#!/usr/bin/env python3

import ast

import collections

import io

import os

import sys

# Import a minimal set of stdlib modules needed for list_stdlib_modules()

# to work when run from a virtualenv.  The modules were chosen empirically

# so that the return value matches the return value without virtualenv.

if True:  # disable lexical sorting checks

    import argparse

    import zlib

import testparseutil

# Allow list of modules that symbols can be directly imported from.

allowsymbolimports = (

    '__future__',

    'breezy',

    'concurrent',

    'hgclient',

    'mercurial',

    'mercurial.hgweb.common',

    'mercurial.hgweb.request',

    'mercurial.i18n',

    'mercurial.interfaces',

    'mercurial.node',

    'mercurial.pycompat',

    # for revlog to re-export constant to extensions

    'mercurial.revlogutils.constants',

    'mercurial.revlogutils.flagutil',

    # for cffi modules to re-export pure functions

    'mercurial.pure.base85',

    'mercurial.pure.bdiff',

    'mercurial.pure.mpatch',

    'mercurial.pure.osutil',

    'mercurial.pure.parsers',

    # third-party imports should be directly imported

    'mercurial.thirdparty',

    'mercurial.thirdparty.attr',

    'mercurial.thirdparty.jaraco.collections',

    'mercurial.thirdparty.tomli',

    'typing',

    'xml.etree.ElementTree',

)

# Allow list of symbols that can be directly imported.

directsymbols = ('demandimport',)

# Modules that must be aliased because they are commonly confused with

# common variables and can create aliasing and readability issues.

requirealias = {

    'ui': 'uimod',

}

def walklocal(root):

    """Recursively yield all descendant nodes but not in a different scope"""

    todo = collections.deque(ast.iter_child_nodes(root))

    yield root, False

    while todo:

        node = todo.popleft()

        newscope = isinstance(node, ast.FunctionDef)

        if not newscope:

            todo.extend(ast.iter_child_nodes(node))

        yield node, newscope

def dotted_name_of_path(path):

    """Given a relative path to a source file, return its dotted module name.

    >>> dotted_name_of_path('mercurial/error.py')

    'mercurial.error'

    >>> dotted_name_of_path('zlibmodule.so')

    'zlib'

    """

    parts = path.replace(os.sep, '/').split('/')

    parts[-1] = parts[-1].split('.', 1)[0]  # remove .py and .so and .ARCH.so

    if parts[-1].endswith('module'):

        parts[-1] = parts[-1][:-6]

    return '.'.join(parts)

def fromlocalfunc(modulename, localmods):

    """Get a function to examine which locally defined module the

    target source imports via a specified name.

    `modulename` is an `dotted_name_of_path()`-ed source file path,

    which may have `.__init__` at the end of it, of the target source.

    `localmods` is a set of absolute `dotted_name_of_path()`-ed source file

    paths of locally defined (= Mercurial specific) modules.

    This function assumes that module names not existing in

    `localmods` are from the Python standard library.

    This function returns the function, which takes `name` argument,

    and returns `(absname, dottedpath, hassubmod)` tuple if `name`

    matches against locally defined module. Otherwise, it returns

    False.

    It is assumed that `name` doesn't have `.__init__`.

    `absname` is an absolute module name of specified `name`

    (e.g. "hgext.convert"). This can be used to compose prefix for sub

    modules or so.

    `dottedpath` is a `dotted_name_of_path()`-ed source file path

    (e.g. "hgext.convert.__init__") of `name`. This is used to look

    module up in `localmods` again.

    `hassubmod` is whether it may have sub modules under it (for

    convenient, even though this is also equivalent to "absname !=

    dottednpath")

    >>> localmods = {'foo.__init__', 'foo.foo1',

    ...              'foo.bar.__init__', 'foo.bar.bar1',

    ...              'baz.__init__', 'baz.baz1'}

    >>> fromlocal = fromlocalfunc('foo.xxx', localmods)

    >>> # relative

    >>> fromlocal('foo1')

    ('foo.foo1', 'foo.foo1', False)

    >>> fromlocal('bar')

    ('foo.bar', 'foo.bar.__init__', True)

    >>> fromlocal('bar.bar1')

    ('foo.bar.bar1', 'foo.bar.bar1', False)

    >>> # absolute

    >>> fromlocal('baz')

    ('baz', 'baz.__init__', True)

    >>> fromlocal('baz.baz1')

    ('baz.baz1', 'baz.baz1', False)

    >>> # unknown = maybe standard library

    >>> fromlocal('os')

    False

    >>> fromlocal(None, 1)

    ('foo', 'foo.__init__', True)

    >>> fromlocal('foo1', 1)

    ('foo.foo1', 'foo.foo1', False)

    >>> fromlocal2 = fromlocalfunc('foo.xxx.yyy', localmods)

    >>> fromlocal2(None, 2)

    ('foo', 'foo.__init__', True)

    >>> fromlocal2('bar2', 1)

    False

    >>> fromlocal2('bar', 2)

    ('foo.bar', 'foo.bar.__init__', True)

    """

    if not isinstance(modulename, str):

        modulename = modulename.decode('ascii')

    prefix = '.'.join(modulename.split('.')[:-1])

    if prefix:

        prefix += '.'

