Warning

This document is for an old release of Galaxy. You can alternatively view this page in the latest release if it exists or view the top of the latest release's documentation.

galaxy.model.store package

class galaxy.model.store.StoreAppProtocol(*args, **kwds)

Bases: Protocol

Define the parts of a Galaxy-like app consumed by model store.

datatypes_registry: Registry

object_store: ObjectStore

security: IdEncodingHelper

tag_handler: GalaxyTagHandler

model: GalaxyModelMapping

file_sources: ConfiguredFileSources

__init__(*args, **kwargs)

class galaxy.model.store.ImportDiscardedDataType(value)

Bases: Enum

An enumeration.

FORBID = 'forbid'

ALLOW = 'allow'

FORCE = 'force'

class galaxy.model.store.ImportOptions(allow_edit=False, allow_library_creation=False, allow_dataset_object_edit=None, discarded_data=ImportDiscardedDataType.FORBID)

Bases: object

__init__(allow_edit=False, allow_library_creation=False, allow_dataset_object_edit=None, discarded_data=ImportDiscardedDataType.FORBID)

allow_edit: bool

allow_library_creation: bool

allow_dataset_object_edit: bool

discarded_data: ImportDiscardedDataType

class galaxy.model.store.SessionlessContext

Bases: object

__init__()

flush()

add(obj)

query(model_class)

galaxy.model.store.replace_metadata_file(metadata: Dict[str, Any], dataset_instance: DatasetInstance, sa_session)

class galaxy.model.store.ModelImportStore(import_options=None, app: Optional[StoreAppProtocol] = None, user=None, object_store=None, tag_handler=None)

Bases: object

__init__(import_options=None, app: Optional[StoreAppProtocol] = None, user=None, object_store=None, tag_handler=None)

app: Optional[StoreAppProtocol]

abstract defines_new_history() → bool

Does this store define a new history to create.

abstract new_history_properties() → Dict[str, Any]

Dict of history properties if defines_new_history() is truthy.

abstract datasets_properties() → List[Dict[str, Any]]

Return a list of HDA properties.

library_properties() → List[Dict[str, Any]]

Return a list of library properties.

abstract collections_properties() → List[Dict[str, Any]]

Return a list of HDCA properties.

abstract jobs_properties() → List[Dict[str, Any]]

Return a list of jobs properties.

abstract property object_key: str

Key used to connect objects in metadata.

Legacy exports used ‘hid’ but associated objects may not be from the same history and a history may contain multiple objects with the same ‘hid’.

property file_source_root: Optional[str]

Source of valid file data.

trust_hid(obj_attrs) → bool

Trust HID when importing objects into a new History.

target_history(default_history=None, legacy_history_naming=True)

perform_import(history=None, new_history=False, job=None)

class galaxy.model.store.ObjectImportTracker

Bases: object

Keep track of new and existing imported objects.

Needed to re-establish connections and such in multiple passes.

__init__()

libraries_by_key: Dict[Union[str, int], Library]

hdas_by_key: Dict[Union[str, int], HistoryDatasetAssociation]

hdas_by_id: Dict[int, HistoryDatasetAssociation]

hdcas_by_key: Dict[Union[str, int], HistoryDatasetCollectionAssociation]

hdcas_by_id: Dict[int, HistoryDatasetCollectionAssociation]

dces_by_key: Dict[Union[str, int], DatasetCollectionElement]

dces_by_id: Dict[int, DatasetCollectionElement]

lddas_by_key: Dict[Union[str, int], LibraryDatasetDatasetAssociation]

hda_copied_from_sinks: Dict[Union[str, int], Union[str, int]]

hdca_copied_from_sinks: Dict[Union[str, int], Union[str, int]]

jobs_by_key: Dict[Union[str, int], Job]

requires_hid: List[Union[HistoryDatasetAssociation, HistoryDatasetCollectionAssociation]]

find_hda(input_key: Union[str, int], hda_id: Optional[int] = None) → Optional[HistoryDatasetAssociation]

find_hdca(input_key: Union[str, int]) → Optional[HistoryDatasetCollectionAssociation]

find_dce(input_key: Union[str, int]) → Optional[DatasetCollectionElement]

exception galaxy.model.store.FileTracebackException(traceback, *args, **kwargs)

Bases: Exception

__init__(traceback, *args, **kwargs)

galaxy.model.store.get_import_model_store_for_directory(archive_dir, **kwd)

class galaxy.model.store.DictImportModelStore(store_as_dict, **kwd)

