update-repoinfo paster command for Kallithea

This file was forked by the Kallithea project in July 2014.

Original author and date, and relevant copyright and licensing information is below:

:created_on: Jul 14, 2012

:author: marcink

:copyright: (c) 2013 RhodeCode GmbH, and others.

:license: GPLv3, see LICENSE.md for more details.

"""

import os

import sys

import logging

import string

from kallithea.lib.utils import BasePasterCommand

from kallithea.model.db import Repository

from kallithea.model.repo import RepoModel

from kallithea.model.meta import Session

# Add location of top level folder to sys.path

from os.path import dirname as dn

rc_path = dn(dn(dn(os.path.realpath(__file__))))

sys.path.append(rc_path)

log = logging.getLogger(__name__)

class Command(BasePasterCommand):

    max_args = 1

    min_args = 1

    usage = "CONFIG_FILE"

    group_name = "Kallithea"

    takes_config_file = -1

    parser = BasePasterCommand.standard_parser(verbose=True)

    summary = "Updates repositories caches for last changeset"

    def command(self):

        #get SqlAlchemy session

        self._init_session()

        repo_update_list = map(string.strip,

                               self.options.repo_update_list.split(',')) \

                               if self.options.repo_update_list else None

            repo_list = list(Repository.query()\

                .filter(Repository.repo_name.in_(repo_update_list)))

        else:

            repo_list = Repository.getAll()

        RepoModel.update_repoinfo(repositories=repo_list)

        Session().commit()

        if self.options.invalidate_cache:

            for r in repo_list:

                r.set_invalidate()

        print 'Updated cache for %s repositories' % (len(repo_list))

    def update_parser(self):

        self.parser.add_option('--update-only',

                           action='store',

                           dest='repo_update_list',

                           help="Specifies a comma separated list of repositories "

                                "to update last commit info for. OPTIONAL")

        self.parser.add_option('--invalidate-cache',

                           action='store_true',

                           dest='invalidate_cache',

                           help="Trigger cache invalidation event for repos. "

                                "OPTIONAL")

        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)

        f_path = safe_str(path)

            cmd = ['log', '-n', str(safe_int(limit, 0)),

                   '--pretty=format:%H', '-s', cs_id, '--', f_path]

        else:

            cmd = ['log',

                   '--pretty=format:%H', '-s', cs_id, '--', f_path]

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

        ids = re.findall(r'[0-9a-fA-F]{40}', so)

        return [self.repository.get_changeset(sha) for sha in ids]

    def get_file_history_2(self, path):

        """

        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.

    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 0100755

        else:

            return 0100644

    def get_file_content(self, path):

        """

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

        """

        fctx = self._get_filectx(path)

        return fctx.data()

    def get_file_size(self, path):

        """

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

        """

        fctx = self._get_filectx(path)

        return fctx.size()

    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.

        """

        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()))

                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

        """

        fctx = self._get_filectx(path)

        for i, annotate_data in enumerate(fctx.annotate()):

            ln_no = i + 1

            sha = hex(annotate_data[0].node())

            yield (ln_no, sha, lambda: self.repository.get_changeset(sha), annotate_data[1],)

    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")

                                          'repository.admin']

        repos = [x[0] for x in filter(access_check, repos.items())]

        return Repository.query().filter(Repository.repo_name.in_(repos))

    def get_users_js(self):

        users = self.sa.query(User).filter(User.active == True).all()

        return json.dumps([

            {

                'id': u.user_id,

                'fname': h.escape(u.name),

                'lname': h.escape(u.lastname),

                'nname': u.username,

                'gravatar_lnk': h.gravatar_url(u.email, size=28),

                'gravatar_size': 14,

            } for u in users]

        )

    def get_user_groups_js(self):

        user_groups = self.sa.query(UserGroup) \

            .filter(UserGroup.users_group_active == True) \

            .options(subqueryload(UserGroup.members)) \

            .all()

        user_groups = UserGroupList(user_groups, perm_set=['usergroup.read',

                                                           'usergroup.write',

                                                           'usergroup.admin'])

        return json.dumps([

            {

                'id': gr.users_group_id,

                'grname': gr.users_group_name,

                'grmembers': len(gr.members),

            } for gr in user_groups]

        )

    @classmethod

    def _render_datatable(cls, tmpl, *args, **kwargs):

        import kallithea

        from pylons import tmpl_context as c

        from pylons.i18n.translation import _

        _tmpl_lookup = kallithea.CONFIG['pylons.app_globals'].mako_lookup

        template = _tmpl_lookup.get_template('data_table/_dt_elements.html')

        tmpl = template.get_def(tmpl)

        kwargs.update(dict(_=_, h=h, c=c))

        return tmpl.render(*args, **kwargs)

    @classmethod

    def update_repoinfo(cls, repositories=None):

            repositories = Repository.getAll()

        for repo in repositories:

            repo.update_changeset_cache()

    def get_repos_as_dict(self, repos_list=None, admin=False, perm_check=True,

                          super_user_actions=False):

        _render = self._render_datatable

        from pylons import tmpl_context as c

        def quick_menu(repo_name):

            return _render('quick_menu', repo_name)

        def repo_lnk(name, rtype, rstate, private, fork_of):

            return _render('repo_name', name, rtype, rstate, private, fork_of,

                           short_name=not admin, admin=False)

        def last_change(last_change):

            return _render("last_change", last_change)

        def rss_lnk(repo_name):

            return _render("rss", repo_name)

        def atom_lnk(repo_name):

            return _render("atom", repo_name)

        def last_rev(repo_name, cs_cache):

            return _render('revision', repo_name, cs_cache.get('revision'),

                           cs_cache.get('raw_id'), cs_cache.get('author'),

                           cs_cache.get('message'))

        def desc(desc):

            return h.urlify_text(desc, truncate=60, stylize=c.visual.stylify_metatags)

        def state(repo_state):

            return _render("repo_state", repo_state)

        def repo_actions(repo_name):

            return _render('repo_actions', repo_name, super_user_actions)

        def owner_actions(user_id, username):

            return _render('user_name', user_id, username)

        repos_data = []

        for repo in repos_list:

            if perm_check:

                # check permission at this level

                if not HasRepoPermissionAny(

                        'repository.read', 'repository.write',