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

# 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/>.

"""

kallithea.lib.auth_modules.auth_internal

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

Kallithea authentication plugin for built in internal auth

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: Created on Nov 17, 2012

:author: marcink

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

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

"""

import logging

from kallithea import EXTERN_TYPE_INTERNAL

from kallithea.lib import auth_modules

from kallithea.lib.compat import formatted_json, hybrid_property

from kallithea.model.db import User

log = logging.getLogger(__name__)

class KallitheaAuthPlugin(auth_modules.KallitheaAuthPluginBase):

    def __init__(self):

        pass

    @hybrid_property

    def name(self):

        return EXTERN_TYPE_INTERNAL

    def settings(self):

        return []

    def user_activation_state(self):

        def_user_perms = User.get_default_user().AuthUser.permissions['global']

        return 'hg.register.auto_activate' in def_user_perms

    def accepts(self, user, accepts_empty=True):

        """

        Custom accepts for this auth that doesn't accept empty users. We

        know that user exists in database.

        """

        return super(KallitheaAuthPlugin, self).accepts(user,

                                                        accepts_empty=False)

    def auth(self, userobj, username, password, settings, **kwargs):

        if not userobj:

            log.debug('userobj was:%s skipping', userobj)

            return None

        if userobj.extern_type != self.name:

            log.warning("userobj:%s extern_type mismatch got:`%s` expected:`%s`",

                     userobj, userobj.extern_type, self.name)

            return None

        user_data = {

            "username": userobj.username,

            "firstname": userobj.firstname,

            "lastname": userobj.lastname,

            "groups": [],

            "email": userobj.email,

            "admin": userobj.admin,

            "active": userobj.active,

            "active_from_extern": userobj.active,

            "extern_name": userobj.user_id,

        }

        log.debug(formatted_json(user_data))

        if userobj.active:

            from kallithea.lib import auth

            password_match = auth.KallitheaCrypto.hash_check(password, userobj.password)

            if userobj.username == User.DEFAULT_USER and userobj.active:

                log.info('user %s authenticated correctly as anonymous user',

                         username)

                return user_data

            elif userobj.username == username and password_match:

                log.info('user %s authenticated correctly', user_data['username'])

                return user_data

            log.error("user %s had a bad password", username)

            return None

        else:

            log.warning('user %s tried auth but is disabled', username)

            return None

    def get_managed_fields(self):

        # Note: 'username' should only be editable (at least for user) if self registration is enabled

        return []

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

# 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/>.

"""

kallithea.lib.auth_modules.auth_pam

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

Kallithea authentication library for PAM

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: Created on Apr 09, 2013

:author: Alexey Larikov

"""

import logging

import time

import pam

import pwd

import grp

import re

import socket

import threading

from kallithea.lib import auth_modules

from kallithea.lib.compat import formatted_json, hybrid_property

log = logging.getLogger(__name__)

# Cache to store PAM authenticated users

_auth_cache = dict()

_pam_lock = threading.Lock()

class KallitheaAuthPlugin(auth_modules.KallitheaExternalAuthPlugin):

    # PAM authnetication can be slow. Repository operations involve a lot of

    # auth calls. Little caching helps speedup push/pull operations significantly

    AUTH_CACHE_TTL = 4

    def __init__(self):

        global _auth_cache

        ts = time.time()

        cleared_cache = dict(

            [(k, v) for (k, v) in _auth_cache.items() if

             (v + KallitheaAuthPlugin.AUTH_CACHE_TTL > ts)])

        _auth_cache = cleared_cache

    @hybrid_property

    def name(self):

        return "pam"

    def settings(self):

        settings = [

            {

                "name": "service",

                "validator": self.validators.UnicodeString(strip=True),

                "type": "string",

                "description": "PAM service name to use for authentication",

                "default": "login",

                "formname": "PAM service name"

            },

            {

                "name": "gecos",

                "validator": self.validators.UnicodeString(strip=True),

                "type": "string",

                "description": "Regex for extracting user name/email etc "

