# repo.py -- For dealing with git repositories.
# Copyright (C) 2007 James Westby <jw+debian@jameswestby.net>
# Copyright (C) 2008-2013 Jelmer Vernooij <jelmer@jelmer.uk>
#
# Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU
# General Public License as public by the Free Software Foundation; version 2.0
# or (at your option) any later version. You can redistribute it and/or
# modify it under the terms of either of these two licenses.
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# You should have received a copy of the licenses; if not, see
# <http://www.gnu.org/licenses/> for a copy of the GNU General Public License
# and <http://www.apache.org/licenses/LICENSE-2.0> for a copy of the Apache
# License, Version 2.0.
#


"""Repository access.

This module contains the base class for git repositories
(BaseRepo) and an implementation which uses a repository on
local disk (Repo).

"""

from io import BytesIO
import errno
import os
import sys
import stat
import time

from dulwich.errors import (
    NoIndexPresent,
    NotBlobError,
    NotCommitError,
    NotGitRepository,
    NotTreeError,
    NotTagError,
    CommitError,
    RefFormatError,
    HookError,
    )
from dulwich.file import (
    GitFile,
    )
from dulwich.object_store import (
    DiskObjectStore,
    MemoryObjectStore,
    ObjectStoreGraphWalker,
    )
from dulwich.objects import (
    check_hexsha,
    Blob,
    Commit,
    ShaFile,
    Tag,
    Tree,
    )
from dulwich.pack import (
    pack_objects_to_data,
    )

from dulwich.hooks import (
    PreCommitShellHook,
    PostCommitShellHook,
    CommitMsgShellHook,
    )

from dulwich.line_ending import BlobNormalizer

from dulwich.refs import (  # noqa: F401
    ANNOTATED_TAG_SUFFIX,
    check_ref_format,
    RefsContainer,
    DictRefsContainer,
    InfoRefsContainer,
    DiskRefsContainer,
    read_packed_refs,
    read_packed_refs_with_peeled,
    write_packed_refs,
    SYMREF,
    )


import warnings


CONTROLDIR = '.git'
OBJECTDIR = 'objects'
REFSDIR = 'refs'
REFSDIR_TAGS = 'tags'
REFSDIR_HEADS = 'heads'
INDEX_FILENAME = "index"
COMMONDIR = 'commondir'
GITDIR = 'gitdir'
WORKTREES = 'worktrees'

BASE_DIRECTORIES = [
    ["branches"],
    [REFSDIR],
    [REFSDIR, REFSDIR_TAGS],
    [REFSDIR, REFSDIR_HEADS],
    ["hooks"],
    ["info"]
    ]

DEFAULT_REF = b'refs/heads/master'


class InvalidUserIdentity(Exception):
    """User identity is not of the format 'user <email>'"""

    def __init__(self, identity):
        self.identity = identity


def _get_default_identity():
    import getpass
    import socket
    username = getpass.getuser()
    try:
        import pwd
    except ImportError:
        fullname = None
    else:
        try:
            gecos = pwd.getpwnam(username).pw_gecos
        except KeyError:
            fullname = None
        else:
            fullname = gecos.split(',')[0]
    if not fullname:
        fullname = username
    email = os.environ.get('EMAIL')
    if email is None:
        email = "{}@{}".format(username, socket.gethostname())
    return (fullname, email)


def get_user_identity(config, kind=None):
    """Determine the identity to use for new commits.
    """
    if kind:
        user = os.environ.get("GIT_" + kind + "_NAME")
        if user is not None:
            user = user.encode('utf-8')
        email = os.environ.get("GIT_" + kind + "_EMAIL")
        if email is not None:
            email = email.encode('utf-8')
    else:
        user = None
        email = None
    if user is None:
        try:
            user = config.get(("user", ), "name")
        except KeyError:
            user = None
    if email is None:
        try:
            email = config.get(("user", ), "email")
        except KeyError:
            email = None
    default_user, default_email = _get_default_identity()
    if user is None:
        user = default_user.encode('utf-8')
    if email is None:
        email = default_email.encode('utf-8')
    return (user + b" <" + email + b">")


def check_user_identity(identity):
    """Verify that a user identity is formatted correctly.

