Exemple #1
0
def deserialize_dict(mainitem, subitems, sep, original_class, original_pk,
                     lesserrors):
    """Deserialize a Python dictionary."""
    # pylint: disable=protected-access
    # subitems contains all subitems, here I store only those of
    # deepness 1, i.e. if I have subitems '0', '1' and '1.c' I
    # store only '0' and '1'
    from aiida.common import AIIDA_LOGGER

    firstlevelsubdict = {k: v for k, v in subitems.items() if sep not in k}

    if len(firstlevelsubdict) != mainitem['ival']:
        if (original_class is not None
                and original_class._subspecifier_field_name is not None):
            subspecifier_string = '{}={} and '.format(
                original_class._subspecifier_field_name, original_pk)
        else:
            subspecifier_string = ''
        if original_class is None:
            sourcestr = 'the data passed'
        else:
            sourcestr = original_class.__name__

        msg = ('Wrong dict length stored in {} for '
               "{}key='{}' ({} vs {})".format(sourcestr, subspecifier_string,
                                              mainitem['key'],
                                              len(firstlevelsubdict),
                                              mainitem['ival']))
        if lesserrors:
            AIIDA_LOGGER.error(msg)
        else:
            raise DeserializationException(msg)

    # I get the values in memory as a dictionary
    tempdict = {}
    for firstsubk, firstsubv in firstlevelsubdict.items():
        # I call recursively the same function to get subitems
        newsubitems = {
            k[len(firstsubk) + len(sep):]: v
            for k, v in subitems.items() if k.startswith(firstsubk + sep)
        }
        tempdict[firstsubk] = _deserialize_attribute(
            mainitem=firstsubv,
            subitems=newsubitems,
            sep=sep,
            original_class=original_class,
            original_pk=original_pk)

    return tempdict
Exemple #2
0
def deserialize_list(mainitem, subitems, sep, original_class, original_pk,
                     lesserrors):
    """Deserialize a Python list."""
    # pylint: disable=protected-access
    # subitems contains all subitems, here I store only those of
    # deepness 1, i.e. if I have subitems '0', '1' and '1.c' I
    # store only '0' and '1'

    from aiida.common import AIIDA_LOGGER

    firstlevelsubdict = {k: v for k, v in subitems.items() if sep not in k}

    # For checking, I verify the expected values
    expected_set = {'{:d}'.format(i) for i in range(mainitem['ival'])}
    received_set = set(firstlevelsubdict.keys())
    # If there are more entries than expected, but all expected
    # ones are there, I just issue an error but I do not stop.

    if not expected_set.issubset(received_set):
        if (original_class is not None
                and original_class._subspecifier_field_name is not None):
            subspecifier_string = '{}={} and '.format(
                original_class._subspecifier_field_name, original_pk)
        else:
            subspecifier_string = ''
        if original_class is None:
            sourcestr = 'the data passed'
        else:
            sourcestr = original_class.__name__

        raise DeserializationException('Wrong list elements stored in {} for '
                                       "{}key='{}' ({} vs {})".format(
                                           sourcestr, subspecifier_string,
                                           mainitem['key'], expected_set,
                                           received_set))
    if expected_set != received_set:
        if (original_class is not None
                and original_class._subspecifier_field_name is not None):
            subspecifier_string = '{}={} and '.format(
                original_class._subspecifier_field_name, original_pk)
        else:
            subspecifier_string = ''

        sourcestr = 'the data passed' if original_class is None else original_class.__name__

        msg = ('Wrong list elements stored in {} for '
               "{}key='{}' ({} vs {})".format(sourcestr, subspecifier_string,
                                              mainitem['key'], expected_set,
                                              received_set))
        if lesserrors:
            AIIDA_LOGGER.error(msg)
        else:
            raise DeserializationException(msg)

    # I get the values in memory as a dictionary
    tempdict = {}
    for firstsubk, firstsubv in firstlevelsubdict.items():
        # I call recursively the same function to get subitems
        newsubitems = {
            k[len(firstsubk) + len(sep):]: v
            for k, v in subitems.items() if k.startswith(firstsubk + sep)
        }
        tempdict[firstsubk] = _deserialize_attribute(
            mainitem=firstsubv,
            subitems=newsubitems,
            sep=sep,
            original_class=original_class,
            original_pk=original_pk)

    # And then I put them in a list
    retlist = [tempdict['{:d}'.format(i)] for i in range(mainitem['ival'])]
    return retlist
Exemple #3
0
def _deserialize_attribute(mainitem,
                           subitems,
                           sep,
                           original_class=None,
                           original_pk=None,
                           lesserrors=False):
    """
    Deserialize a single attribute.

