def model_datastoreio():
"""Using a Read and Write transform to read/write to Cloud Datastore."""
import uuid
from google.cloud.proto.datastore.v1 import entity_pb2
from google.cloud.proto.datastore.v1 import query_pb2
import googledatastore
import apache_beam as beam
from apache_beam.options.pipeline_options import PipelineOptions
from apache_beam.io.gcp.datastore.v1.datastoreio import ReadFromDatastore
from apache_beam.io.gcp.datastore.v1.datastoreio import WriteToDatastore
project = 'my_project'
kind = 'my_kind'
query = query_pb2.Query()
query.kind.add().name = kind
# [START model_datastoreio_read]
p = beam.Pipeline(options=PipelineOptions())
entities = p | 'Read From Datastore' >> ReadFromDatastore(project, query)
# [END model_datastoreio_read]
# [START model_datastoreio_write]
p = beam.Pipeline(options=PipelineOptions())
musicians = p | 'Musicians' >> beam.Create(
['Mozart', 'Chopin', 'Beethoven', 'Vivaldi'])
def to_entity(content):
entity = entity_pb2.Entity()
googledatastore.helper.add_key_path(entity.key, kind, str(uuid.uuid4()))
googledatastore.helper.add_properties(entity, {'content': unicode(content)})
return entity
entities = musicians | 'To Entity' >> beam.Map(to_entity)
entities | 'Write To Datastore' >> WriteToDatastore(project)
def test_get_splits_query_with_unsupported_filter(self):
query = query_pb2.Query()
query.kind.add()
test_filter = query.filter.composite_filter.filters.add()
test_filter.property_filter.op = PropertyFilter.GREATER_THAN
self.assertRaises(ValueError, query_splitter.get_splits, None, query,
2)
def test_get_splits_query_with_order(self):
query = query_pb2.Query()
query.kind.add()
query.order.add()
self.assertRaises(ValueError, query_splitter.get_splits, None, query,
3)
def test__build_protobuf_all_values(self):
from google.cloud.proto.datastore.v1 import query_pb2
from google.cloud.datastore.query import Query
client = _Client(None, None)
query = Query(client)
limit = 15
offset = 9
start_bytes = b'i\xb7\x1d'
start_cursor = 'abcd'
end_bytes = b'\xc3\x1c\xb3'
end_cursor = 'wxyz'
iterator = self._make_one(
query, client, limit=limit, offset=offset,
start_cursor=start_cursor, end_cursor=end_cursor)
self.assertEqual(iterator.max_results, limit)
iterator.num_results = 4
iterator._skipped_results = 1
pb = iterator._build_protobuf()
expected_pb = query_pb2.Query(
start_cursor=start_bytes,
end_cursor=end_bytes,
offset=offset - iterator._skipped_results,
)
expected_pb.limit.value = limit - iterator.num_results
self.assertEqual(pb, expected_pb)
def _next_page_helper(self, txn_id=None):
from google.cloud.iterator import Page
from google.cloud.proto.datastore.v1 import datastore_pb2
from google.cloud.proto.datastore.v1 import entity_pb2
from google.cloud.proto.datastore.v1 import query_pb2
from google.cloud.datastore.query import Query
more_enum = query_pb2.QueryResultBatch.NOT_FINISHED
result = _make_query_response([], b'', more_enum, 0)
project = 'prujekt'
ds_api = _make_datastore_api(result)
if txn_id is None:
client = _Client(project, datastore_api=ds_api)
else:
transaction = mock.Mock(id=txn_id, spec=['id'])
client = _Client(
project, datastore_api=ds_api, transaction=transaction)
query = Query(client)
iterator = self._make_one(query, client)
page = iterator._next_page()
self.assertIsInstance(page, Page)
self.assertIs(page._parent, iterator)
partition_id = entity_pb2.PartitionId(project_id=project)
if txn_id is None:
read_options = datastore_pb2.ReadOptions()
else:
read_options = datastore_pb2.ReadOptions(transaction=txn_id)
empty_query = query_pb2.Query()
ds_api.run_query.assert_called_once_with(
project, partition_id, read_options, query=empty_query)
def get_namespaces(self):
# Skip auth-ing to db in test operations
if not self.argv:
return ['4952435991248896_1']
query_pb = query_pb2.Query()
helper.set_kind(query_pb, "__namespace__")
client = apache_helper.get_datastore(PROJECT)
namespace_entities = apache_helper.fetch_entities(
PROJECT, '', query_pb, client)
namespaces = []
for n in namespace_entities:
# Get namespace name or id
key_path = n.key.path[-1]
if key_path.HasField('id'):
name_or_id = key_path.id
else:
name_or_id = key_path.name
# Avoid duplicates and test namespaces
if len(str(name_or_id)) > 1 and name_or_id not in namespaces:
namespaces.append(name_or_id)
return namespaces
def _create_split(last_key, next_key, query):
"""Create a new {@link Query} given the query and range..