Bases: ModelImportStore

object_key = 'encoded_id'

__init__(store_as_dict, **kwd)

defines_new_history() → bool

Does this store define a new history to create.

new_history_properties()

Dict of history properties if defines_new_history() is truthy.

datasets_properties()

Return a list of HDA properties.

collections_properties()

Return a list of HDCA properties.

library_properties()

Return a list of library properties.

jobs_properties()

Return a list of jobs properties.

implicit_collection_jobs_properties()

invocations_properties()

workflow_paths()

app: Optional[StoreAppProtocol]

galaxy.model.store.get_import_model_store_for_dict(as_dict, **kwd)

class galaxy.model.store.BaseDirectoryImportModelStore(import_options=None, app: Optional[StoreAppProtocol] = None, user=None, object_store=None, tag_handler=None)

Bases: ModelImportStore

property file_source_root

Source of valid file data.

defines_new_history()

Does this store define a new history to create.

new_history_properties()

Dict of history properties if defines_new_history() is truthy.

datasets_properties()

Return a list of HDA properties.

collections_properties()

Return a list of HDCA properties.

library_properties()

Return a list of library properties.

jobs_properties()

Return a list of jobs properties.

implicit_collection_jobs_properties()

invocations_properties()

workflow_paths()

app: Optional[StoreAppProtocol]

galaxy.model.store.restore_times(model_object, attrs)

class galaxy.model.store.DirectoryImportModelStore1901(archive_dir, **kwd)

Bases: BaseDirectoryImportModelStore

object_key = 'hid'

__init__(archive_dir, **kwd)

trust_hid(obj_attrs)

Trust HID when importing objects into a new History.

app: Optional[StoreAppProtocol]

class galaxy.model.store.DirectoryImportModelStoreLatest(archive_dir, **kwd)

Bases: BaseDirectoryImportModelStore

object_key = 'encoded_id'

__init__(archive_dir, **kwd)

trust_hid(obj_attrs)

Trust HID when importing objects into a new History.

app: Optional[StoreAppProtocol]

class galaxy.model.store.BagArchiveImportModelStore(bag_archive, **kwd)

Bases: DirectoryImportModelStoreLatest

__init__(bag_archive, **kwd)

app: Optional[StoreAppProtocol]

class galaxy.model.store.ModelExportStore

Bases: object

abstract export_history(history: History, include_hidden: bool = False, include_deleted: bool = False)

Export history to store.

abstract export_library(history, include_hidden=False, include_deleted=False)

Export library to store.

abstract export_workflow_invocation(workflow_invocation, include_hidden=False, include_deleted=False)

Export workflow invocation to store.

abstract add_dataset_collection(collection: Union[DatasetCollection, HistoryDatasetCollectionAssociation])

Add Dataset Collection or HDCA to export store.

abstract add_dataset(dataset: DatasetInstance, include_files: bool = True)

Add HDA to export store.

include_files controls whether file contents are exported as well.

class galaxy.model.store.DirectoryModelExportStore(export_directory: str, app: Optional[StoreAppProtocol] = None, file_sources: Optional[ConfiguredFileSources] = None, for_edit: bool = False, serialize_dataset_objects=None, export_files: Optional[str] = None, strip_metadata_files: bool = True, serialize_jobs: bool = True, user_context=None)

Bases: ModelExportStore

__init__(export_directory: str, app: Optional[StoreAppProtocol] = None, file_sources: Optional[ConfiguredFileSources] = None, for_edit: bool = False, serialize_dataset_objects=None, export_files: Optional[str] = None, strip_metadata_files: bool = True, serialize_jobs: bool = True, user_context=None) → None

Parameters

• export_directory – path to export directory. Will be created if it does not exist.

• app – Galaxy App or app-like object. Must be provided if for_edit and/or serialize_dataset_objects are True

• for_edit – Allow modifying existing HDA and dataset metadata during import.

• serialize_dataset_objects – If True will encode IDs using the host secret. Defaults for_edit.

• export_files – How files should be exported, can be ‘symlink’, ‘copy’ or None, in which case files will not be serialized.

