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

"""This module provides tools to import tabular data.

:organization: Logilab

:copyright: 2001-2010 LOGILAB S.A. (Paris, FRANCE), license is LGPL v2.

:contact: http://www.logilab.fr/ -- mailto:contact@logilab.fr

:license: GNU Lesser General Public License, v2.1 - http://www.gnu.org/licenses

Example of use (run this with `cubicweb-ctl shell instance import-script.py`):

.. sourcecode:: python

  from cubicweb.devtools.dataimport import *

  # define data generators

  GENERATORS = []

  USERS = [('Prenom', 'firstname', ()),

           ('Nom', 'surname', ()),

           ('Identifiant', 'login', ()),

           ]

  def gen_users(ctl):

      for row in ctl.get_data('utilisateurs'):

          entity = mk_entity(row, USERS)

          entity['upassword'] = u'motdepasse'

          ctl.check('login', entity['login'], None)

          ctl.store.add('CWUser', entity)

          email = {'address': row['email']}

          ctl.store.add('EmailAddress', email)

          ctl.store.relate(entity['eid'], 'use_email', email['eid'])

          ctl.store.rql('SET U in_group G WHERE G name "users", U eid %(x)s', {'x':entity['eid']})

  CHK = [('login', check_doubles, 'Utilisateurs Login',

          'Deux utilisateurs ne devraient pas avoir le même login.'),

         ]

  GENERATORS.append( (gen_users, CHK) )

  # create controller

  ctl = CWImportController(RQLObjectStore())

  ctl.generators = GENERATORS

  ctl.store._checkpoint = checkpoint

  ctl.store._rql = rql

  ctl.data['utilisateurs'] = lazytable(utf8csvreader(open('users.csv')))

  # run

  ctl.run()

  sys.exit(0)

"""

__docformat__ = "restructuredtext en"

import sys

import csv

import traceback

import os.path as osp

from StringIO import StringIO

from logilab.common import shellutils

from logilab.common.deprecation import deprecated

def ucsvreader_pb(filepath, encoding='utf-8', separator=',', quote='"',

                  skipfirst=False, withpb=True):

    """same as ucsvreader but a progress bar is displayed as we iter on rows"""

    if not osp.exists(filepath):

        raise Exception("file doesn't exists: %s" % filepath)

    rowcount = int(shellutils.Execute('wc -l "%s"' % filepath).out.strip().split()[0])

    if skipfirst:

        rowcount -= 1

    if withpb:

        pb = shellutils.ProgressBar(rowcount, 50)

    for urow in ucsvreader(file(filepath), encoding, separator, quote, skipfirst):

        yield urow

        if withpb:

            pb.update()

    print ' %s rows imported' % rowcount

def ucsvreader(stream, encoding='utf-8', separator=',', quote='"',

               skipfirst=False):

    """A csv reader that accepts files with any encoding and outputs unicode

    strings

    """

    it = iter(csv.reader(stream, delimiter=separator, quotechar=quote))

    if skipfirst:

        it.next()

    for row in it:

        yield [item.decode(encoding) for item in row]

utf8csvreader = deprecated('use ucsvreader instead')(ucsvreader)

def commit_every(nbit, store, it):

    for i, x in enumerate(it):

        yield x

        if nbit is not None and i % nbit:

            store.checkpoint()

    if nbit is not None:

        store.checkpoint()

def lazytable(reader):

    """The first row is taken to be the header of the table and

    used to output a dict for each row of data.

    >>> data = lazytable(utf8csvreader(open(filename)))

    """

    header = reader.next()

    for row in reader:

        yield dict(zip(header, row))

def mk_entity(row, map):

    """Return a dict made from sanitized mapped values.

    >>> row = {'myname': u'dupont'}

    >>> map = [('myname', u'name', (capitalize_if_unicase,))]

    >>> mk_entity(row, map)

    {'name': u'Dupont'}

    """

    res = {}

    for src, dest, funcs in map:

        res[dest] = row[src]

    return res

# user interactions ############################################################

def tell(msg):

    print msg

def confirm(question):

    """A confirm function that asks for yes/no/abort and exits on abort."""

    answer = shellutils.ASK.ask(question, ('Y','n','abort'), 'Y')

    if answer == 'abort':

        sys.exit(1)

    return answer == 'Y'

class catch_error(object):

    """Helper for @contextmanager decorator."""

    def __init__(self, ctl, key='unexpected error', msg=None):

        self.ctl = ctl

        self.key = key

        self.msg = msg

    def __enter__(self):

        return self

    def __exit__(self, type, value, traceback):

        if type is not None:

            if issubclass(type, (KeyboardInterrupt, SystemExit)):

                return # re-raise

            if self.ctl.catcherrors:

                self.ctl.record_error(self.key, None, type, value, traceback)

                return True # silent

# base sanitizing functions ####################################################

def capitalize_if_unicase(txt):

    if txt.isupper() or txt.islower():

        return txt.capitalize()

    return txt

def no_space(txt):

    return txt.replace(' ','')

def no_uspace(txt):

    return txt.replace(u'\xa0','')

def no_dash(txt):

    return txt.replace('-','')

def alldigits(txt):

    if txt.isdigit():

        return txt

    else:

        return u''

# base integrity checking functions ############################################

def check_doubles(buckets):

    """Extract the keys that have more than one item in their bucket."""

    return [(key, len(value)) for key,value in buckets.items() if len(value) > 1]

def check_doubles_not_none(buckets):

    """Extract the keys that have more than one item in their bucket."""

    return [(key, len(value)) for key,value in buckets.items() if key is not None and len(value) > 1]

# object stores #################################################################

class ObjectStore(object):

    >>> store = ObjectStore()

    >>> user = {'login': 'johndoe'}

    >>> store.add('CWUser', user)

    >>> group = {'name': 'unknown'}

    >>> store.add('CWUser', group)

    >>> store.relate(user['eid'], 'in_group', group['eid'])

    """

    def __init__(self):

        self.items = []

        self.eids = {}

        self.types = {}

        self.relations = set()

        self.indexes = {}

        self._rql = None

        self._checkpoint = None

    def _put(self, type, item):

        self.items.append(item)

        return len(self.items) - 1

    def add(self, type, item):

        assert isinstance(item, dict), 'item is not a dict but a %s' % type(item)

        eid = item['eid'] = self._put(type, item)

        self.eids[eid] = item

        self.types.setdefault(type, []).append(eid)

    def relate(self, eid_from, rtype, eid_to):

        index = {}

        for eid in self.types[type]:

            index.setdefault(func(self.eids[eid]), []).append(eid)

        self.indexes[name] = index

    def get_many(self, name, key):

    def get_one(self, name, key):

        eids = self.indexes[name].get(key, [])

    def find(self, type, key, value):

        for idx in self.types[type]:

            item = self.items[idx]

            if item[key] == value:

                yield item

    def checkpoint(self):

        pass

class RQLObjectStore(ObjectStore):

    _rql = None # bw compat

    def __init__(self, session=None, checkpoint=None):

        ObjectStore.__init__(self)

        if session is not None:

            if not hasattr(session, 'set_pool'):

                # connection

                cnx = session

                session = session.request()

                session.set_pool = lambda : None

                checkpoint = checkpoint or cnx.commit

            self.session = session