Merge remote-tracking branch 'upstream/release_22.01' into release_22.05 (f959f05b) · Commits · NDIP / Galaxy

lib/galaxy/tool_util/xsd/galaxy.xsd

+5 −0

Original line number	Diff line number	Diff line
		@@ -2275,6 +2275,11 @@ $attribute_list::5
		</xs:annotation>
		<xs:attributeGroup ref="AssertAttributeN"/>
		<xs:attributeGroup ref="AssertAttributeNegate"/>
		<xs:attribute name="comment" type="xs:string">
		<xs:annotation>
		<xs:documentation xml:lang="en">Comment character(s) used to skip comment lines (which should not be used for counting columns)</xs:documentation>
		</xs:annotation>
		</xs:attribute>
		</xs:complexType>
		<xs:complexType name="AssertHasArchiveMember">
		<xs:annotation>

scripts/cleanup_datasets/admin_cleanup_datasets.py

+24 −23

Original line number	Diff line number	Diff line
		@@ -204,14 +204,15 @@ def administrative_delete_datasets(
		# We really only need the id column here, but sqlalchemy barfs when
		# trying to select only 1 column
		hda_ids_query = sa.select(
		(app.model.HistoryDatasetAssociation.table.c.id, app.model.HistoryDatasetAssociation.table.c.deleted),
		(app.model.HistoryDatasetAssociation.__table__.c.id,
		app.model.HistoryDatasetAssociation.__table__.c.deleted),
		whereclause=and_(
		app.model.Dataset.table.c.deleted == false(),
		app.model.HistoryDatasetAssociation.table.c.update_time < cutoff_time,
		app.model.HistoryDatasetAssociation.table.c.deleted == false(),
		),
		from_obj=[sa.outerjoin(app.model.Dataset.table, app.model.HistoryDatasetAssociation.table)],
		)
		app.model.Dataset.__table__.c.deleted == false(),
		app.model.HistoryDatasetAssociation.__table__.c.update_time < cutoff_time,
		app.model.HistoryDatasetAssociation.__table__.c.deleted == false()),
		from_obj=[sa.outerjoin(
		app.model.Dataset.__table__,
		app.model.HistoryDatasetAssociation.__table__)])

		# Add all datasets associated with Histories to our list
		hda_ids = []
		@@ -232,17 +233,19 @@ def administrative_delete_datasets(
		# Process each of the Dataset objects
		for hda_id in hda_ids:
		user_query = sa.select(
		[app.model.HistoryDatasetAssociation.table, app.model.History.table, app.model.User.table],
		whereclause=and_(app.model.HistoryDatasetAssociation.table.c.id == hda_id),
		from_obj=[
		sa.join(app.model.User.table, app.model.History.table).join(app.model.HistoryDatasetAssociation.table)
		],
		use_labels=True,
		)
		[app.model.HistoryDatasetAssociation.__table__,
		app.model.History.__table__,
		app.model.User.__table__],
		whereclause=and_(
		app.model.HistoryDatasetAssociation.__table__.c.id == hda_id),
		from_obj=[sa.join(app.model.User.__table__,
		app.model.History.__table__)
		.join(app.model.HistoryDatasetAssociation.__table__)],
		use_labels=True)
		for result in app.sa_session.execute(user_query):
		user_notifications[result[app.model.User.table.c.email]].append(
		(result[app.model.HistoryDatasetAssociation.table.c.name], result[app.model.History.table.c.name])
		)
		user_notifications[result[app.model.User.__table__.c.email]].append(
		(result[app.model.HistoryDatasetAssociation.__table__.c.name],
		result[app.model.History.__table__.c.name]))
		deleted_instance_count += 1
		if not info_only and not email_only:
		# Get the HistoryDatasetAssociation objects
		@@ -279,12 +282,10 @@ def _get_tool_id_for_hda(app, hda_id):
		# TODO Some datasets don't seem to have an entry in jtod or a copied_from
		if hda_id is None:
		return None
		job = (
		app.sa_session.query(app.model.Job)
		.join(app.model.JobToOutputDatasetAssociation)
		.filter(app.model.JobToOutputDatasetAssociation.table.c.dataset_id == hda_id)
		.first()
		)
		job = app.sa_session.query(app.model.Job).\
		join(app.model.JobToOutputDatasetAssociation).\
		filter(app.model.JobToOutputDatasetAssociation.__table__.c.dataset_id
		== hda_id).first()
		if job is not None:
		return job.tool_id
		else:

scripts/cleanup_datasets/cleanup_datasets.py

+65 −98

Original line number	Diff line number	Diff line
		@@ -222,17 +222,14 @@ def delete_userless_histories(app, cutoff_time, info_only=False, force_retry=Fal
		history_count = 0
		start = time.time()
		if force_retry:
		histories = app.sa_session.query(app.model.History).filter(
		and_(app.model.History.table.c.user_id == null(), app.model.History.update_time < cutoff_time)
		)
		histories = app.sa_session.query(app.model.History) \
		.filter(and_(app.model.History.__table__.c.user_id == null(),
		app.model.History.update_time < cutoff_time))
		else:
		histories = app.sa_session.query(app.model.History).filter(
		and_(
		app.model.History.table.c.user_id == null(),
		app.model.History.table.c.deleted == false(),
		app.model.History.update_time < cutoff_time,
		)
		)
		histories = app.sa_session.query(app.model.History) \
		.filter(and_(app.model.History.__table__.c.user_id == null(),
		app.model.History.__table__.c.deleted == false(),
		app.model.History.update_time < cutoff_time))
		for history in histories:
		if not info_only:
		log.info("Deleting history id %d", history.id)
		@@ -255,23 +252,16 @@ def purge_histories(app, cutoff_time, remove_from_disk, info_only=False, force_r
		history_count = 0
		start = time.time()
		if force_retry:
		histories = (
		app.sa_session.query(app.model.History)
		.filter(and_(app.model.History.table.c.deleted == true(), app.model.History.update_time < cutoff_time))
		.options(joinedload("datasets"))
		)
		histories = app.sa_session.query(app.model.History) \
		.filter(and_(app.model.History.__table__.c.deleted == true(),
		app.model.History.update_time < cutoff_time)) \
		.options(eagerload('datasets'))
		else:
		histories = (
		app.sa_session.query(app.model.History)
		.filter(
		and_(
		app.model.History.table.c.deleted == true(),
		app.model.History.table.c.purged == false(),
		app.model.History.update_time < cutoff_time,
		)
		)
		.options(joinedload("datasets"))
		)
		histories = app.sa_session.query(app.model.History) \
		.filter(and_(app.model.History.__table__.c.deleted == true(),
		app.model.History.__table__.c.purged == false(),
		app.model.History.update_time < cutoff_time)) \
		.options(eagerload('datasets'))
		for history in histories:
		log.info("### Processing history id %d (%s)", history.id, unicodify(history.name))
		for dataset_assoc in history.datasets:
		@@ -306,17 +296,14 @@ def purge_libraries(app, cutoff_time, remove_from_disk, info_only=False, force_r
		library_count = 0
		start = time.time()
		if force_retry:
		libraries = app.sa_session.query(app.model.Library).filter(
		and_(app.model.Library.table.c.deleted == true(), app.model.Library.table.c.update_time < cutoff_time)
		)
		libraries = app.sa_session.query(app.model.Library) \
		.filter(and_(app.model.Library.__table__.c.deleted == true(),
		app.model.Library.__table__.c.update_time < cutoff_time))
		else:
		libraries = app.sa_session.query(app.model.Library).filter(
		and_(
		app.model.Library.table.c.deleted == true(),
		app.model.Library.table.c.purged == false(),
		app.model.Library.table.c.update_time < cutoff_time,
		)
		)
		libraries = app.sa_session.query(app.model.Library) \
		.filter(and_(app.model.Library.__table__.c.deleted == true(),
		app.model.Library.__table__.c.purged == false(),
		app.model.Library.__table__.c.update_time < cutoff_time))
		for library in libraries:
		_purge_folder(library.root_folder, app, remove_from_disk, info_only=info_only)
		if not info_only:
		@@ -340,20 +327,14 @@ def purge_folders(app, cutoff_time, remove_from_disk, info_only=False, force_ret
		folder_count = 0
		start = time.time()
		if force_retry:
		folders = app.sa_session.query(app.model.LibraryFolder).filter(
		and_(
		app.model.LibraryFolder.table.c.deleted == true(),
		app.model.LibraryFolder.table.c.update_time < cutoff_time,
		)
		)
		folders = app.sa_session.query(app.model.LibraryFolder) \
		.filter(and_(app.model.LibraryFolder.__table__.c.deleted == true(),
		app.model.LibraryFolder.__table__.c.update_time < cutoff_time))
		else:
		folders = app.sa_session.query(app.model.LibraryFolder).filter(
		and_(
		app.model.LibraryFolder.table.c.deleted == true(),
		app.model.LibraryFolder.table.c.purged == false(),
		app.model.LibraryFolder.table.c.update_time < cutoff_time,
		)
		)
		folders = app.sa_session.query(app.model.LibraryFolder) \
		.filter(and_(app.model.LibraryFolder.__table__.c.deleted == true(),
		app.model.LibraryFolder.__table__.c.purged == false(),
		app.model.LibraryFolder.__table__.c.update_time < cutoff_time))
		for folder in folders:
		_purge_folder(folder, app, remove_from_disk, info_only=info_only)
		folder_count += 1
		@@ -367,36 +348,30 @@ def delete_datasets(app, cutoff_time, remove_from_disk, info_only=False, force_r
		# Marks datasets as deleted if associated items are all deleted.
		start = time.time()
		if force_retry:
		history_dataset_ids_query = sa.select(
		(app.model.Dataset.table.c.id, app.model.Dataset.table.c.state),
		whereclause=app.model.HistoryDatasetAssociation.table.c.update_time < cutoff_time,
		from_obj=[sa.outerjoin(app.model.Dataset.table, app.model.HistoryDatasetAssociation.table)],
		)
		library_dataset_ids_query = sa.select(
		(app.model.LibraryDataset.table.c.id, app.model.LibraryDataset.table.c.deleted),
		whereclause=app.model.LibraryDataset.table.c.update_time < cutoff_time,
		from_obj=[app.model.LibraryDataset.table],
		)
		history_dataset_ids_query = sa.select((app.model.Dataset.__table__.c.id,
		app.model.Dataset.__table__.c.state),
		whereclause=app.model.HistoryDatasetAssociation.__table__.c.update_time < cutoff_time,
		from_obj=[sa.outerjoin(app.model.Dataset.__table__,
		app.model.HistoryDatasetAssociation.__table__)])
		library_dataset_ids_query = sa.select((app.model.LibraryDataset.__table__.c.id,
		app.model.LibraryDataset.__table__.c.deleted),
		whereclause=app.model.LibraryDataset.__table__.c.update_time < cutoff_time,
		from_obj=[app.model.LibraryDataset.__table__])
		else:
		# We really only need the id column here, but sqlalchemy barfs when trying to select only 1 column
		history_dataset_ids_query = sa.select(
		(app.model.Dataset.table.c.id, app.model.Dataset.table.c.state),
		whereclause=and_(
		app.model.Dataset.table.c.deleted == false(),
		app.model.HistoryDatasetAssociation.table.c.update_time < cutoff_time,
		app.model.HistoryDatasetAssociation.table.c.deleted == true(),
		),
		from_obj=[sa.outerjoin(app.model.Dataset.table, app.model.HistoryDatasetAssociation.table)],
		)
		library_dataset_ids_query = sa.select(
		(app.model.LibraryDataset.table.c.id, app.model.LibraryDataset.table.c.deleted),
		whereclause=and_(
		app.model.LibraryDataset.table.c.deleted == true(),
