"""

The main QuerySet implementation. This provides the public API for the ORM.

"""

from copy import deepcopy

from itertools import izip

from django.db import connections, router, transaction, IntegrityError

from django.db.models.aggregates import Aggregate

from django.db.models.fields import DateField

from django.db.models.query_utils import Q, select_related_descend, CollectedObjects, CyclicDependency, deferred_class_factory, InvalidQuery

from django.db.models import signals, sql

from django.utils.copycompat import deepcopy

# Used to control how many objects are worked with at once in some cases (e.g.

# when deleting objects).

CHUNK_SIZE = 100

ITER_CHUNK_SIZE = CHUNK_SIZE

# The maximum number of items to display in a QuerySet.__repr__

REPR_OUTPUT_SIZE = 20

# Pull into this namespace for backwards compatibility.

EmptyResultSet = sql.EmptyResultSet

class QuerySet(object):

    """

    Represents a lazy database lookup for a set of objects.

    """

    def __init__(self, model=None, query=None, using=None):

        self.model = model

        # EmptyQuerySet instantiates QuerySet with model as None

        self._db = using

        self.query = query or sql.Query(self.model)

        self._result_cache = None

        self._iter = None

        self._sticky_filter = False

        self._for_write = False

    ########################

    # PYTHON MAGIC METHODS #

    ########################

    def __deepcopy__(self, memo):

        """

        Deep copy of a QuerySet doesn't populate the cache

        """

        obj = self.__class__()

        for k,v in self.__dict__.items():

            if k in ('_iter','_result_cache'):

                obj.__dict__[k] = None

            else:

                obj.__dict__[k] = deepcopy(v, memo)

        return obj

    def __getstate__(self):

        """

        Allows the QuerySet to be pickled.

        """

        # Force the cache to be fully populated.

        len(self)

        obj_dict = self.__dict__.copy()

        obj_dict['_iter'] = None

        return obj_dict

    def __repr__(self):

        data = list(self[:REPR_OUTPUT_SIZE + 1])

        if len(data) > REPR_OUTPUT_SIZE:

            data[-1] = "...(remaining elements truncated)..."

        return repr(data)

    def __len__(self):

        # Since __len__ is called quite frequently (for example, as part of

        # list(qs), we make some effort here to be as efficient as possible

        # whilst not messing up any existing iterators against the QuerySet.

        if self._result_cache is None:

            if self._iter:

                self._result_cache = list(self._iter)

            else:

                self._result_cache = list(self.iterator())

        elif self._iter:

            self._result_cache.extend(list(self._iter))

        return len(self._result_cache)

    def __iter__(self):

        if self._result_cache is None:

            self._iter = self.iterator()

            self._result_cache = []

        if self._iter:

            return self._result_iter()

        # Python's list iterator is better than our version when we're just

        # iterating over the cache.

        return iter(self._result_cache)

    def _result_iter(self):

        pos = 0

        while 1:

            upper = len(self._result_cache)

            while pos < upper:

                yield self._result_cache[pos]

                pos = pos + 1

            if not self._iter:

                raise StopIteration

            if len(self._result_cache) <= pos:

                self._fill_cache()

    def __nonzero__(self):

        if self._result_cache is not None:

            return bool(self._result_cache)

        try:

            iter(self).next()

        except StopIteration:

            return False

        return True

    def __contains__(self, val):

        # The 'in' operator works without this method, due to __iter__. This

        # implementation exists only to shortcut the creation of Model

        # instances, by bailing out early if we find a matching element.

        pos = 0

        if self._result_cache is not None:

            if val in self._result_cache:

                return True

            elif self._iter is None:

                # iterator is exhausted, so we have our answer

                return False

            # remember not to check these again:

            pos = len(self._result_cache)

        else:

            # We need to start filling the result cache out. The following

            # ensures that self._iter is not None and self._result_cache is not

            # None

            it = iter(self)

        # Carry on, one result at a time.

        while True:

            if len(self._result_cache) <= pos:

                self._fill_cache(num=1)

            if self._iter is None:

                # we ran out of items

                return False

            if self._result_cache[pos] == val:

                return True

            pos += 1

    def __getitem__(self, k):

        """

        Retrieves an item or slice from the set of results.

