import re

from itertools import chain

from dulwich import objects

from subprocess import Popen, PIPE

from kallithea.lib.vcs.conf import settings

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

from kallithea.lib.vcs.exceptions import (

    RepositoryError, ChangesetError, NodeDoesNotExistError, VCSError,

    ChangesetDoesNotExistError, ImproperArchiveTypeError

)

from kallithea.lib.vcs.nodes import (

    FileNode, DirNode, NodeKind, RootNode, SubModuleNode,

    ChangedFileNodesGenerator, AddedFileNodesGenerator, RemovedFileNodesGenerator

)

from kallithea.lib.vcs.utils import (

    safe_unicode, safe_str, safe_int, date_fromtimestamp

)

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

class GitChangeset(BaseChangeset):

    """

    Represents state of the repository at single 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.revision = repository.revisions.index(revision)

        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)

        ref = heads.get(self.raw_id)

        if ref:

            return safe_unicode(ref)

        """

        self._get_filectx(path)

        from dulwich.walk import Walker

        include = [self.id]

        walker = Walker(self.repository._repo.object_store, include,

                        paths=[path], max_entries=1)

        return [self.repository.get_changeset(sha)

                for sha in (x.commit.id for x in walker)]

    def get_file_annotate(self, path):

        """

        Returns a generator of four element tuples with

            lineno, sha, changeset lazy loader and line

        TODO: This function now uses os underlying 'git' command which is

        generally not good. Should be replaced with algorithm iterating

        commits.

        """

        cmd = ['blame', '-l', '--root', '-r', self.id, '--', path]

        # -l     ==> outputs long shas (and we need all 40 characters)

        # --root ==> doesn't put '^' character for boundaries

        # -r sha ==> blames for the given revision

        so, se = self.repository.run_git_command(cmd)

        for i, blame_line in enumerate(so.split('\n')[:-1]):

            ln_no = i + 1

            sha, line = re.split(r' ', blame_line, 1)

            yield (ln_no, sha, lambda: self.repository.get_changeset(sha), line)

    def fill_archive(self, stream=None, kind='tgz', prefix=None,

                     subrepos=False):

        """

        Fills up given stream.

        :param stream: file like object.

        :param kind: one of following: ``zip``, ``tgz`` or ``tbz2``.

            Default: ``tgz``.

        :param prefix: name of root directory in archive.

            Default is repository name and changeset's raw_id joined with dash

            (``repo-tip.<KIND>``).

        :param subrepos: include subrepos in this archive.

        :raise ImproperArchiveTypeError: If given kind is wrong.

        :raise VcsError: If given stream is None

        """

        allowed_kinds = settings.ARCHIVE_SPECS.keys()

        if kind not in allowed_kinds:

            raise ImproperArchiveTypeError('Archive kind not supported use one'

                'of %s', allowed_kinds)

        if prefix is None:

            prefix = '%s-%s' % (self.repository.name, self.short_id)

        elif prefix.startswith('/'):

            raise VCSError("Prefix cannot start with leading slash")

        elif prefix.strip() == '':

            raise VCSError("Prefix cannot be empty")

        if kind == 'zip':

            frmt = 'zip'

        else:

            frmt = 'tar'

        _git_path = settings.GIT_EXECUTABLE_PATH

        cmd = '%s archive --format=%s --prefix=%s/ %s' % (_git_path,

                                                frmt, prefix, self.raw_id)

        if kind == 'tgz':

            cmd += ' | gzip -9'

        elif kind == 'tbz2':

            cmd += ' | bzip2 -9'

        if stream is None:

            raise VCSError('You need to pass in a valid stream for filling'

                           ' with archival data')

        popen = Popen(cmd, stdout=PIPE, stderr=PIPE, shell=True,

                      cwd=self.repository.path)

        buffer_size = 1024 * 8

        chunk = popen.stdout.read(buffer_size)

        while chunk:

            stream.write(chunk)

            chunk = popen.stdout.read(buffer_size)

        # Make sure all descriptors would be read

        popen.communicate()

    def get_nodes(self, path):

        if self._get_kind(path) != NodeKind.DIR:

            raise ChangesetError("Directory does not exist for revision %s at "

                " '%s'" % (self.revision, path))

        path = self._fix_path(path)

        id = self._get_id_for_path(path)

        tree = self.repository._repo[id]

        dirnodes = []

        filenodes = []

        als = self.repository.alias

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

            if objects.S_ISGITLINK(stat):

                                              alias=als))

                continue

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

            if path != '':

                obj_path = '/'.join((path, name))

            else:

                obj_path = name

            if obj_path not in self._stat_modes:

                self._stat_modes[obj_path] = stat

            if isinstance(obj, objects.Tree):

                dirnodes.append(DirNode(obj_path, changeset=self))

            elif isinstance(obj, objects.Blob):

                filenodes.append(FileNode(obj_path, changeset=self, mode=stat))

            else:

                raise ChangesetError("Requested object should be Tree "

                                     "or Blob, is %r" % type(obj))

        nodes = dirnodes + filenodes

        for node in nodes:

            if node.path not in self.nodes:

                self.nodes[node.path] = node

        nodes.sort()

        return nodes

    def get_node(self, path):

        if isinstance(path, unicode):

            path = path.encode('utf-8')

        path = self._fix_path(path)

        if path not in self.nodes:

            try:

                id_ = self._get_id_for_path(path)

            except ChangesetError:

                raise NodeDoesNotExistError("Cannot find one of parents' "

                    "directories for a given path: %s" % path)

            _GL = lambda m: m and objects.S_ISGITLINK(m)

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

                                     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 _diff_name_status(self):

        output = []

        for parent in self.parents:

            cmd = ['diff', '--name-status', parent.raw_id, self.raw_id,

                   '--encoding=utf8']

            so, se = self.repository.run_git_command(cmd)

            output.append(so.strip())

        return '\n'.join(output)