		app.model.LibraryDataset.table.c.purged == false(),
		app.model.LibraryDataset.table.c.update_time < cutoff_time,
		),
		from_obj=[app.model.LibraryDataset.table],
		)
		history_dataset_ids_query = sa.select((app.model.Dataset.__table__.c.id,
		app.model.Dataset.__table__.c.state),
		whereclause=and_(app.model.Dataset.__table__.c.deleted == false(),
		app.model.HistoryDatasetAssociation.__table__.c.update_time < cutoff_time,
		app.model.HistoryDatasetAssociation.__table__.c.deleted == true()),
		from_obj=[sa.outerjoin(app.model.Dataset.__table__,
		app.model.HistoryDatasetAssociation.__table__)])
		library_dataset_ids_query = sa.select((app.model.LibraryDataset.__table__.c.id,
		app.model.LibraryDataset.__table__.c.deleted),
		whereclause=and_(app.model.LibraryDataset.__table__.c.deleted == true(),
		app.model.LibraryDataset.__table__.c.purged == false(),
		app.model.LibraryDataset.__table__.c.update_time < cutoff_time),
		from_obj=[app.model.LibraryDataset.__table__])
		deleted_dataset_count = 0
		deleted_instance_count = 0
		skip = []
		@@ -469,22 +444,16 @@ def purge_datasets(app, cutoff_time, remove_from_disk, info_only=False, force_re
		disk_space = 0
		start = time.time()
		if force_retry:
		datasets = app.sa_session.query(app.model.Dataset).filter(
		and_(
		app.model.Dataset.table.c.deleted == true(),
		app.model.Dataset.table.c.purgable == true(),
		app.model.Dataset.table.c.update_time < cutoff_time,
		)
		)
		datasets = app.sa_session.query(app.model.Dataset) \
		.filter(and_(app.model.Dataset.__table__.c.deleted == true(),
		app.model.Dataset.__table__.c.purgable == true(),
		app.model.Dataset.__table__.c.update_time < cutoff_time))
		else:
		datasets = app.sa_session.query(app.model.Dataset).filter(
		and_(
		app.model.Dataset.table.c.deleted == true(),
		app.model.Dataset.table.c.purgable == true(),
		app.model.Dataset.table.c.purged == false(),
		app.model.Dataset.table.c.update_time < cutoff_time,
		)
		)
		datasets = app.sa_session.query(app.model.Dataset) \
		.filter(and_(app.model.Dataset.__table__.c.deleted == true(),
		app.model.Dataset.__table__.c.purgable == true(),
		app.model.Dataset.__table__.c.purged == false(),
		app.model.Dataset.__table__.c.update_time < cutoff_time))
		for dataset in datasets:
		file_size = dataset.file_size
		_purge_dataset(app, dataset, remove_from_disk, info_only=info_only)
		@@ -554,14 +523,12 @@ def _delete_dataset(dataset, app, remove_from_disk, info_only=False, is_deletabl
		metadata_files = []
		# lets create a list of metadata files, then perform actions on them
		for hda in dataset.history_associations:
		for metadata_file in app.sa_session.query(app.model.MetadataFile).filter(
		app.model.MetadataFile.table.c.hda_id == hda.id
		):
		for metadata_file in app.sa_session.query(app.model.MetadataFile) \
		.filter(app.model.MetadataFile.__table__.c.hda_id == hda.id):
		metadata_files.append(metadata_file)
		for ldda in dataset.library_associations:
		for metadata_file in app.sa_session.query(app.model.MetadataFile).filter(
		app.model.MetadataFile.table.c.lda_id == ldda.id
		):
		for metadata_file in app.sa_session.query(app.model.MetadataFile) \
		.filter(app.model.MetadataFile.__table__.c.lda_id == ldda.id):
		metadata_files.append(metadata_file)
		for metadata_file in metadata_files:
		op_description = "marked as deleted"

Admin message