[ https://issues.apache.org/jira/browse/BEAM-7860?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Niels Stender updated BEAM-7860: -------------------------------- Description: In the presence of mixed type keys, v1new ReadFromDatastore may return duplicate items. The attached example returns 4 records, not the expected 3. {code:java} // code placeholder from __future__ import unicode_literals import apache_beam as beam from apache_beam.io.gcp.datastore.v1new.types import Key, Entity, Query from apache_beam.io.gcp.datastore.v1new import datastoreio config = dict(project='your-google-project', namespace='test') def test_mixed(): keys = [ Key(['mixed', '10038260-iperm_eservice'], **config), Key(['mixed', 4812224868188160L], **config), Key(['mixed', '99152975-pointshop'], **config) ] entities = map(lambda key: Entity(key=key), keys) with beam.Pipeline() as p: (p | beam.Create(entities) | datastoreio.WriteToDatastore(project=config['project']) ) query = Query(kind=u'mixed', **config) with beam.Pipeline() as p: (p | datastoreio.ReadFromDatastore(query=query, num_splits=4) | beam.io.WriteToText('tmp.txt', num_shards=1, shard_name_template='') ) items = open('tmp.txt').read().strip().split('\n') assert len(items) == 3, 'incorrect number of items' {code} was: In the presence of mixed type keys, v1new ReadFromDatastore may return duplicate items. The attached example returns 4 records, not the expected 3. {code:java} // code placeholder import apache_beam as beam from apache_beam.io.gcp.datastore.v1new.types import Key, Entity, Query from apache_beam.io.gcp.datastore.v1new import datastoreio config = dict(project='your-google-project', namespace='test') def test_mixed(): keys = [ Key([u'mixed', u'10038260-iperm_eservice'], **config), Key([u'mixed', 4812224868188160L], **config), Key([u'mixed', u'99152975-pointshop'], **config) ] entities = map(lambda key: Entity(key=key), keys) with beam.Pipeline() as p: (p | beam.Create(entities) | datastoreio.WriteToDatastore(project=config['project']) ) query = Query(kind=u'mixed', **config) with beam.Pipeline() as p: (p | datastoreio.ReadFromDatastore(query=query, num_splits=4) | beam.io.WriteToText('tmp.txt', num_shards=1, shard_name_template='') ) items = open('tmp.txt').read().strip().split('\n') assert len(items) == 3, 'incorrect number of items' {code} > v1new ReadFromDatastore splits incorrectly in the presence of mixed type keys > ----------------------------------------------------------------------------- > > Key: BEAM-7860 > URL: https://issues.apache.org/jira/browse/BEAM-7860 > Project: Beam > Issue Type: Bug > Components: io-python-gcp > Affects Versions: 2.13.0 > Environment: Python 2.7 > Reporter: Niels Stender > Priority: Major > > In the presence of mixed type keys, v1new ReadFromDatastore may return > duplicate items. The attached example returns 4 records, not the expected 3. > > {code:java} > // code placeholder > from __future__ import unicode_literals > import apache_beam as beam > from apache_beam.io.gcp.datastore.v1new.types import Key, Entity, Query > from apache_beam.io.gcp.datastore.v1new import datastoreio > config = dict(project='your-google-project', namespace='test') > def test_mixed(): > keys = [ > Key(['mixed', '10038260-iperm_eservice'], **config), > Key(['mixed', 4812224868188160L], **config), > Key(['mixed', '99152975-pointshop'], **config) > ] > entities = map(lambda key: Entity(key=key), keys) > with beam.Pipeline() as p: > (p > | beam.Create(entities) > | datastoreio.WriteToDatastore(project=config['project']) > ) > query = Query(kind=u'mixed', **config) > with beam.Pipeline() as p: > (p > | datastoreio.ReadFromDatastore(query=query, num_splits=4) > | beam.io.WriteToText('tmp.txt', num_shards=1, > shard_name_template='') > ) > items = open('tmp.txt').read().strip().split('\n') > assert len(items) == 3, 'incorrect number of items' > {code} -- This message was sent by Atlassian JIRA (v7.6.14#76016)