    def fromlocal(name, level=0):

        # name is false value when relative imports are used.

        if not name:

            # If relative imports are used, level must not be absolute.

            assert level > 0

            candidates = ['.'.join(modulename.split('.')[:-level])]

        else:

            if not level:

                # Check relative name first.

                candidates = [prefix + name, name]

            else:

                candidates = [

                    '.'.join(modulename.split('.')[:-level]) + '.' + name

                ]

        for n in candidates:

            if n in localmods:

                return (n, n, False)

            dottedpath = n + '.__init__'

            if dottedpath in localmods:

                return (n, dottedpath, True)

        return False

    return fromlocal

def populateextmods(localmods):

    """Populate C extension modules based on pure modules"""

    newlocalmods = set(localmods)

    for n in localmods:

        if n.startswith('mercurial.pure.'):

            m = n[len('mercurial.pure.') :]

            newlocalmods.add('mercurial.cext.' + m)

            newlocalmods.add('mercurial.cffi._' + m)

    return newlocalmods

def list_stdlib_modules():

    """List the modules present in the stdlib.

    >>> mods = set(list_stdlib_modules())

    >>> 'http' in mods

    True

    os.path isn't really a module, so it's missing:

    >>> 'os.path' in mods

    False

    sys requires special treatment, because it's baked into the

    interpreter, but it should still appear:

    >>> 'sys' in mods

    True

    >>> 'collections' in mods

    True

    >>> 'array' in mods

    True

    >>> 'cffi' in mods

    True

    """

    # These modules only exist on windows, but we should always

    # consider them stdlib.

    yield '__builtin__'

    yield 'builtins'  # python3 only

    yield 'importlib.abc'  # python3 only

    yield 'importlib.machinery'  # python3 only

    yield 'importlib.util'  # python3 only

    yield 'packaging.version'

    yield 'distutils'  # in Python < 3.12

    yield 'distutils.version'  # in Python < 3.12

    stdlib_prefixes = {sys.prefix, sys.exec_prefix}

    # We need to supplement the list of prefixes for the search to work

    # when run from within a virtualenv.

    for mod in (argparse, zlib):

        if mod is None:

            continue

        try:

            # Not all module objects have a __file__ attribute.

            filename = mod.__file__

        except AttributeError:

            continue

        dirname = os.path.dirname(filename)

        for prefix in stdlib_prefixes:

            if dirname.startswith(prefix):

                # Then this directory is redundant.

                break

        else:

            stdlib_prefixes.add(dirname)

    sourceroot = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))

    for libpath in sys.path:

        # We want to walk everything in sys.path that starts with something in

        # stdlib_prefixes, but not directories from the hg sources.

        if os.path.abspath(libpath).startswith(sourceroot) or not any(

            libpath.startswith(p) for p in stdlib_prefixes

        ):

            continue

        for top, dirs, files in os.walk(libpath):

            if 'dist-packages' in top.split(os.path.sep):

                continue

            for i, d in reversed(list(enumerate(dirs))):

                if (

                    not os.path.exists(os.path.join(top, d, '__init__.py'))

                    or top == libpath

                    and d in ('hgdemandimport', 'hgext', 'mercurial')

                ):

                    del dirs[i]

            for name in files:

                if not name.endswith(('.py', '.so', '.pyc', '.pyo', '.pyd')):

                    continue

                if name.startswith('__init__.py'):

                    full_path = top

                else:

                    full_path = os.path.join(top, name)

                rel_path = full_path[len(libpath) + 1 :]

                mod = dotted_name_of_path(rel_path)

                yield mod

stdlib_modules = set(list_stdlib_modules())

def imported_modules(source, modulename, f, localmods, ignore_nested=False):

    """Given the source of a file as a string, yield the names

    imported by that file.

    Args:

      source: The python source to examine as a string.

      modulename: of specified python source (may have `__init__`)

      localmods: set of locally defined module names (may have `__init__`)

      ignore_nested: If true, import statements that do not start in

                     column zero will be ignored.

    Returns:

      A list of absolute module names imported by the given source.

    >>> f = 'foo/xxx.py'

    >>> modulename = 'foo.xxx'

    >>> localmods = {'foo.__init__': True,

    ...              'foo.foo1': True, 'foo.foo2': True,

    ...              'foo.bar.__init__': True, 'foo.bar.bar1': True,

    ...              'baz.__init__': True, 'baz.baz1': True }

    >>> # standard library (= not locally defined ones)

    >>> sorted(imported_modules(

    ...        'from stdlib1 import foo, bar; import stdlib2',

    ...        modulename, f, localmods))

    []

    >>> # relative importing

    >>> sorted(imported_modules(

    ...        'import foo1; from bar import bar1',

    ...        modulename, f, localmods))

    ['foo.bar.bar1', 'foo.foo1']

    >>> sorted(imported_modules(

    ...        'from bar.bar1 import name1, name2, name3',

    ...        modulename, f, localmods))

    ['foo.bar.bar1']

    >>> # absolute importing

    >>> sorted(imported_modules(

    ...        'from baz import baz1, name1',

    ...        modulename, f, localmods))

