {prefix!r}"
                    )
                dfile = dfile[len(prefix) :]
            if base_dir:
                dfile = os.path.join(base_dir, dfile)

            cfile_base = os.path.basename(cfile)
            if direct:
                if force or newer(file, cfile):
                    log.info("byte-compiling %s to %s", file, cfile_base)
                    compile(file, cfile, dfile)
                else:
                    log.debug("skipping byte-compilation of %s to %s", file, cfile_base)


def rfc822_escape(header: str) -> str:
    """Return a version of the string escaped for inclusion in an
    RFC-822 header, by ensuring there are 8 spaces space after each newline.
    """
    indent = 8 * " "
    lines = header.splitlines(keepends=True)

    # Emulate the behaviour of `str.split`
    # (the terminal line break in `splitlines` does not result in an extra line):
    ends_in_newline = lines and lines[-1].splitlines()[0] != lines[-1]
    suffix = indent if ends_in_newline else ""

    return indent.join(lines) + suffix


def is_freethreaded() -> bool:
    """Return True if the Python interpreter is built with free threading support."""
    return bool(sysconfig.get_config_var('Py_GIL_DISABLED'))