    @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:

                oid = _r[parent.raw_id].tree

            changes = _r.object_store.tree_changes(oid, _r[self.raw_id].tree)

            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)

        stdout, stderr = Command(TESTS_TMP_PATH).execute('git clone', clone_url, _get_tmp_dir())

        assert 'Cloning into' in stdout + stderr

        assert stderr == '' or stdout == ''

    @parametrize('repo_type, repo_name', [

                #('git',      GIT_REPO), # git hooks doesn't work like hg hooks

                ('hg',       HG_REPO),

    ])

    def test_custom_hooks_preoutgoing(self, testhook_cleanup, webserver, testfork, repo_type, repo_name):

        # set prechangegroup to failing hook (returns True)

        Ui.create_or_update_hook('preoutgoing.testhook', 'python:kallithea.tests.fixture.failing_test_hook')

        Session().commit()

        # clone repo

        clone_url = webserver.repo_url(testfork[repo_type], username=TEST_USER_ADMIN_LOGIN, password=TEST_USER_ADMIN_PASS)

        dest_dir = _get_tmp_dir()

        stdout, stderr = Command(TESTS_TMP_PATH) \

            .execute('%s clone' % repo_type, clone_url, dest_dir, ignoreReturnCode=True)

        if repo_type == 'hg':

            assert 'preoutgoing.testhook hook failed' in stdout

        elif repo_type == 'git':

            assert 'error: 406' in stderr

    @parametrize('repo_type, repo_name', [

                #('git',      GIT_REPO), # git hooks doesn't work like hg hooks

                ('hg',       HG_REPO),

    ])

    def test_custom_hooks_prechangegroup(self, testhook_cleanup, webserver, testfork, repo_type, repo_name):

        # set prechangegroup to failing hook (returns True)

        Ui.create_or_update_hook('prechangegroup.testhook', 'python:kallithea.tests.fixture.failing_test_hook')

        Session().commit()

        # clone repo

        clone_url = webserver.repo_url(testfork[repo_type], username=TEST_USER_ADMIN_LOGIN, password=TEST_USER_ADMIN_PASS)

        dest_dir = _get_tmp_dir()

        stdout, stderr = Command(TESTS_TMP_PATH).execute('%s clone' % repo_type, clone_url, dest_dir)

        stdout, stderr = _add_files_and_push(webserver, repo_type, dest_dir,

                                             username=TEST_USER_ADMIN_LOGIN,

                                             password=TEST_USER_ADMIN_PASS,

                                             ignoreReturnCode=True)

        assert 'failing_test_hook failed' in stdout + stderr

        assert 'Traceback' not in stdout + stderr

        assert 'prechangegroup.testhook hook failed' in stdout + stderr

        # there are still outgoing changesets

        stdout, stderr = _check_outgoing(repo_type, dest_dir, clone_url)

        assert stdout != ''

        # set prechangegroup hook to exception throwing method

        Ui.create_or_update_hook('prechangegroup.testhook', 'python:kallithea.tests.fixture.exception_test_hook')

        Session().commit()

        # re-try to push

        stdout, stderr = Command(dest_dir).execute('%s push' % repo_type, clone_url, ignoreReturnCode=True)

        if repo_type == 'hg':

            # like with 'hg serve...' 'HTTP Error 500: INTERNAL SERVER ERROR' should be returned

            assert 'HTTP Error 500: INTERNAL SERVER ERROR' in stderr

        elif repo_type == 'git':

            assert 'exception_test_hook threw an exception' in stderr

        # there are still outgoing changesets

        stdout, stderr = _check_outgoing(repo_type, dest_dir, clone_url)

        assert stdout != ''

        # set prechangegroup hook to method that returns False

        Ui.create_or_update_hook('prechangegroup.testhook', 'python:kallithea.tests.fixture.passing_test_hook')

        Session().commit()

        # re-try to push

        stdout, stderr = Command(dest_dir).execute('%s push' % repo_type, clone_url, ignoreReturnCode=True)

        assert 'passing_test_hook succeeded' in stdout + stderr

        assert 'Traceback' not in stdout + stderr

        assert 'prechangegroup.testhook hook failed' not in stdout + stderr

        # no more outgoing changesets

        stdout, stderr = _check_outgoing(repo_type, dest_dir, clone_url)

        assert stdout == ''

        assert stderr == ''

    def test_add_submodule(self, webserver):

        dest_dir = _get_tmp_dir()

        clone_url = webserver.repo_url(GIT_REPO)

        # GIT_REPO should be untouched for other tests so create a fork

        fork_name = '%s_fork%s' % (GIT_REPO, _RandomNameSequence().next())

        fixture.create_fork(GIT_REPO, fork_name)

        fork_url = webserver.repo_url(fork_name)

        # add submodule

        stdout, stderr = Command(TESTS_TMP_PATH).execute('git clone', fork_url, dest_dir)

        stdout, stderr = Command(dest_dir).execute('git submodule add', clone_url, 'testsubmodule')

        stdout, stderr = Command(dest_dir).execute('git commit -am "added testsubmodule pointing to', clone_url, '"')

        stdout, stderr = Command(dest_dir).execute('git push', fork_url, 'master')

        # check for testsubmodule link in files page

        self.log_user()

        response = self.app.get(url(controller='files', action='index',

                                    repo_name=fork_name,

                                    revision='tip',

                                    f_path='/'))

        # check that following a submodule link actually works - and redirects

        response = self.app.get(url(controller='files', action='index',

                                    repo_name=fork_name,

                                    revision='tip',

                                    f_path='/testsubmodule'),

                                status=500) # BUG