        """

        if not isinstance(k, (slice, int, long)):

            raise TypeError

        assert ((not isinstance(k, slice) and (k >= 0))

                or (isinstance(k, slice) and (k.start is None or k.start >= 0)

                    and (k.stop is None or k.stop >= 0))), \

                "Negative indexing is not supported."

        if self._result_cache is not None:

            if self._iter is not None:

                # The result cache has only been partially populated, so we may

                # need to fill it out a bit more.

                if isinstance(k, slice):

                    if k.stop is not None:

                        # Some people insist on passing in strings here.

                        bound = int(k.stop)

                    else:

                        bound = None

                else:

                    bound = k + 1

                if len(self._result_cache) < bound:

                    self._fill_cache(bound - len(self._result_cache))

            return self._result_cache[k]

        if isinstance(k, slice):

            qs = self._clone()

            if k.start is not None:

                start = int(k.start)

            else:

                start = None

            if k.stop is not None:

                stop = int(k.stop)

            else:

                stop = None

            qs.query.set_limits(start, stop)

            return k.step and list(qs)[::k.step] or qs

        try:

            qs = self._clone()

            qs.query.set_limits(k, k + 1)

            return list(qs)[0]

        except self.model.DoesNotExist, e:

            raise IndexError(e.args)

    def __and__(self, other):

        self._merge_sanity_check(other)

        if isinstance(other, EmptyQuerySet):

            return other._clone()

        combined = self._clone()

        combined.query.combine(other.query, sql.AND)

        return combined

    def __or__(self, other):

        self._merge_sanity_check(other)

        combined = self._clone()

        if isinstance(other, EmptyQuerySet):

            return combined

        combined.query.combine(other.query, sql.OR)

        return combined

    ####################################

    # METHODS THAT DO DATABASE QUERIES #

    ####################################

    def iterator(self):

        """

        An iterator over the results from applying this QuerySet to the

        database.

        """

        fill_cache = self.query.select_related

        if isinstance(fill_cache, dict):

            requested = fill_cache

        else:

            requested = None

        max_depth = self.query.max_depth

        extra_select = self.query.extra_select.keys()

        aggregate_select = self.query.aggregate_select.keys()

        only_load = self.query.get_loaded_field_names()

        if not fill_cache:

            fields = self.model._meta.fields

            pk_idx = self.model._meta.pk_index()

        index_start = len(extra_select)

        aggregate_start = index_start + len(self.model._meta.fields)

        load_fields = []

        # If only/defer clauses have been specified,

        # build the list of fields that are to be loaded.

        if only_load:

            for field, model in self.model._meta.get_fields_with_model():

                if model is None:

                    model = self.model

                if field == self.model._meta.pk:

                    # Record the index of the primary key when it is found

                    pk_idx = len(load_fields)

                try:

                    if field.name in only_load[model]:

                        # Add a field that has been explicitly included

                        load_fields.append(field.name)

                except KeyError:

                    # Model wasn't explicitly listed in the only_load table

                    # Therefore, we need to load all fields from this model

                    load_fields.append(field.name)

        skip = None

        if load_fields and not fill_cache:

            # Some fields have been deferred, so we have to initialise

            # via keyword arguments.

            skip = set()

            init_list = []

            for field in fields:

                if field.name not in load_fields:

                    skip.add(field.attname)

                else:

                    init_list.append(field.attname)

            model_cls = deferred_class_factory(self.model, skip)

        compiler = self.query.get_compiler(using=self.db)

        for row in compiler.results_iter():

            if fill_cache:

                obj, _ = get_cached_row(self.model, row,

                            index_start, using=self.db, max_depth=max_depth,

                            requested=requested, offset=len(aggregate_select),

                            only_load=only_load)

            else:

                if skip:

                    row_data = row[index_start:aggregate_start]

                    pk_val = row_data[pk_idx]

                    obj = model_cls(**dict(zip(init_list, row_data)))

                else:

                    # Omit aggregates in object creation.

                    obj = self.model(*row[index_start:aggregate_start])

                # Store the source database of the object

                obj._state.db = self.db

            for i, k in enumerate(extra_select):

                setattr(obj, k, row[i])

            # Add the aggregates to the model

            for i, aggregate in enumerate(aggregate_select):

                setattr(obj, aggregate, row[i+aggregate_start])

            yield obj

    def aggregate(self, *args, **kwargs):

        """

        Returns a dictionary containing the calculations (aggregation)

        over the current queryset

        If args is present the expression is passed as a kwarg using

        the Aggregate object's default alias.

        """

        for arg in args:

            kwargs[arg.default_alias] = arg

        query = self.query.clone()

        for (alias, aggregate_expr) in kwargs.items():

            query.add_aggregate(aggregate_expr, self.model, alias,

                is_summary=True)

        return query.get_aggregation(using=self.db)

    def count(self):

        """

        Performs a SELECT COUNT() and returns the number of records as an

        integer.

        If the QuerySet is already fully cached this simply returns the length

        of the cached results set to avoid multiple SELECT COUNT(*) calls.

        """

        if self._result_cache is not None and not self._iter:

            return len(self._result_cache)

        return self.query.get_count(using=self.db)

    def get(self, *args, **kwargs):

        """

        Performs the query and returns a single object matching the given

        keyword arguments.

        """

        clone = self.filter(*args, **kwargs)

        if self.query.can_filter():

            clone = clone.order_by()

        num = len(clone)

        if num == 1:

            return clone._result_cache[0]

        if not num:

            raise self.model.DoesNotExist("%s matching query does not exist."

                    % self.model._meta.object_name)

        raise self.model.MultipleObjectsReturned("get() returned more than one %s -- it returned %s! Lookup parameters were %s"

                % (self.model._meta.object_name, num, kwargs))

    def create(self, **kwargs):

        """

        Creates a new object with the given kwargs, saving it to the database

        and returning the created object.

        """

        obj = self.model(**kwargs)

        self._for_write = True

        obj.save(force_insert=True, using=self.db)

        return obj

    def get_or_create(self, **kwargs):

        """

        Looks up an object with the given kwargs, creating one if necessary.

        Returns a tuple of (object, created), where created is a boolean

        specifying whether an object was created.

        """

        assert kwargs, \

                'get_or_create() must be passed at least one keyword argument'

        defaults = kwargs.pop('defaults', {})

        try:

            self._for_write = True

            return self.get(**kwargs), False

        except self.model.DoesNotExist:

            try:

                params = dict([(k, v) for k, v in kwargs.items() if '__' not in k])

                params.update(defaults)

                obj = self.model(**params)

                sid = transaction.savepoint(using=self.db)

                obj.save(force_insert=True, using=self.db)

                transaction.savepoint_commit(sid, using=self.db)

                return obj, True

            except IntegrityError, e:

                transaction.savepoint_rollback(sid, using=self.db)

                try:

                    return self.get(**kwargs), False

                except self.model.DoesNotExist:

                    raise e

    def latest(self, field_name=None):

        """

        Returns the latest object, according to the model's 'get_latest_by'

        option or optional given field_name.

        """

        latest_by = field_name or self.model._meta.get_latest_by

        assert bool(latest_by), "latest() requires either a field_name parameter or 'get_latest_by' in the model"

        assert self.query.can_filter(), \

                "Cannot change a query once a slice has been taken."

        obj = self._clone()

        obj.query.set_limits(high=1)

        obj.query.add_ordering('-%s' % latest_by)

        return obj.get()