                               "from Unix userinfo",

                "default": "(?P<last_name>.+),\s*(?P<first_name>\w+)",

                "formname": "Gecos Regex"

            }

        ]

        return settings

    def use_fake_password(self):

        return True

    def auth(self, userobj, username, password, settings, **kwargs):

        if username not in _auth_cache:

            # Need lock here, as PAM authentication is not thread safe

            _pam_lock.acquire()

            try:

                auth_result = pam.authenticate(username, password,

                                               settings["service"])

                # cache result only if we properly authenticated

                if auth_result:

                    _auth_cache[username] = time.time()

            finally:

                _pam_lock.release()

            if not auth_result:

                log.error("PAM was unable to authenticate user: %s", username)

                return None

        else:

            log.debug("Using cached auth for user: %s", username)

        # old attrs fetched from Kallithea database

        admin = getattr(userobj, 'admin', False)

        active = getattr(userobj, 'active', True)

        email = getattr(userobj, 'email', '') or "%s@%s" % (username, socket.gethostname())

        firstname = getattr(userobj, 'firstname', '')

        lastname = getattr(userobj, 'lastname', '')

        user_data = {

            'username': username,

            'firstname': firstname,

            'lastname': lastname,

            'groups': [g.gr_name for g in grp.getgrall() if username in g.gr_mem],

            'email': email,

            'admin': admin,

            'active': active,

            "active_from_extern": None,

            'extern_name': username,

        }

        try:

            user_pw_data = pwd.getpwnam(username)

            regex = settings["gecos"]

            match = re.search(regex, user_pw_data.pw_gecos)

            if match:

                user_data["firstname"] = match.group('first_name')

                user_data["lastname"] = match.group('last_name')

        except Exception:

            log.warning("Cannot extract additional info for PAM user %s", username)

            pass

        log.debug("pamuser: \n%s", formatted_json(user_data))

        log.info('user %s authenticated correctly', user_data['username'])

        return user_data

    def get_managed_fields(self):

        return ['username', 'password']

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

# 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/>.

"""

kallithea.lib.diffs

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

Set of diffing helpers, previously part of vcs

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: Dec 4, 2011

:author: marcink

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

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

"""

import re

import difflib

import logging

from itertools import tee, imap

from pylons.i18n.translation import _

from kallithea.lib.vcs.exceptions import VCSError

from kallithea.lib.vcs.nodes import FileNode, SubModuleNode

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

from kallithea.lib.helpers import escape

from kallithea.lib.utils2 import safe_unicode

log = logging.getLogger(__name__)

def wrap_to_table(str_):

    return '''<table class="code-difftable">

                <tr class="line no-comment">

                <td class="lineno new"></td>

                <td class="code no-comment"><pre>%s</pre></td>

                </tr>

              </table>''' % str_

def wrapped_diff(filenode_old, filenode_new, cut_off_limit=None,

                ignore_whitespace=True, line_context=3,

                enable_comments=False):

    """

    returns a wrapped diff into a table, checks for cut_off_limit and presents

    proper message

    """

    if filenode_old is None:

        filenode_old = FileNode(filenode_new.path, '', EmptyChangeset())

    if filenode_old.is_binary or filenode_new.is_binary:

        diff = wrap_to_table(_('Binary file'))

        stats = (0, 0)

        size = 0

    elif cut_off_limit != -1 and (cut_off_limit is None or

    (filenode_old.size < cut_off_limit and filenode_new.size < cut_off_limit)):

        f_gitdiff = get_gitdiff(filenode_old, filenode_new,

                                ignore_whitespace=ignore_whitespace,

                                context=line_context)

        diff_processor = DiffProcessor(f_gitdiff, format='gitdiff')

        diff = diff_processor.as_html(enable_comments=enable_comments)

        stats = diff_processor.stat()

        size = len(diff or '')

    else:

        diff = wrap_to_table(_('Changeset was too big and was cut off, use '

                               'diff menu to display this diff'))

        stats = (0, 0)

        size = 0

    if not diff:

        submodules = filter(lambda o: isinstance(o, SubModuleNode),

                            [filenode_new, filenode_old])

        if submodules:

            diff = wrap_to_table(escape('Submodule %r' % submodules[0]))

        else:

            diff = wrap_to_table(_('No changes detected'))

    cs1 = filenode_old.changeset.raw_id

    cs2 = filenode_new.changeset.raw_id

    return size, cs1, cs2, diff, stats

def get_gitdiff(filenode_old, filenode_new, ignore_whitespace=True, context=3):

    """

    Returns git style diff between given ``filenode_old`` and ``filenode_new``.