    :param identity: User identity bytestring
    :raise InvalidUserIdentity: Raised when identity is invalid
    """
    try:
        fst, snd = identity.split(b' <', 1)
    except ValueError:
        raise InvalidUserIdentity(identity)
    if b'>' not in snd:
        raise InvalidUserIdentity(identity)


def parse_graftpoints(graftpoints):
    """Convert a list of graftpoints into a dict

    :param graftpoints: Iterator of graftpoint lines

    Each line is formatted as:
        <commit sha1> <parent sha1> [<parent sha1>]*

    Resulting dictionary is:
        <commit sha1>: [<parent sha1>*]

    https://git.wiki.kernel.org/index.php/GraftPoint
    """
    grafts = {}
    for l in graftpoints:
        raw_graft = l.split(None, 1)

        commit = raw_graft[0]
        if len(raw_graft) == 2:
            parents = raw_graft[1].split()
        else:
            parents = []

        for sha in [commit] + parents:
            check_hexsha(sha, 'Invalid graftpoint')

        grafts[commit] = parents
    return grafts


def serialize_graftpoints(graftpoints):
    """Convert a dictionary of grafts into string

    The graft dictionary is:
        <commit sha1>: [<parent sha1>*]

    Each line is formatted as:
        <commit sha1> <parent sha1> [<parent sha1>]*

    https://git.wiki.kernel.org/index.php/GraftPoint

    """
    graft_lines = []
    for commit, parents in graftpoints.items():
        if parents:
            graft_lines.append(commit + b' ' + b' '.join(parents))
        else:
            graft_lines.append(commit)
    return b'\n'.join(graft_lines)


class BaseRepo(object):
    """Base class for a git repository.

    :ivar object_store: Dictionary-like object for accessing
        the objects
    :ivar refs: Dictionary-like object with the refs in this
        repository
    """

    def __init__(self, object_store, refs):
        """Open a repository.

        This shouldn't be called directly, but rather through one of the
        base classes, such as MemoryRepo or Repo.

        :param object_store: Object store to use
        :param refs: Refs container to use
        """
        self.object_store = object_store
        self.refs = refs

        self._graftpoints = {}
        self.hooks = {}

    def _determine_file_mode(self):
        """Probe the file-system to determine whether permissions can be trusted.

        :return: True if permissions can be trusted, False otherwise.
        """
        raise NotImplementedError(self._determine_file_mode)

    def _init_files(self, bare):
        """Initialize a default set of named files."""
        from dulwich.config import ConfigFile
        self._put_named_file('description', b"Unnamed repository")
        f = BytesIO()
        cf = ConfigFile()
        cf.set("core", "repositoryformatversion", "0")
        if self._determine_file_mode():
            cf.set("core", "filemode", True)
        else:
            cf.set("core", "filemode", False)

        cf.set("core", "bare", bare)
        cf.set("core", "logallrefupdates", True)
        cf.write_to_file(f)
        self._put_named_file('config', f.getvalue())
        self._put_named_file(os.path.join('info', 'exclude'), b'')

    def get_named_file(self, path):
        """Get a file from the control dir with a specific name.

        Although the filename should be interpreted as a filename relative to
        the control dir in a disk-based Repo, the object returned need not be
        pointing to a file in that location.

        :param path: The path to the file, relative to the control dir.
        :return: An open file object, or None if the file does not exist.
        """
        raise NotImplementedError(self.get_named_file)

    def _put_named_file(self, path, contents):
        """Write a file to the control dir with the given name and contents.

        :param path: The path to the file, relative to the control dir.
        :param contents: A string to write to the file.
        """
        raise NotImplementedError(self._put_named_file)

    def _del_named_file(self, path):
        """Delete a file in the contrl directory with the given name."""
        raise NotImplementedError(self._del_named_file)

    def open_index(self):
        """Open the index for this repository.

        :raise NoIndexPresent: If no index is present
        :return: The matching `Index`
        """
        raise NotImplementedError(self.open_index)

    def fetch(self, target, determine_wants=None, progress=None, depth=None):
        """Fetch objects into another repository.

        :param target: The target repository
        :param determine_wants: Optional function to determine what refs to
            fetch.
        :param progress: Optional progress function
        :param depth: Optional shallow fetch depth
        :return: The local refs
        """
        if determine_wants is None:
            determine_wants = target.object_store.determine_wants_all
        count, pack_data = self.fetch_pack_data(
                determine_wants, target.get_graph_walker(), progress=progress,
                depth=depth)
        target.object_store.add_pack_data(count, pack_data, progress)
        return self.get_refs()

    def fetch_pack_data(self, determine_wants, graph_walker, progress,
                        get_tagged=None, depth=None):
        """Fetch the pack data required for a set of revisions.

        :param determine_wants: Function that takes a dictionary with heads