Args:
last_key: the previous key. If null then assumed to be the beginning.
next_key: the next key. If null then assumed to be the end.
query: the desired query.
Returns:
A split query with fetches entities in the range [last_key, next_key)
"""
if not (last_key or next_key):
return query
split_query = query_pb2.Query()
split_query.CopyFrom(query)
composite_filter = split_query.filter.composite_filter
composite_filter.op = CompositeFilter.AND
if query.HasField('filter'):
composite_filter.filters.add().CopyFrom(query.filter)
if last_key:
lower_bound = composite_filter.filters.add()
lower_bound.property_filter.property.name = KEY_PROPERTY_NAME
lower_bound.property_filter.op = PropertyFilter.GREATER_THAN_OR_EQUAL
lower_bound.property_filter.value.key_value.CopyFrom(last_key)
if next_key:
upper_bound = composite_filter.filters.add()
upper_bound.property_filter.property.name = KEY_PROPERTY_NAME
upper_bound.property_filter.op = PropertyFilter.LESS_THAN
upper_bound.property_filter.value.key_value.CopyFrom(next_key)
return split_query
def split_query(self, query, num_splits):
"""Generate dummy query splits."""
split_queries = []
for _ in range(0, num_splits):
q = query_pb2.Query()
q.CopyFrom(query)
split_queries.append(q)
return split_queries
def test_get_splits_with_two_splits(self):
query = query_pb2.Query()
kind = query.kind.add()
kind.name = 'shakespeare-demo'
num_splits = 2
num_entities = 97
batch_size = 9
self.check_get_splits(query, num_splits, num_entities, batch_size)
def test_get_splits_with_multiple_splits(self):
query = query_pb2.Query()
kind = query.kind.add()
kind.name = 'shakespeare-demo'
num_splits = 4
num_entities = 369
batch_size = 12
self.check_get_splits(query, num_splits, num_entities, batch_size)
def test_get_splits_with_large_num_splits(self):
query = query_pb2.Query()
kind = query.kind.add()
kind.name = 'shakespeare-demo'
num_splits = 10
num_entities = 4
batch_size = 10
self.check_get_splits(query, num_splits, num_entities, batch_size)
def test_get_splits_with_batch_size_exact_multiple(self):
"""Test get_splits when num scatter keys is a multiple of batch size."""
query = query_pb2.Query()
kind = query.kind.add()
kind.name = 'shakespeare-demo'
num_splits = 4
num_entities = 400
batch_size = 32
self.check_get_splits(query, num_splits, num_entities, batch_size)
def test_get_splits_with_large_batch_size(self):
"""Test get_splits when all scatter keys are retured in a single req."""
query = query_pb2.Query()
kind = query.kind.add()
kind.name = 'shakespeare-demo'
num_splits = 4
num_entities = 400
batch_size = 500
self.check_get_splits(query, num_splits, num_entities, batch_size)
def test__build_protobuf_empty(self):
from google.cloud.proto.datastore.v1 import query_pb2
from google.cloud.datastore.query import Query
client = _Client(None, None)
query = Query(client)
iterator = self._make_one(query, client)
pb = iterator._build_protobuf()
expected_pb = query_pb2.Query()
self.assertEqual(pb, expected_pb)
def make_latest_timestamp_query(namespace):
"""Make a Query to fetch the latest timestamp statistics."""
query = query_pb2.Query()
if namespace is None:
query.kind.add().name = '__Stat_Total__'
else:
query.kind.add().name = '__Stat_Ns_Total__'
# Descending order of `timestamp`
datastore_helper.add_property_orders(query, "-timestamp")
# Only get the latest entity
query.limit.value = 1
return query
def test_create_scatter_query(self):
query = query_pb2.Query()
kind = query.kind.add()
kind.name = 'shakespeare-demo'
num_splits = 10
scatter_query = query_splitter._create_scatter_query(query, num_splits)
self.assertEqual(scatter_query.kind[0], kind)
self.assertEqual(scatter_query.limit.value,
(num_splits - 1) * query_splitter.KEYS_PER_SPLIT)
self.assertEqual(scatter_query.order[0].direction,
query_pb2.PropertyOrder.ASCENDING)
self.assertEqual(scatter_query.projection[0].property.name,
query_splitter.KEY_PROPERTY_NAME)
def make_ancestor_query(kind, namespace, ancestor):
"""Creates a Cloud Datastore ancestor query."""
ancestor_key = entity_pb2.Key()
datastore_helper.add_key_path(ancestor_key, kind, ancestor)
if namespace is not None:
ancestor_key.partition_id.namespace_id = namespace
query = query_pb2.Query()
query.kind.add().name = kind
datastore_helper.set_property_filter(
query.filter, '__key__', PropertyFilter.HAS_ANCESTOR, ancestor_key)
return query
def create_query(self, kinds=(), order=False, limit=None, offset=None,
inequality_filter=False):
query = query_pb2.Query()
for kind in kinds:
query.kind.add().name = kind
if order:
query.order.add()
if limit is not None:
query.limit.value = limit
if offset is not None:
query.offset = offset
if inequality_filter:
test_filter = query.filter.composite_filter.filters.add()
test_filter.property_filter.op = PropertyFilter.GREATER_THAN
return query
def make_query(kind):
"""Creates a Cloud Datastore query to retrieve all entities with a
'created_at' date > N days ago.
"""
days = 4
now = datetime.datetime.now()
earlier = now - datetime.timedelta(days=days)
query = query_pb2.Query()
query.kind.add().name = kind
datastore_helper.set_property_filter(query.filter, 'created_at',
PropertyFilter.GREATER_THAN, earlier)
return query
def query(self):
# Instantiate a filter protobuf
# You MUST instantiate the filter before the query, then instantiate
# the query with the filter.
filter_pb = query_pb2.Filter()
# Get all non-deleted model instances
helper.set_property_filter(filter_pb, 'deleted',
query_pb2.PropertyFilter.EQUAL, False)
# Instantiate a query protobuf
query_pb = query_pb2.Query(filter=filter_pb)
helper.set_kind(query_pb, self.model)
return query_pb
def setUp(self):
self._mock_datastore = MagicMock()
self._query = query_pb2.Query()
self._query.kind.add().name = 'dummy_kind'
patch_retry(self, helper)
self._retriable_errors = [
RPCError("dummy", code_pb2.INTERNAL, "failed"),
SocketError(errno.ECONNRESET, "Connection Reset"),
SocketError(errno.ETIMEDOUT, "Timed out")
]
self._non_retriable_errors = [
RPCError("dummy", code_pb2.UNAUTHENTICATED, "failed"),
SocketError(errno.EADDRNOTAVAIL, "Address not available")
]
def make_ancestor_query(kind, namespace, ancestor):
"""Creates a Cloud Datastore ancestor query.
The returned query will fetch all the entities that have the parent key name
set to the given `ancestor`.
"""
ancestor_key = entity_pb2.Key()
datastore_helper.add_key_path(ancestor_key, kind, ancestor)
if namespace is not None:
ancestor_key.partition_id.namespace_id = namespace
query = query_pb2.Query()
query.kind.add().name = kind
datastore_helper.set_property_filter(
query.filter, '__key__', PropertyFilter.HAS_ANCESTOR, ancestor_key)
return query
def expand(self, pcoll):
query = query_pb2.Query()
query.kind.add().name = 'Tweet'
now = datetime.datetime.now()
# The 'earlier' var will be set to a static value on template creation.
# That is, because of the way that templates work, the value is defined
# at template compile time, not runtime.
# But defining a filter based on this value will still serve to make the
# query more efficient than if we didn't filter at all.
earlier = now - datetime.timedelta(days=self.days)
datastore_helper.set_property_filter(query.filter, 'created_at',
PropertyFilter.GREATER_THAN,
earlier)
return (pcoll
| 'read from datastore' >> ReadFromDatastore(
self.project, query, None))
def make_kind_stats_query(namespace, kind, latest_timestamp):
"""Make a Query to fetch the latest kind statistics."""
kind_stat_query = query_pb2.Query()
if namespace is None:
kind_stat_query.kind.add().name = '__Stat_Kind__'
else:
kind_stat_query.kind.add().name = '__Stat_Ns_Kind__'
kind_filter = datastore_helper.set_property_filter(
query_pb2.Filter(), 'kind_name', PropertyFilter.EQUAL, unicode(kind))
timestamp_filter = datastore_helper.set_property_filter(
query_pb2.Filter(), 'timestamp', PropertyFilter.EQUAL,
latest_timestamp)
datastore_helper.set_composite_filter(kind_stat_query.filter,
CompositeFilter.AND, kind_filter,
timestamp_filter)
return kind_stat_query
def _create_scatter_query(query, num_splits):
"""Creates a scatter query from the given user query."""
scatter_query = query_pb2.Query()
for kind in query.kind:
scatter_kind = scatter_query.kind.add()
scatter_kind.CopyFrom(kind)
# ascending order
datastore_helper.add_property_orders(scatter_query, SCATTER_PROPERTY_NAME)
# There is a split containing entities before and after each scatter entity:
# ||---*------*------*------*------*------*------*---|| * = scatter entity
# If we represent each split as a region before a scatter entity, there is an
# extra region following the last scatter point. Thus, we do not need the
# scatter entity for the last region.
scatter_query.limit.value = (num_splits - 1) * KEYS_PER_SPLIT
datastore_helper.add_projection(scatter_query, KEY_PROPERTY_NAME)
return scatter_query
def test__next_page(self):
from google.cloud.iterator import Page
from google.cloud.proto.datastore.v1 import query_pb2
from google.cloud.datastore.query import Query
connection = _Connection()
more_enum = query_pb2.QueryResultBatch.NOT_FINISHED
result = _make_query_response([], b'', more_enum, 0)
connection._results = [result]
project = 'prujekt'
client = _Client(project, connection)
query = Query(client)
iterator = self._make_one(query, client)
page = iterator._next_page()
self.assertIsInstance(page, Page)
self.assertIs(page._parent, iterator)
self.assertEqual(connection._called_with, [{
'query_pb': query_pb2.Query(),
'project': project,
'namespace': None,
'transaction_id': None,
}])
def run(argv=None):
"""Main entry point."""
parser = argparse.ArgumentParser()
parser.add_argument('--kind',
dest='kind',
default='writereadtest',
help='Datastore Kind')
parser.add_argument('--num_entities',
dest='num_entities',
type=int,
required=True,
help='Number of entities to write')
parser.add_argument('--limit',
dest='limit',
type=int,
help='Limit of number of entities to write')
known_args, pipeline_args = parser.parse_known_args(argv)
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(SetupOptions).save_main_session = True
gcloud_options = pipeline_options.view_as(GoogleCloudOptions)
job_name = gcloud_options.job_name
kind = known_args.kind
num_entities = known_args.num_entities
project = gcloud_options.project
# a random ancesor key
ancestor = str(uuid.uuid4())
query = make_ancestor_query(kind, None, ancestor)
# Pipeline 1: Create and write the specified number of Entities to the
# Cloud Datastore.
logging.info('Writing %s entities to %s', num_entities, project)
p = new_pipeline_with_job_name(pipeline_options, job_name, '-write')
# pylint: disable=expression-not-assigned
(p
| 'Input' >> beam.Create(list(range(known_args.num_entities)))
| 'To String' >> beam.Map(str)
|
'To Entity' >> beam.Map(EntityWrapper(kind, None, ancestor).make_entity)
| 'Write to Datastore' >> WriteToDatastore(project))
p.run()
# Optional Pipeline 2: If a read limit was provided, read it and confirm
# that the expected entities were read.
if known_args.limit is not None:
logging.info(
'Querying a limited set of %s entities and verifying count.',
known_args.limit)
p = new_pipeline_with_job_name(pipeline_options, job_name,
'-verify-limit')
query_with_limit = query_pb2.Query()
query_with_limit.CopyFrom(query)
query_with_limit.limit.value = known_args.limit
entities = p | 'read from datastore' >> ReadFromDatastore(
project, query_with_limit)
assert_that(entities | beam.combiners.Count.Globally(),
equal_to([known_args.limit]))
p.run()
# Pipeline 3: Query the written Entities and verify result.
logging.info('Querying entities, asserting they match.')
p = new_pipeline_with_job_name(pipeline_options, job_name, '-verify')
entities = p | 'read from datastore' >> ReadFromDatastore(project, query)
assert_that(entities | beam.combiners.Count.Globally(),
equal_to([num_entities]))
p.run()
# Pipeline 4: Delete Entities.
logging.info('Deleting entities.')
p = new_pipeline_with_job_name(pipeline_options, job_name, '-delete')
entities = p | 'read from datastore' >> ReadFromDatastore(project, query)
# pylint: disable=expression-not-assigned
(entities
| 'To Keys' >> beam.Map(lambda entity: entity.key)
| 'Delete keys' >> DeleteFromDatastore(project))
p.run()
# Pipeline 5: Query the written Entities, verify no results.
logging.info(
'Querying for the entities to make sure there are none present.')
p = new_pipeline_with_job_name(pipeline_options, job_name,
'-verify-deleted')
entities = p | 'read from datastore' >> ReadFromDatastore(project, query)
assert_that(entities | beam.combiners.Count.Globally(), equal_to([0]))
p.run()
def setUp(self):
self._mock_datastore = MagicMock()
self._query = query_pb2.Query()
self._query.kind.add().name = self._KIND
def test_get_splits_query_with_offset(self):
query = query_pb2.Query()
query.kind.add()
query.offset = 10
self.assertRaises(ValueError, query_splitter.get_splits, None, query,
2)
def test_get_splits_query_with_multiple_kinds(self):
query = query_pb2.Query()
query.kind.add()
query.kind.add()
self.assertRaises(ValueError, query_splitter.get_splits, None, query,
4)