    :param ignore_whitespace: ignore whitespaces in diff

    """

    # make sure we pass in default context

    context = context or 3

    submodules = filter(lambda o: isinstance(o, SubModuleNode),

                        [filenode_new, filenode_old])

    if submodules:

        return ''

    for filenode in (filenode_old, filenode_new):

        if not isinstance(filenode, FileNode):

            raise VCSError("Given object should be FileNode object, not %s"

                % filenode.__class__)

    repo = filenode_new.changeset.repository

    old_raw_id = getattr(filenode_old.changeset, 'raw_id', repo.EMPTY_CHANGESET)

    new_raw_id = getattr(filenode_new.changeset, 'raw_id', repo.EMPTY_CHANGESET)

    vcs_gitdiff = repo.get_diff(old_raw_id, new_raw_id, filenode_new.path,

                                ignore_whitespace, context)

    return vcs_gitdiff

NEW_FILENODE = 1

DEL_FILENODE = 2

MOD_FILENODE = 3

RENAMED_FILENODE = 4

COPIED_FILENODE = 5

CHMOD_FILENODE = 6

BIN_FILENODE = 7

class DiffLimitExceeded(Exception):

    pass

class LimitedDiffContainer(object):

    def __init__(self, diff_limit, cur_diff_size, diff):

        self.diff = diff

        self.diff_limit = diff_limit

        self.cur_diff_size = cur_diff_size

    def __iter__(self):

        for l in self.diff:

            yield l

class DiffProcessor(object):

    """

    Give it a unified or git diff and it returns a list of the files that were

    mentioned in the diff together with a dict of meta information that

    can be used to render it in a HTML template.

    """

    _chunk_re = re.compile(r'^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@(.*)')

    _newline_marker = re.compile(r'^\\ No newline at end of file')

    _git_header_re = re.compile(r"""

        # has already been split on this:

        # ^diff[ ]--git

            [ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n

        (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%\n

           ^rename[ ]from[ ](?P<rename_from>.+)\n

           ^rename[ ]to[ ](?P<rename_to>.+)(?:\n|$))?

        (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))?

        (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))?

        (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+)

            \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))?

        (?:^(?P<bin_patch>GIT[ ]binary[ ]patch)(?:\n|$))?

        (?:^---[ ](a/(?P<a_file>.+?)|/dev/null)\t?(?:\n|$))?

        (?:^\+\+\+[ ](b/(?P<b_file>.+?)|/dev/null)\t?(?:\n|$))?

    """, re.VERBOSE | re.MULTILINE)

    _hg_header_re = re.compile(r"""

        # has already been split on this:

        # ^diff[ ]--git

            [ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n

        (?:^old[ ]mode[ ](?P<old_mode>\d+)\n

           ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))?

        (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%(?:\n|$))?

        (?:^rename[ ]from[ ](?P<rename_from>.+)\n

           ^rename[ ]to[ ](?P<rename_to>.+)(?:\n|$))?

        (?:^copy[ ]from[ ](?P<copy_from>.+)\n

           ^copy[ ]to[ ](?P<copy_to>.+)(?:\n|$))?

        (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))?

        (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))?

        (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+)

            \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))?

        (?:^(?P<bin_patch>GIT[ ]binary[ ]patch)(?:\n|$))?

        (?:^---[ ](a/(?P<a_file>.+?)|/dev/null)\t?(?:\n|$))?

