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):

    """

    """

    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))

            ['rev-list', rev_filter, '--children']

        )

        children = []

        pat = re.compile(r'^%s' % self.raw_id)

        for l in so.splitlines():

            if pat.match(l):

                childs = l.split(' ')[1:]

                children.extend(childs)

        return [self.repository.get_changeset(cs) for cs in children]

    def next(self, branch=None):

        if branch and self.branch != branch:

            raise VCSError('Branch option used on changeset not belonging '

                           'to that branch')

        cs = self

        while True:

            try:

                next_ = cs.revision + 1

                next_rev = cs.repository.revisions[next_]

            except IndexError:

                raise ChangesetDoesNotExistError

            cs = cs.repository.get_changeset(next_rev)

            if not branch or branch == cs.branch:

                return cs

    def prev(self, branch=None):

        if branch and self.branch != branch:

            raise VCSError('Branch option used on changeset not belonging '

                           'to that branch')

        cs = self

        while True:

            try:

                prev_ = cs.revision - 1

                if prev_ < 0:

                    raise IndexError

                prev_rev = cs.repository.revisions[prev_]

            except IndexError:

                raise ChangesetDoesNotExistError

            cs = cs.repository.get_changeset(prev_rev)

            if not branch or branch == cs.branch:

                return cs

    def diff(self, ignore_whitespace=True, context=3):

        rev1 = self.parents[0] if self.parents else self.repository.EMPTY_CHANGESET

        rev2 = self

        return ''.join(self.repository.get_diff(rev1, rev2,

                                    ignore_whitespace=ignore_whitespace,

                                    context=context))

    def get_file_mode(self, path):

        """

        Returns stat mode of the file at the given ``path``.

        """

        # ensure path is traversed

        path = safe_str(path)

        self._get_id_for_path(path)

        return self._stat_modes[path]

    def get_file_content(self, path):

        """

        Returns content of the file at given ``path``.

        """

        id = self._get_id_for_path(path)

        blob = self.repository._repo[id]

        return blob.as_pretty_string()

    def get_file_size(self, path):

        """

        Returns size of the file at given ``path``.

        """

        id = self._get_id_for_path(path)

        blob = self.repository._repo[id]

        return blob.raw_length()

    def get_file_changeset(self, path):

        """

        Returns last commit of the file at the given ``path``.

        """

        return self.get_file_history(path, limit=1)[0]

    def get_file_history(self, path, limit=None):

        """

        Returns history of file as reversed list of ``Changeset`` objects for

        which file at given ``path`` has been modified.

        TODO: This function now uses os underlying 'git' and 'grep' commands

        which is generally not good. Should be replaced with algorithm

        iterating commits.

        """

        self._get_filectx(path)

        cs_id = safe_str(self.id)

        """

        Returns history of file as reversed list of ``Changeset`` objects for

        which file at given ``path`` has been modified.

        """

        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 path != '':

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

            else:

                obj_path = name

            if objects.S_ISGITLINK(stat):

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

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

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

                dirnodes.append(SubModuleNode(obj_path, url=url, changeset=id,

                                              alias=als))

                continue

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

            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)):

                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 "

                        % (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

import os

import posixpath

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

from kallithea.lib.vcs.conf import settings

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

from kallithea.lib.vcs.nodes import (

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

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

from kallithea.lib.vcs.utils.hgcompat import archival, hex, obsutil

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

from kallithea.lib.vcs.utils.paths import get_dirs_for_path

class MercurialChangeset(BaseChangeset):

    """

    """

    def __init__(self, repository, revision):

        self.repository = repository

        assert isinstance(revision, basestring), repr(revision)

        self.raw_id = revision

        self._ctx = repository._repo[revision]

        self.revision = self._ctx._rev

        self.nodes = {}

    @LazyProperty

    def tags(self):

        return [safe_unicode(tag) for tag in self._ctx.tags()]

    @LazyProperty

    def branch(self):

        return safe_unicode(self._ctx.branch())

    @LazyProperty

    def branches(self):

        return [safe_unicode(self._ctx.branch())]

    @LazyProperty

    def closesbranch(self):

        return self._ctx.closesbranch()

    @LazyProperty

    def obsolete(self):

        return self._ctx.obsolete()

    @LazyProperty

    def bumped(self):

        try:

            return self._ctx.phasedivergent()

        except AttributeError: # renamed in Mercurial 4.6 (9fa874fb34e1)

            return self._ctx.bumped()

    @LazyProperty

    def divergent(self):

        try:

            return self._ctx.contentdivergent()

        except AttributeError: # renamed in Mercurial 4.6 (8b2d7684407b)

            return self._ctx.divergent()

    @LazyProperty

    def extinct(self):

        return self._ctx.extinct()

        return [self.repository.get_changeset(parent.rev())

                for parent in self._ctx.parents() if parent.rev() >= 0]

    @LazyProperty

    def children(self):

        """

        Returns list of children changesets.