    :param mainitem: the main item (either the attribute itself for base
      types (None, string, ...) or the main item for lists and dicts.
      Must contain the 'key' key and also the following keys:
      datatype, tval, fval, ival, bval, dval.
      NOTE that a type check is not performed! tval is expected to be a string,
      dval a date, etc.
    :param subitems: must be a dictionary of dictionaries. In the top-level dictionary,
      the key must be the key of the attribute, stripped of all prefixes
      (i.e., if the mainitem has key 'a.b' and we pass subitems
      'a.b.0', 'a.b.1', 'a.b.1.c', their keys must be '0', '1', '1.c').
      It must be None if the value is not iterable (int, str,
      float, ...).
      It is an empty dictionary if there are no subitems.
    :param sep: a string, the separator between subfields (to separate the
      name of a dictionary from the keys it contains, for instance)
    :param original_class: if these elements come from a specific subclass
      of DbMultipleValueAttributeBaseClass, pass here the class (note: the class,
      not the instance!). This is used only in case the wrong number of elements
      is found in the raw data, to print a more meaningful message (if the class
      has a dbnode associated to it)
    :param original_pk: if the elements come from a specific subclass
      of DbMultipleValueAttributeBaseClass that has a dbnode associated to it,
      pass here the PK integer. This is used only in case the wrong number
      of elements is found in the raw data, to print a more meaningful message
    :param lesserrors: If set to True, in some cases where the content of the
      DB is not consistent but data is still recoverable,
      it will just log the message rather than raising
      an exception (e.g. if the number of elements of a dictionary is different
      from the number declared in the ival field).

    :return: the deserialized value
    :raise aiida.backends.djsite.db.migrations.DeserializationException: if an error occurs
    """
    from aiida.common import json
    from aiida.common.timezone import (is_naive, make_aware,
                                       get_current_timezone)

    from aiida.common import AIIDA_LOGGER

    if mainitem['datatype'] == 'none':
        if subitems:
            raise DeserializationException("'{}' is of a base type, "
                                           'but has subitems!'.format(
                                               mainitem.key))
        return None
    elif mainitem['datatype'] == 'bool':
        if subitems:
            raise DeserializationException("'{}' is of a base type, "
                                           'but has subitems!'.format(
                                               mainitem.key))
        return mainitem['bval']
    elif mainitem['datatype'] == 'int':
        if subitems:
            raise DeserializationException("'{}' is of a base type, "
                                           'but has subitems!'.format(
                                               mainitem.key))
        return mainitem['ival']
    elif mainitem['datatype'] == 'float':
        if subitems:
            raise DeserializationException("'{}' is of a base type, "
                                           'but has subitems!'.format(
                                               mainitem.key))
        return mainitem['fval']
    elif mainitem['datatype'] == 'txt':
        if subitems:
            raise DeserializationException("'{}' is of a base type, "
                                           'but has subitems!'.format(
                                               mainitem.key))
        return mainitem['tval']
    elif mainitem['datatype'] == 'date':
        if subitems:
            raise DeserializationException("'{}' is of a base type, "
                                           'but has subitems!'.format(
                                               mainitem.key))
        if is_naive(mainitem['dval']):
            return make_aware(mainitem['dval'], get_current_timezone())
        else:
            return mainitem['dval']

    elif mainitem['datatype'] == 'list':
        # subitems contains all subitems, here I store only those of
        # deepness 1, i.e. if I have subitems '0', '1' and '1.c' I
        # store only '0' and '1'
        firstlevelsubdict = {k: v for k, v in subitems.items() if sep not in k}

        # For checking, I verify the expected values
        expected_set = set(['{:d}'.format(i) for i in range(mainitem['ival'])])
        received_set = set(firstlevelsubdict.keys())
        # If there are more entries than expected, but all expected
        # ones are there, I just issue an error but I do not stop.

        if not expected_set.issubset(received_set):
            if (original_class is not None
                    and original_class._subspecifier_field_name is not None):
                subspecifier_string = '{}={} and '.format(
                    original_class._subspecifier_field_name, original_pk)
            else:
                subspecifier_string = ''
            if original_class is None:
                sourcestr = 'the data passed'
            else:
                sourcestr = original_class.__name__

            raise DeserializationException(
                'Wrong list elements stored in {} for '
                "{}key='{}' ({} vs {})".format(sourcestr, subspecifier_string,
                                               mainitem['key'], expected_set,
                                               received_set))
        if expected_set != received_set:
            if (original_class is not None
                    and original_class._subspecifier_field_name is not None):
                subspecifier_string = '{}={} and '.format(
                    original_class._subspecifier_field_name, original_pk)
            else:
                subspecifier_string = ''
            if original_class is None:
                sourcestr = 'the data passed'
            else:
                sourcestr = original_class.__name__

            msg = ('Wrong list elements stored in {} for '
                   "{}key='{}' ({} vs {})".format(sourcestr,
                                                  subspecifier_string,
                                                  mainitem['key'],
                                                  expected_set, received_set))
            if lesserrors:
                AIIDA_LOGGER.error(msg)
            else:
                raise DeserializationException(msg)

        # I get the values in memory as a dictionary
        tempdict = {}
        for firstsubk, firstsubv in firstlevelsubdict.items():
            # I call recursively the same function to get subitems
            newsubitems = {
                k[len(firstsubk) + len(sep):]: v
                for k, v in subitems.items() if k.startswith(firstsubk + sep)
            }
            tempdict[firstsubk] = _deserialize_attribute(
                mainitem=firstsubv,
                subitems=newsubitems,
                sep=sep,
                original_class=original_class,
                original_pk=original_pk)

        # And then I put them in a list
        retlist = [tempdict['{:d}'.format(i)] for i in range(mainitem['ival'])]
        return retlist
    elif mainitem['datatype'] == 'dict':
        # subitems contains all subitems, here I store only those of
        # deepness 1, i.e. if I have subitems '0', '1' and '1.c' I
        # store only '0' and '1'
        firstlevelsubdict = {k: v for k, v in subitems.items() if sep not in k}

        if len(firstlevelsubdict) != mainitem['ival']:
            if (original_class is not None
                    and original_class._subspecifier_field_name is not None):
                subspecifier_string = '{}={} and '.format(
                    original_class._subspecifier_field_name, original_pk)
            else:
                subspecifier_string = ''
            if original_class is None:
                sourcestr = 'the data passed'
            else:
                sourcestr = original_class.__name__

            msg = ('Wrong dict length stored in {} for '
                   "{}key='{}' ({} vs {})".format(sourcestr,
                                                  subspecifier_string,
                                                  mainitem['key'],
                                                  len(firstlevelsubdict),
                                                  mainitem['ival']))
            if lesserrors:
                AIIDA_LOGGER.error(msg)
            else:
                raise DeserializationException(msg)

        # I get the values in memory as a dictionary
        tempdict = {}
        for firstsubk, firstsubv in firstlevelsubdict.items():
            # I call recursively the same function to get subitems
            newsubitems = {
                k[len(firstsubk) + len(sep):]: v
                for k, v in subitems.items() if k.startswith(firstsubk + sep)
            }
            tempdict[firstsubk] = _deserialize_attribute(
                mainitem=firstsubv,
                subitems=newsubitems,
                sep=sep,
                original_class=original_class,
                original_pk=original_pk)

        return tempdict
    elif mainitem['datatype'] == 'json':
        try:
            return json.loads(mainitem['tval'])
        except ValueError:
            raise DeserializationException(
                'Error in the content of the json field')
    else:
        raise DeserializationException(
            "The type field '{}' is not recognized".format(
                mainitem['datatype']))