        (?:^\+\+\+[ ](b/(?P<b_file>.+?)|/dev/null)\t?(?:\n|$))?

    """, re.VERBOSE | re.MULTILINE)

    # Used for inline highlighter word split, must match the substitutions in _escaper

    _token_re = re.compile(r'()(&amp;|&lt;|&gt;|<u>\t</u>|<u class="cr"></u>| <i></i>|\W+?)')

    _escape_re = re.compile(r'(&)|(<)|(>)|(\t)|(\r)|(?<=.)( \n| $)')

    def __init__(self, diff, vcs='hg', format='gitdiff', diff_limit=None):

        """

        :param diff:   a text in diff format

        :param vcs: type of version control hg or git

        :param format: format of diff passed, `udiff` or `gitdiff`

        :param diff_limit: define the size of diff that is considered "big"

            based on that parameter cut off will be triggered, set to None

            to show full diff

        """

        if not isinstance(diff, basestring):

            raise Exception('Diff must be a basestring got %s instead' % type(diff))

        self._diff = diff

        self._format = format

        self.adds = 0

        self.removes = 0

        # calculate diff size

        self.diff_size = len(diff)

        self.diff_limit = diff_limit

        self.cur_diff_size = 0

        self.parsed = False

        self.parsed_diff = []

        self.vcs = vcs

        if format == 'gitdiff':

            self.differ = self._highlight_line_difflib

            self._parser = self._parse_gitdiff

        else:

            self.differ = self._highlight_line_udiff

            self._parser = self._parse_udiff

    def _copy_iterator(self):

        """

        make a fresh copy of generator, we should not iterate thru

        an original as it's needed for repeating operations on

        this instance of DiffProcessor

        """

        self.__udiff, iterator_copy = tee(self.__udiff)

        return iterator_copy

    def _escaper(self, string):

        """

        Escaper for diff escapes special chars and checks the diff limit

        :param string:

        """

        self.cur_diff_size += len(string)

        # escaper gets iterated on each .next() call and it checks if each

        # parsed line doesn't exceed the diff limit

        if self.diff_limit is not None and self.cur_diff_size > self.diff_limit:

            raise DiffLimitExceeded('Diff Limit Exceeded')

        def substitute(m):

            groups = m.groups()

            if groups[0]:

                return '&'

            if groups[1]:

                return '<'

            if groups[2]:

                return '>'

            if groups[3]:

                return '<u>\t</u>'

            if groups[4]:

                return '<u class="cr"></u>'

            if groups[5]:

                return ' <i></i>'

            assert False

        return self._escape_re.sub(substitute, safe_unicode(string))

    def _line_counter(self, l):

        """

        Checks each line and bumps total adds/removes for this diff

        :param l:

        """

        if l.startswith('+') and not l.startswith('+++'):

            self.adds += 1

        elif l.startswith('-') and not l.startswith('---'):

            self.removes += 1

        return safe_unicode(l)

    def _highlight_line_difflib(self, line, next_):

        """

        Highlight inline changes in both lines.

        """

        if line['action'] == 'del':

            old, new = line, next_

        else:

            old, new = next_, line

        oldwords = self._token_re.split(old['line'])

        newwords = self._token_re.split(new['line'])

        sequence = difflib.SequenceMatcher(None, oldwords, newwords)

        oldfragments, newfragments = [], []

        for tag, i1, i2, j1, j2 in sequence.get_opcodes():

            oldfrag = ''.join(oldwords[i1:i2])

            newfrag = ''.join(newwords[j1:j2])

            if tag != 'equal':

                if oldfrag:

                    oldfrag = '<del>%s</del>' % oldfrag

                if newfrag:

                    newfrag = '<ins>%s</ins>' % newfrag

            oldfragments.append(oldfrag)

            newfragments.append(newfrag)

        old['line'] = "".join(oldfragments)

        new['line'] = "".join(newfragments)

    def _highlight_line_udiff(self, line, next_):

        """

        Highlight inline changes in both lines.