        """

        return [self.repository.get_changeset(child.rev())

                for child in self._ctx.children() if child.rev() >= 0]

    def next(self, branch=None):

        if branch and self.branch != branch:

            raise VCSError('Branch option used on changeset not belonging '

                           'to that branch')

        cs = self

        while True:

            try:

                next_ = cs.repository.revisions.index(cs.raw_id) + 1

                next_rev = cs.repository.revisions[next_]

            except IndexError:

                raise ChangesetDoesNotExistError

            cs = cs.repository.get_changeset(next_rev)

            if not branch or branch == cs.branch:

                return cs

    def prev(self, branch=None):

        if branch and self.branch != branch:

            raise VCSError('Branch option used on changeset not belonging '

                           'to that branch')

        cs = self

        while True:

            try:

                prev_ = cs.repository.revisions.index(cs.raw_id) - 1

                if prev_ < 0:

                    raise IndexError

                prev_rev = cs.repository.revisions[prev_]

            except IndexError:

                raise ChangesetDoesNotExistError

            cs = cs.repository.get_changeset(prev_rev)

            if not branch or branch == cs.branch:

                return cs

    def diff(self):

        return ''.join(self._ctx.diff())

    def _fix_path(self, path):

        """

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

        needed. Also mercurial keeps filenodes as str so we need to decode

        from unicode to str

        """

        if path.endswith('/'):

            path = path.rstrip('/')

        return safe_str(path)

    def _get_kind(self, path):

        path = self._fix_path(path)

        if path in self._file_paths:

            return NodeKind.FILE

        elif path in self._dir_paths:

            return NodeKind.DIR

        else:

            raise ChangesetError("Node does not exist at the given path '%s'"

                % (path))

    def _get_filectx(self, path):

        path = self._fix_path(path)

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

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

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

        return self._ctx.filectx(path)

    def _extract_submodules(self):

        """

        returns a dictionary with submodule information from substate file

        of hg repository

        """

        return self._ctx.substate

    def get_file_mode(self, path):

        """

        Returns stat mode of the file at the given ``path``.

        """

        fctx = self._get_filectx(path)

        if 'x' in fctx.flags():

            return 0o100755

        else:

            return 0o100644

    def get_file_content(self, path):

        return self.get_file_history(path, limit=1)[0]

    def get_file_history(self, path, limit=None):

        """

        Returns history of file as reversed list of ``Changeset`` objects for

        which file at given ``path`` has been modified.

        """

        fctx = self._get_filectx(path)

        hist = []

        cnt = 0

        for cs in reversed([x for x in fctx.filelog()]):

            cnt += 1

            hist.append(hex(fctx.filectx(cs).node()))

            if limit is not None and cnt == limit:

                break

        return [self.repository.get_changeset(node) for node in hist]

    def get_file_annotate(self, path):

        """

        Returns a generator of four element tuples with

            lineno, sha, changeset lazy loader and line

        """

        annotations = self._get_filectx(path).annotate()

        try:

            annotation_lines = [(annotateline.fctx, annotateline.text) for annotateline in annotations]

        except AttributeError: # annotateline was introduced in Mercurial 4.6 (b33b91ca2ec2)

            annotation_lines = [(aline.fctx, l) for aline, l in annotations]

        for i, (fctx, l) in enumerate(annotation_lines):

            sha = fctx.hex()

            yield (i + 1, sha, lambda sha=sha, l=l: self.repository.get_changeset(sha), l)

    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 stream is None:

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

                           ' with archival data')

        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")

        archival.archive(self.repository._repo, stream, self.raw_id,

                         kind, prefix=prefix, subrepos=subrepos)

    def get_nodes(self, path):

        """

        Returns combined ``DirNode`` and ``FileNode`` objects list representing

        state of changeset at the given ``path``. If node at the given ``path``

        is not instance of ``DirNode``, ChangesetError would be raised.

        """

        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)

        filenodes = [FileNode(f, changeset=self) for f in self._file_paths

            if os.path.dirname(f) == path]

        dirs = path == '' and '' or [d for d in self._dir_paths

            if d and posixpath.dirname(d) == path]

        dirnodes = [DirNode(d, changeset=self) for d in dirs

            if os.path.dirname(d) == path]

        als = self.repository.alias

        for k, vals in self._extract_submodules().iteritems():

            #vals = url,rev,type

            loc = vals[0]

            cs = vals[1]

            dirnodes.append(SubModuleNode(k, url=loc, changeset=cs,

                                          alias=als))

        nodes = dirnodes + filenodes

        for node in nodes:

            self.nodes[node.path] = node

        nodes.sort()

        return nodes

    def get_node(self, path):

        """

        Returns ``Node`` object from the given ``path``. If there is no node at

        the given ``path``, ``ChangesetError`` would be raised.

        """

        path = self._fix_path(path)

        if path not in self.nodes:

            if path in self._file_paths:

                node = FileNode(path, changeset=self)

            elif path in self._dir_paths or path in self._dir_paths:

                if path == '':

                    node = RootNode(changeset=self)

                else:

                    node = DirNode(path, changeset=self)

            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

        """

        return self._ctx.files()

    @property

    def added(self):

        """

        Returns list of added ``FileNode`` objects.

        """

        return AddedFileNodesGenerator([n for n in self.status[1]], self)

    @property

    def changed(self):

        """

        Returns list of modified ``FileNode`` objects.

        """

        return ChangedFileNodesGenerator([n for n in self.status[0]], self)

    @property

    def removed(self):

        """

        Returns list of removed ``FileNode`` objects.

        """

        return RemovedFileNodesGenerator([n for n in self.status[2]], self)

    @LazyProperty

    def extra(self):

        return self._ctx.extra()