    ['baz.__init__', 'baz.baz1']

    >>> # mixed importing, even though it shouldn't be recommended

    >>> sorted(imported_modules(

    ...        'import stdlib, foo1, baz',

    ...        modulename, f, localmods))

    ['baz.__init__', 'foo.foo1']

    >>> # ignore_nested

    >>> sorted(imported_modules(

    ... '''import foo

    ... def wat():

    ...     import bar

    ... ''', modulename, f, localmods))

    ['foo.__init__', 'foo.bar.__init__']

    >>> sorted(imported_modules(

    ... '''import foo

    ... def wat():

    ...     import bar

    ... ''', modulename, f, localmods, ignore_nested=True))

    ['foo.__init__']

    """

    fromlocal = fromlocalfunc(modulename, localmods)

    for node in ast.walk(ast.parse(source, f)):

        if ignore_nested and getattr(node, 'col_offset', 0) > 0:

            continue

        if isinstance(node, ast.Import):

            for n in node.names:

                found = fromlocal(n.name)

                if not found:

                    # this should import standard library

                    continue

                yield found[1]

        elif isinstance(node, ast.ImportFrom):

            found = fromlocal(node.module, node.level)

            if not found:

                # this should import standard library

                continue

            absname, dottedpath, hassubmod = found

            if not hassubmod:

                # "dottedpath" is not a package; must be imported

                yield dottedpath

                # examination of "node.names" should be redundant

                # e.g.: from mercurial.node import nullid, nullrev

                continue

            modnotfound = False

            prefix = absname + '.'

            for n in node.names:

                found = fromlocal(prefix + n.name)

                if not found:

                    # this should be a function or a property of "node.module"

                    modnotfound = True

                    continue

                yield found[1]

            if modnotfound and dottedpath != modulename:

                # "dottedpath" is a package, but imported because of non-module

                # lookup

                # specifically allow "from . import foo" from __init__.py

                yield dottedpath

def verify_import_convention(module, source, localmods):

    """Verify imports match our established coding convention."""

    root = ast.parse(source)

    return verify_modern_convention(module, root, localmods)

def verify_modern_convention(module, root, localmods, root_col_offset=0):

    """Verify a file conforms to the modern import convention rules.

    The rules of the modern convention are:

    * Ordering is stdlib followed by local imports. Each group is lexically

      sorted.

    * Importing multiple modules via "import X, Y" is not allowed: use

      separate import statements.

    * Importing multiple modules via "from X import ..." is allowed if using

      parenthesis and one entry per line.

    * Only 1 relative import statement per import level ("from .", "from ..")

      is allowed.

    * Relative imports from higher levels must occur before lower levels. e.g.

      "from .." must be before "from .".

    * Imports from peer packages should use relative import (e.g. do not

      "import mercurial.foo" from a "mercurial.*" module).

    * Symbols can only be imported from specific modules (see

      `allowsymbolimports`). For other modules, first import the module then

      assign the symbol to a module-level variable. In addition, these imports

      must be performed before other local imports. This rule only

      applies to import statements outside of any blocks.

    * Relative imports from the standard library are not allowed, unless that

      library is also a local module.

    * Certain modules must be aliased to alternate names to avoid aliasing

      and readability problems. See `requirealias`.

    """

    if not isinstance(module, str):

        module = module.decode('ascii')

    topmodule = module.split('.')[0]

    fromlocal = fromlocalfunc(module, localmods)

    # Whether a local/non-stdlib import has been performed.

    seenlocal = None

    # Whether a local/non-stdlib, non-symbol import has been seen.

    seennonsymbollocal = False

    # The last name to be imported (for sorting).

    lastname = None

    laststdlib = None

    # Relative import levels encountered so far.

    seenlevels = set()

    for node, newscope in walklocal(root):

        def msg(fmt, *args):

            return (fmt % args, node.lineno)

        if newscope:

            # Check for local imports in function

                module, node, localmods, node.col_offset + 4

        elif isinstance(node, ast.Import):

            # Disallow "import foo, bar" and require separate imports

            # for each module.

            if len(node.names) > 1:

                yield msg(

                    'multiple imported names: %s',

                    ', '.join(n.name for n in node.names),

                )

            name = node.names[0].name

            asname = node.names[0].asname

            stdlib = name in stdlib_modules

            # Ignore sorting rules on imports inside blocks.

            if node.col_offset == root_col_offset:

                if lastname and name < lastname and laststdlib == stdlib:

                    yield msg(

                        'imports not lexically sorted: %s < %s', name, lastname

                    )

            lastname = name

            laststdlib = stdlib

            # stdlib imports should be before local imports.

            if stdlib and seenlocal and node.col_offset == root_col_offset:

                yield msg(

                    'stdlib import "%s" follows local import: %s',

                    name,

                    seenlocal,

                )

            if not stdlib:

                seenlocal = name

            # Import of sibling modules should use relative imports.

            topname = name.split('.')[0]

            if topname == topmodule:

                yield msg('import should be relative: %s', name)

            if name in requirealias and asname != requirealias[name]:

                yield msg(