        """

        start = 0

        limit = min(len(line['line']), len(next_['line']))

        while start < limit and line['line'][start] == next_['line'][start]:

            start += 1

        end = -1

        limit -= start

        while -end <= limit and line['line'][end] == next_['line'][end]:

            end -= 1

        end += 1

        if start or end:

            def do(l):

                last = end + len(l['line'])

                if l['action'] == 'add':

                    tag = 'ins'

                else:

                    tag = 'del'

                l['line'] = '%s<%s>%s</%s>%s' % (

                    l['line'][:start],

                    tag,

                    l['line'][start:last],

                    tag,

                    l['line'][last:]

                )

            do(line)

            do(next_)

    def _get_header(self, diff_chunk):

        """

        parses the diff header, and returns parts, and leftover diff

        parts consists of 14 elements::

            a_path, b_path, similarity_index, rename_from, rename_to,

            old_mode, new_mode, new_file_mode, deleted_file_mode,

            a_blob_id, b_blob_id, b_mode, a_file, b_file

        :param diff_chunk:

        """

        match = None

        if self.vcs == 'git':

            match = self._git_header_re.match(diff_chunk)

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

# 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/>.

"""

kallithea.lib.indexers.daemon

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

A daemon will read from task table and run tasks

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: Jan 26, 2010

:author: marcink

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

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

"""

import os

import sys

import logging

import traceback

from shutil import rmtree

from time import mktime

from os.path import dirname as dn

from os.path import join as jn

# Add location of top level folder to sys.path

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

sys.path.append(project_path)

from kallithea.config.conf import INDEX_EXTENSIONS, INDEX_FILENAMES

from kallithea.model.scm import ScmModel

from kallithea.model.db import Repository

from kallithea.lib.utils2 import safe_unicode, safe_str

from kallithea.lib.indexers import SCHEMA, IDX_NAME, CHGSETS_SCHEMA, \

    CHGSET_IDX_NAME

from kallithea.lib.vcs.exceptions import ChangesetError, RepositoryError, \

    NodeDoesNotExistError

from whoosh.index import create_in, open_dir, exists_in

from whoosh.query import *

from whoosh.qparser import QueryParser

log = logging.getLogger('whoosh_indexer')

class WhooshIndexingDaemon(object):

    """

    Daemon for atomic indexing jobs

    """

    def __init__(self, indexname=IDX_NAME, index_location=None,

                 repo_location=None, sa=None, repo_list=None,

                 repo_update_list=None):

        self.indexname = indexname

        self.index_location = index_location

        if not index_location:

            raise Exception('You have to provide index location')

        self.repo_location = repo_location

        if not repo_location:

            raise Exception('You have to provide repositories location')

        self.repo_paths = ScmModel(sa).repo_scan(self.repo_location)

        #filter repo list

        if repo_list:

            #Fix non-ascii repo names to unicode

            repo_list = map(safe_unicode, repo_list)

            self.filtered_repo_paths = {}

            for repo_name, repo in self.repo_paths.items():

                if repo_name in repo_list:

                    self.filtered_repo_paths[repo_name] = repo

            self.repo_paths = self.filtered_repo_paths

        #filter update repo list

        self.filtered_repo_update_paths = {}

        if repo_update_list:

            self.filtered_repo_update_paths = {}

            for repo_name, repo in self.repo_paths.items():

                if repo_name in repo_update_list:

                    self.filtered_repo_update_paths[repo_name] = repo

            self.repo_paths = self.filtered_repo_update_paths

        self.initial = True

        if not os.path.isdir(self.index_location):

            os.makedirs(self.index_location)

            log.info('Cannot run incremental index since it does not '

                     'yet exist running full build')

        elif not exists_in(self.index_location, IDX_NAME):

            log.info('Running full index build as the file content '

                     'index does not exist')

        elif not exists_in(self.index_location, CHGSET_IDX_NAME):

            log.info('Running full index build as the changeset '

                     'index does not exist')

        else:

            self.initial = False

    def _get_index_revision(self, repo):

        db_repo = Repository.get_by_repo_name(repo.name_unicode)

        landing_rev = 'tip'

        if db_repo:

            _rev_type, _rev = db_repo.landing_rev

            landing_rev = _rev

        return landing_rev

    def _get_index_changeset(self, repo, index_rev=None):

        if not index_rev:

            index_rev = self._get_index_revision(repo)

        cs = repo.get_changeset(index_rev)

        return cs

    def get_paths(self, repo):

        """

        recursive walk in root dir and return a set of all path in that dir

        based on repository walk function

        """

        index_paths_ = set()

        try:

            cs = self._get_index_changeset(repo)

            for _topnode, _dirs, files in cs.walk('/'):

                for f in files:

                    index_paths_.add(jn(safe_str(repo.path), safe_str(f.path)))

        except RepositoryError:

            log.debug(traceback.format_exc())

            pass

        return index_paths_

    def get_node(self, repo, path, index_rev=None):

        """

        gets a filenode based on given full path. It operates on string for

        hg git compatibility.

        :param repo: scm repo instance

        :param path: full path including root location

        :return: FileNode

        """

        # FIXME: paths should be normalized ... or even better: don't include repo.path

        path = safe_str(path)

        repo_path = safe_str(repo.path)

        assert path.startswith(repo_path)

        assert path[len(repo_path)] in (os.path.sep, os.path.altsep)

        node_path = path[len(repo_path) + 1:]

        cs = self._get_index_changeset(repo, index_rev=index_rev)

        node = cs.get_node(node_path)

        return node

    def is_indexable_node(self, node):

        """

        Just index the content of chosen files, skipping binary files

        """

        return (node.extension in INDEX_EXTENSIONS or node.name in INDEX_FILENAMES) and \

               not node.is_binary

    def get_node_mtime(self, node):

        return mktime(node.last_changeset.date.timetuple())

    def add_doc(self, writer, path, repo, repo_name, index_rev=None):

        """

        Adding doc to writer this function itself fetches data from

        the instance of vcs backend

        """

        indexed = indexed_w_content = 0

        if self.is_indexable_node(node):

            u_content = node.content

            if not isinstance(u_content, unicode):

                log.warning('  >> %s Could not get this content as unicode '

                            'replacing with empty content' % path)

                u_content = u''

            else:

                log.debug('    >> %s [WITH CONTENT]', path)

                indexed_w_content += 1

        else:

            log.debug('    >> %s', path)

            # just index file name without it's content

            u_content = u''

            indexed += 1

        p = safe_unicode(path)

        writer.add_document(

            fileid=p,

            owner=unicode(repo.contact),

            repository=safe_unicode(repo_name),

            path=p,

            content=u_content,

            modtime=self.get_node_mtime(node),

            extension=node.extension

        )

        return indexed, indexed_w_content

    def index_changesets(self, writer, repo_name, repo, start_rev=None):

        """

        Add all changeset in the vcs repo starting at start_rev

        to the index writer

        :param writer: the whoosh index writer to add to

        :param repo_name: name of the repository from whence the

          changeset originates including the repository group

        :param repo: the vcs repository instance to index changesets for,

          the presumption is the repo has changesets to index

        :param start_rev=None: the full sha id to start indexing from

          if start_rev is None then index from the first changeset in

          the repo

        """

        if start_rev is None:

            start_rev = repo[0].raw_id

        log.debug('indexing changesets in %s starting at rev: %s',

                  repo_name, start_rev)

        indexed = 0

        cs_iter = repo.get_changesets(start=start_rev)

        total = len(cs_iter)

        for cs in cs_iter:

            log.debug('    >> %s/%s', cs, total)

            writer.add_document(

                raw_id=unicode(cs.raw_id),

                owner=unicode(repo.contact),

                date=cs._timestamp,

                repository=safe_unicode(repo_name),

                author=cs.author,

                message=cs.message,

                last=cs.last,

                added=u' '.join([safe_unicode(node.path) for node in cs.added]).lower(),

                removed=u' '.join([safe_unicode(node.path) for node in cs.removed]).lower(),