import re

from io import BytesIO

from itertools import chain

from subprocess import PIPE, Popen

from dulwich import objects

from dulwich.config import ConfigFile

from kallithea.lib.vcs.backends.base import BaseChangeset, EmptyChangeset

from kallithea.lib.vcs.conf import settings

from kallithea.lib.vcs.exceptions import ChangesetDoesNotExistError, ChangesetError, ImproperArchiveTypeError, NodeDoesNotExistError, RepositoryError, VCSError

from kallithea.lib.vcs.nodes import (

    AddedFileNodesGenerator, ChangedFileNodesGenerator, DirNode, FileNode, NodeKind, RemovedFileNodesGenerator, RootNode, SubModuleNode)

from kallithea.lib.vcs.utils import date_fromtimestamp, safe_int, safe_str, safe_unicode

from kallithea.lib.vcs.utils.lazy import LazyProperty

class GitChangeset(BaseChangeset):

    """

    Represents state of the repository at a revision.

    """

    def __init__(self, repository, revision):

        self._stat_modes = {}

        self.repository = repository

        revision = safe_str(revision)

        try:

            commit = self.repository._repo[revision]

            if isinstance(commit, objects.Tag):

                revision = safe_str(commit.object[1])

                commit = self.repository._repo.get_object(commit.object[1])

        except KeyError:

            raise RepositoryError("Cannot get object with id %s" % revision)

        self.raw_id = revision

        self.id = self.raw_id

        self.short_id = self.raw_id[:12]

        self._commit = commit

        self._tree_id = commit.tree

        self._committer_property = 'committer'

        self._author_property = 'author'

        self._date_property = 'commit_time'

        self._date_tz_property = 'commit_timezone'

        self.nodes = {}

        self._paths = {}

    @LazyProperty

    def bookmarks(self):

        return ()

    @LazyProperty

    def message(self):

        return safe_unicode(self._commit.message)

    @LazyProperty

    def committer(self):

        return safe_unicode(getattr(self._commit, self._committer_property))

    @LazyProperty

    def author(self):

        return safe_unicode(getattr(self._commit, self._author_property))

    @LazyProperty

    def date(self):

        return date_fromtimestamp(getattr(self._commit, self._date_property),

                                  getattr(self._commit, self._date_tz_property))

    @LazyProperty

    def _timestamp(self):

        return getattr(self._commit, self._date_property)

    @LazyProperty

    def status(self):

        """

        Returns modified, added, removed, deleted files for current changeset

        """

        return self.changed, self.added, self.removed

    @LazyProperty

    def tags(self):

        _tags = []

        for tname, tsha in self.repository.tags.iteritems():

            if tsha == self.raw_id:

                _tags.append(tname)

        return _tags

    @LazyProperty

    def branch(self):

        # Note: This function will return one branch name for the changeset -

        # that might not make sense in Git where branches() is a better match

        # for the basic model

        heads = self.repository._heads(reverse=False)

        if ref:

            return safe_unicode(ref)

    @LazyProperty

    def branches(self):

        heads = self.repository._heads(reverse=True)

        return [b for b in heads if heads[b] == self.raw_id] # FIXME: Inefficient ... and returning None!

    def _fix_path(self, path):

        """

        Paths are stored without trailing slash so we need to get rid off it if

        needed.

        """

        if path.endswith('/'):

            path = path.rstrip('/')

        return path

    def _get_id_for_path(self, path):

        path = safe_str(path)

        # FIXME: Please, spare a couple of minutes and make those codes cleaner;

        if path not in self._paths:

            path = path.strip('/')

            # set root tree

            tree = self.repository._repo[self._tree_id]

            if path == '':

                self._paths[''] = tree.id

                return tree.id

            splitted = path.split('/')

            dirs, name = splitted[:-1], splitted[-1]

            curdir = ''

            # initially extract things from root dir

            for item, stat, id in tree.iteritems():

                if curdir:

                    name = '/'.join((curdir, item))

                else:

                    name = item

                self._paths[name] = id

                self._stat_modes[name] = stat

            for dir in dirs:

                if curdir:

                    curdir = '/'.join((curdir, dir))

                else:

                    curdir = dir

                dir_id = None

                for item, stat, id in tree.iteritems():

                    if dir == item:

            if _GL(self._stat_modes.get(path)):

                tree = self.repository._repo[self._tree_id]

                cf = ConfigFile.from_file(BytesIO(self.repository._repo.get_object(tree['.gitmodules'][1]).data))

                url = cf.get(('submodule', path), 'url')

                node = SubModuleNode(path, url=url, changeset=id_,

                                     alias=self.repository.alias)

            else:

                obj = self.repository._repo.get_object(id_)

                if isinstance(obj, objects.Tree):

                    if path == '':

                        node = RootNode(changeset=self)

                    else:

                        node = DirNode(path, changeset=self)

                    node._tree = obj

                elif isinstance(obj, objects.Blob):

                    node = FileNode(path, changeset=self)

                    node._blob = obj

                else:

                    raise NodeDoesNotExistError("There is no file nor directory "

                        "at the given path: '%s' at revision %s"

                        % (path, self.short_id))

            # cache node

            self.nodes[path] = node

        return self.nodes[path]

    @LazyProperty

    def affected_files(self):

        """

        Gets a fast accessible file changes for given changeset

        """

        added, modified, deleted = self._changes_cache

        return list(added.union(modified).union(deleted))

    @LazyProperty

    def _changes_cache(self):

        added = set()

        modified = set()

        deleted = set()

        _r = self.repository._repo

        parents = self.parents

        if not self.parents:

            parents = [EmptyChangeset()]

        for parent in parents:

            if isinstance(parent, EmptyChangeset):

                oid = None

            else:

            for (oldpath, newpath), (_, _), (_, _) in changes:

                if newpath and oldpath:

                    modified.add(newpath)

                elif newpath and not oldpath:

                    added.add(newpath)

                elif not newpath and oldpath:

                    deleted.add(oldpath)

        return added, modified, deleted

    def _get_paths_for_status(self, status):

        """

        Returns sorted list of paths for given ``status``.

        :param status: one of: *added*, *modified* or *deleted*

        """

        added, modified, deleted = self._changes_cache

        return sorted({

            'added': list(added),

            'modified': list(modified),

            'deleted': list(deleted)}[status]

        )

    @LazyProperty

    def added(self):

        """

        Returns list of added ``FileNode`` objects.

        """

        if not self.parents:

            return list(self._get_file_nodes())

        return AddedFileNodesGenerator([n for n in

                                self._get_paths_for_status('added')], self)

    @LazyProperty

    def changed(self):

        """

        Returns list of modified ``FileNode`` objects.

        """

        if not self.parents:

            return []

        return ChangedFileNodesGenerator([n for n in

                                self._get_paths_for_status('modified')], self)

    @LazyProperty

    def removed(self):

        """

        Returns list of removed ``FileNode`` objects.

        """

        if not self.parents: