# -*- coding: utf-8 -*-

"""

    rhodecode.controllers.files

    ~~~~~~~~~~~~~~~~~~~~~~~~~~~

    Files controller for RhodeCode

    :created_on: Apr 21, 2010

    :author: marcink

    :copyright: (C) 2010-2012 Marcin Kuzminski <marcin@python-works.com>

    :license: GPLv3, see COPYING for more details.

"""

# This program is free software: you can redistribute it and/or modify

# it under the terms of the GNU General Public License as published by

# the Free Software Foundation, either version 3 of the License, or

# (at your option) any later version.

#

# This program is distributed in the hope that it will be useful,

# but WITHOUT ANY WARRANTY; without even the implied warranty of

# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

# GNU General Public License for more details.

#

# You should have received a copy of the GNU General Public License

# along with this program.  If not, see <http://www.gnu.org/licenses/>.

from __future__ import with_statement

import os

import logging

import traceback

import tempfile

from pylons import request, response, tmpl_context as c, url

from pylons.i18n.translation import _

from pylons.controllers.util import redirect

from pylons.decorators import jsonify

from rhodecode.lib import diffs

from rhodecode.lib import helpers as h

from rhodecode.lib.compat import OrderedDict

from rhodecode.lib.utils2 import convert_line_endings, detect_mode, safe_str

from rhodecode.lib.auth import LoginRequired, HasRepoPermissionAnyDecorator

from rhodecode.lib.base import BaseRepoController, render

from rhodecode.lib.utils import EmptyChangeset

from rhodecode.lib.vcs.conf import settings

from rhodecode.lib.vcs.exceptions import RepositoryError, \

    ChangesetDoesNotExistError, EmptyRepositoryError, \

    ImproperArchiveTypeError, VCSError, NodeAlreadyExistsError

from rhodecode.lib.vcs.nodes import FileNode

from rhodecode.model.repo import RepoModel

from rhodecode.model.scm import ScmModel

from rhodecode.model.db import Repository

from rhodecode.controllers.changeset import anchor_url, _ignorews_url,\

    _context_url, get_line_ctx, get_ignore_ws

log = logging.getLogger(__name__)

class FilesController(BaseRepoController):

    def __before__(self):

        super(FilesController, self).__before__()

        c.cut_off_limit = self.cut_off_limit

    def __get_cs_or_redirect(self, rev, repo_name, redirect_after=True):

        """

        Safe way to get changeset if error occur it redirects to tip with

        proper message

        :param rev: revision to fetch

        :param repo_name: repo name to redirect after

        """

        try:

            return c.rhodecode_repo.get_changeset(rev)

        except EmptyRepositoryError, e:

            if not redirect_after:

                return None

            url_ = url('files_add_home',

                       repo_name=c.repo_name,

                       revision=0, f_path='')

            add_new = '<a href="%s">[%s]</a>' % (url_, _('add new'))

            h.flash(h.literal(_('There are no files yet %s' % add_new)),

                    category='warning')

            redirect(h.url('summary_home', repo_name=repo_name))

        except RepositoryError, e:

            h.flash(str(e), category='warning')

            redirect(h.url('files_home', repo_name=repo_name, revision='tip'))

    def __get_filenode_or_redirect(self, repo_name, cs, path):

        """

        Returns file_node, if error occurs or given path is directory,

        it'll redirect to top level path

        :param repo_name: repo_name

        :param cs: given changeset

        :param path: path to lookup

        """

        try:

            file_node = cs.get_node(path)

            if file_node.is_dir():

                raise RepositoryError('given path is a directory')

        except RepositoryError, e:

            h.flash(str(e), category='warning')

            redirect(h.url('files_home', repo_name=repo_name,

                           revision=cs.raw_id))

        post_revision = request.POST.get('at_rev', None)

        if post_revision:

            cs = self.__get_cs_or_redirect(post_revision, repo_name)

            redirect(url('files_home', repo_name=c.repo_name,

                         revision=cs.raw_id, f_path=f_path))

        c.changeset = self.__get_cs_or_redirect(revision, repo_name)

        c.branch = request.GET.get('branch', None)

        c.f_path = f_path

        c.annotate = annotate

        cur_rev = c.changeset.revision

        # prev link

        try:

            prev_rev = c.rhodecode_repo.get_changeset(cur_rev).prev(c.branch)

            c.url_prev = url('files_home', repo_name=c.repo_name,

                         revision=prev_rev.raw_id, f_path=f_path)

            if c.branch:

                c.url_prev += '?branch=%s' % c.branch

        except (ChangesetDoesNotExistError, VCSError):

            c.url_prev = '#'

        # next link

        try:

            next_rev = c.rhodecode_repo.get_changeset(cur_rev).next(c.branch)

            c.url_next = url('files_home', repo_name=c.repo_name,

                     revision=next_rev.raw_id, f_path=f_path)

            if c.branch:

                c.url_next += '?branch=%s' % c.branch

        except (ChangesetDoesNotExistError, VCSError):

            c.url_next = '#'

        # files or dirs

        try:

            c.file = c.changeset.get_node(f_path)

            if c.file.is_file():

                _hist = c.changeset.get_file_history(f_path)

                c.file_history = self._get_node_history(c.changeset, f_path,

                                                        _hist)

                c.authors = []

                for a in set([x.author for x in _hist]):

                    c.authors.append((h.email(a), h.person(a)))

            else:

                c.authors = c.file_history = []

        except RepositoryError, e:

            h.flash(str(e), category='warning')

            redirect(h.url('files_home', repo_name=repo_name,

        return render('files/files.html')

    @LoginRequired()

    @HasRepoPermissionAnyDecorator('repository.read', 'repository.write',

                                   'repository.admin')

    def rawfile(self, repo_name, revision, f_path):

        cs = self.__get_cs_or_redirect(revision, repo_name)

        file_node = self.__get_filenode_or_redirect(repo_name, cs, f_path)

        response.content_disposition = 'attachment; filename=%s' % \

            safe_str(f_path.split(Repository.url_sep())[-1])

        response.content_type = file_node.mimetype

        return file_node.content

    @LoginRequired()

    @HasRepoPermissionAnyDecorator('repository.read', 'repository.write',

                                   'repository.admin')

    def raw(self, repo_name, revision, f_path):

        cs = self.__get_cs_or_redirect(revision, repo_name)

        file_node = self.__get_filenode_or_redirect(repo_name, cs, f_path)

        raw_mimetype_mapping = {

            # map original mimetype to a mimetype used for "show as raw"

            # you can also provide a content-disposition to override the

            # default "attachment" disposition.

            # orig_type: (new_type, new_dispo)

            # show images inline:

            'image/x-icon': ('image/x-icon', 'inline'),

            'image/png': ('image/png', 'inline'),

            'image/gif': ('image/gif', 'inline'),

            'image/jpeg': ('image/jpeg', 'inline'),

            'image/svg+xml': ('image/svg+xml', 'inline'),

        }

        mimetype = file_node.mimetype

        try:

            mimetype, dispo = raw_mimetype_mapping[mimetype]

        except KeyError:

            # we don't know anything special about this, handle it safely

            if file_node.is_binary:

                # do same as download raw for binary files

                mimetype, dispo = 'application/octet-stream', 'attachment'

            else:

                # do not just use the original mimetype, but force text/plain,

                # otherwise it would serve text/html and that might be unsafe.

import re

from itertools import chain

from dulwich import objects

from subprocess import Popen, PIPE

from rhodecode.lib.vcs.conf import settings

from rhodecode.lib.vcs.exceptions import RepositoryError

from rhodecode.lib.vcs.exceptions import ChangesetError

from rhodecode.lib.vcs.exceptions import NodeDoesNotExistError

from rhodecode.lib.vcs.exceptions import VCSError

from rhodecode.lib.vcs.exceptions import ChangesetDoesNotExistError

from rhodecode.lib.vcs.exceptions import ImproperArchiveTypeError

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

from rhodecode.lib.vcs.nodes import FileNode, DirNode, NodeKind, RootNode, \

    RemovedFileNode, SubModuleNode

from rhodecode.lib.vcs.utils import safe_unicode

from rhodecode.lib.vcs.utils import date_fromtimestamp

from rhodecode.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

        self.raw_id = revision

        self.short_id = self.raw_id[:12]

        self.id = self.raw_id

        try:

            commit = self.repository._repo.get_object(self.raw_id)

        except KeyError:

            raise RepositoryError("Cannot get object with id %s" % self.raw_id)

        self._commit = commit

        self.message = safe_unicode(commit.message)

        #self.branch = None

        self.tags = []

        self.nodes = {}

        self._paths = {}

    @LazyProperty

    def author(self):

    @LazyProperty

    def date(self):

    @LazyProperty

    def status(self):

        """

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

        """

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

    @LazyProperty

    def branch(self):

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

        ref = heads.get(self.raw_id)

        if ref:

            return safe_unicode(ref)

    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):

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

        if not path in self._paths:

            path = path.strip('/')

            # set root tree

            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:

                        dir_id = id

                if dir_id:

                    # Update tree

                    tree = self.repository._repo[dir_id]

                    if not isinstance(tree, objects.Tree):

                        raise ChangesetError('%s is not a directory' % curdir)

                else:

                    raise ChangesetError('%s have not been found' % curdir)

                # cache all items from the given traversed tree

                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

            if not path in self._paths:

                raise NodeDoesNotExistError("There is no file nor directory "

                    "at the given path %r at revision %r"

                    % (path, self.short_id))

        return self._paths[path]

    def _get_kind(self, path):

        if isinstance(obj, objects.Blob):

            return NodeKind.FILE

        elif isinstance(obj, objects.Tree):

            return NodeKind.DIR

    def _get_file_nodes(self):

        return chain(*(t[2] for t in self.walk()))

    @LazyProperty

    def parents(self):

        """

        Returns list of parents changesets.

        """

        return [self.repository.get_changeset(parent)

    def next(self, branch=None):

        if branch and self.branch != branch:

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

                           'to that branch')

        def _next(changeset, branch):

            try:

                next_ = changeset.revision + 1

                next_rev = changeset.repository.revisions[next_]

            except IndexError:

                raise ChangesetDoesNotExistError

            cs = changeset.repository.get_changeset(next_rev)

            if branch and branch != cs.branch:

                return _next(cs, branch)

            return cs

        return _next(self, branch)

    def prev(self, branch=None):

        if branch and self.branch != branch:

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

                           'to that branch')

        def _prev(changeset, branch):

            try:

                prev_ = changeset.revision - 1

                if prev_ < 0:

                    raise IndexError

                prev_rev = changeset.repository.revisions[prev_]

            except IndexError:

                raise ChangesetDoesNotExistError

            cs = changeset.repository.get_changeset(prev_rev)

            if branch and branch != cs.branch:

                return _prev(cs, branch)

            return cs

        return _prev(self, branch)

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

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

        rev2 = self

    def get_nodes(self, path):

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

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

                " %r" % (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):

                dirnodes.append(SubModuleNode(name, url=None, changeset=id,

                                              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 not node.path 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 not path 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)):

            else:

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

                    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 %r at revision %r"

                        % (path, self.short_id))

            # cache node

            self.nodes[path] = node

        return self.nodes[path]

    @LazyProperty

    def affected_files(self):

        """

        Get's a fast accessible file changes for given changeset

        """

        return self.added + self.changed

    @LazyProperty

    def _diff_name_status(self):

        output = []

        for parent in self.parents:

            cmd = 'diff --name-status %s %s --encoding=utf8' % (parent.raw_id, self.raw_id)

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

            output.append(so.strip())

        return '\n'.join(output)

    def _get_paths_for_status(self, status):

        """

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

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

        """

        paths = set()

        char = status[0].upper()

        for line in self._diff_name_status.splitlines():

            if not line:

                continue

            if line.startswith(char):

                splitted = line.split(char, 1)

                if not len(splitted) == 2:

                if bare:

                    return Repo.init_bare(self.path)

                else:

                    return Repo.init(self.path)

            else:

                return Repo(self.path)

        except (NotGitRepository, OSError), err:

            raise RepositoryError(err)

    def _get_all_revisions(self):

        cmd = 'rev-list --all --reverse --date-order'

        try:

            so, se = self.run_git_command(cmd)

        except RepositoryError:

            # Can be raised for empty repositories

            return []

        return so.splitlines()

    def _get_all_revisions2(self):

        #alternate implementation using dulwich

        includes = [x[1][0] for x in self._parsed_refs.iteritems()

                    if x[1][1] != 'T']

        return [c.commit.id for c in self._repo.get_walker(include=includes)]

    def _get_revision(self, revision):

        """

        For git backend we always return integer here. This way we ensure

        that changset's revision attribute would become integer.

        """

        pattern = re.compile(r'^[[0-9a-fA-F]{12}|[0-9a-fA-F]{40}]$')

        is_bstr = lambda o: isinstance(o, (str, unicode))

        is_null = lambda o: len(o) == revision.count('0')

        if len(self.revisions) == 0:

            raise EmptyRepositoryError("There are no changesets yet")

        if revision in (None, '', 'tip', 'HEAD', 'head', -1):

            revision = self.revisions[-1]

        if ((is_bstr(revision) and revision.isdigit() and len(revision) < 12)

            or isinstance(revision, int) or is_null(revision)):

            try:

                revision = self.revisions[int(revision)]

            except:

                raise ChangesetDoesNotExistError("Revision %r does not exist "

                    "for this repository %s" % (revision, self))

        elif is_bstr(revision):

            _ref_revision = self._parsed_refs.get(revision)

            if _ref_revision:  # and _ref_revision[1] in ['H', 'RH', 'T']:

                return _ref_revision[0]

            elif not pattern.match(revision) or revision not in self.revisions:

                raise ChangesetDoesNotExistError("Revision %r does not exist "

                    "for this repository %s" % (revision, self))

        # Ensure we return full id

        if not pattern.match(str(revision)):

            raise ChangesetDoesNotExistError("Given revision %r not recognized"

                % revision)

        return revision

    def _get_archives(self, archive_name='tip'):

        for i in [('zip', '.zip'), ('gz', '.tar.gz'), ('bz2', '.tar.bz2')]:

                yield {"type": i[0], "extension": i[1], "node": archive_name}

    def _get_url(self, url):

        """

        Returns normalized url. If schema is not given, would fall to

        filesystem (``file:///``) schema.

        """

        url = str(url)

        if url != 'default' and not '://' in url:

            url = ':///'.join(('file', url))

        return url

    @LazyProperty

    def name(self):

        return os.path.basename(self.path)

    @LazyProperty

    def last_change(self):

        """

        Returns last change made on this repository as datetime object

        """

        return date_fromtimestamp(self._get_mtime(), makedate()[1])

    def _get_mtime(self):

        try:

            return time.mktime(self.get_changeset().date.timetuple())

        except RepositoryError:

            idx_loc = '' if self.bare else '.git'

            # fallback to filesystem

            in_path = os.path.join(self.path, idx_loc, "index")

            he_path = os.path.join(self.path, idx_loc, "HEAD")

            if os.path.exists(in_path):

                return os.stat(in_path).st_mtime

            else:

                return os.stat(he_path).st_mtime