• serialize_jobs – Include job data in model export. Not needed for set_metadata script.

app: Optional[StoreAppProtocol]

file_sources: Optional[ConfiguredFileSources]

property workflows_directory

serialize_files(dataset: DatasetInstance, as_dict: Dict[str, Any]) → None

exported_key(obj)

push_metadata_files()

export_job(job: Job, tool=None, include_job_data=True)

export_jobs(jobs: List[Job], jobs_attrs=None, include_job_data=True)

Export jobs.

include_job_data determines whether datasets associated with jobs should be exported as well. This should generally be True, except when re-exporting a job (to store the generated command line) when running the set_meta script.

export_history(history: History, include_hidden: bool = False, include_deleted: bool = False) → None

Export history to store.

export_library(library: Library, include_hidden=False, include_deleted=False)

Export library to store.

export_library_folder(library_folder: LibraryFolder, include_hidden=False, include_deleted=False)

export_library_folder_contents(library_folder: LibraryFolder, include_hidden=False, include_deleted=False)

export_workflow_invocation(workflow_invocation: WorkflowInvocation, include_hidden=False, include_deleted=False)

Export workflow invocation to store.

add_job_output_dataset_associations(job_id: int, name: str, dataset_instance: DatasetInstance) → None

export_collection(collection: Union[DatasetCollection, HistoryDatasetCollectionAssociation], include_deleted: bool = False, include_hidden: bool = False) → None

add_dataset_collection(collection: Union[DatasetCollection, HistoryDatasetCollectionAssociation]) → None

Add Dataset Collection or HDCA to export store.

add_dataset(dataset: DatasetInstance, include_files: bool = True) → None

Add HDA to export store.

include_files controls whether file contents are exported as well.

class galaxy.model.store.TarModelExportStore(uri, gzip=True, **kwds)

Bases: DirectoryModelExportStore

__init__(uri, gzip=True, **kwds)

Parameters

• export_directory – path to export directory. Will be created if it does not exist.

• app – Galaxy App or app-like object. Must be provided if for_edit and/or serialize_dataset_objects are True

• for_edit – Allow modifying existing HDA and dataset metadata during import.

• serialize_dataset_objects – If True will encode IDs using the host secret. Defaults for_edit.

• export_files – How files should be exported, can be ‘symlink’, ‘copy’ or None, in which case files will not be serialized.

• serialize_jobs – Include job data in model export. Not needed for set_metadata script.

app: Optional[StoreAppProtocol]

file_sources: Optional[ConfiguredFileSources]

included_datasets: Dict[DatasetInstance, Tuple[DatasetInstance, bool]]

included_collections: List[Union[DatasetCollection, HistoryDatasetCollectionAssociation]]

included_libraries: List[Library]

included_library_folders: List[LibraryFolder]

included_invocations: List[WorkflowInvocation]

collection_datasets: Set[int]

collections_attrs: List[Union[DatasetCollection, HistoryDatasetCollectionAssociation]]

dataset_id_to_path: Dict[int, Tuple[Optional[str], Optional[str]]]

job_output_dataset_associations: Dict[int, Dict[str, DatasetInstance]]

class galaxy.model.store.BagDirectoryModelExportStore(out_directory, **kwds)

Bases: DirectoryModelExportStore

app: Optional[StoreAppProtocol]

file_sources: Optional[ConfiguredFileSources]

included_datasets: Dict[DatasetInstance, Tuple[DatasetInstance, bool]]

included_collections: List[Union[DatasetCollection, HistoryDatasetCollectionAssociation]]

included_libraries: List[Library]

included_library_folders: List[LibraryFolder]

included_invocations: List[WorkflowInvocation]

collection_datasets: Set[int]

collections_attrs: List[Union[DatasetCollection, HistoryDatasetCollectionAssociation]]

dataset_id_to_path: Dict[int, Tuple[Optional[str], Optional[str]]]

job_output_dataset_associations: Dict[int, Dict[str, DatasetInstance]]

__init__(out_directory, **kwds)

Parameters

• export_directory – path to export directory. Will be created if it does not exist.

• app – Galaxy App or app-like object. Must be provided if for_edit and/or serialize_dataset_objects are True

• for_edit – Allow modifying existing HDA and dataset metadata during import.

• serialize_dataset_objects – If True will encode IDs using the host secret. Defaults for_edit.

• export_files – How files should be exported, can be ‘symlink’, ‘copy’ or None, in which case files will not be serialized.

• serialize_jobs – Include job data in model export. Not needed for set_metadata script.

class galaxy.model.store.BagArchiveModelExportStore(uri, bag_archiver='tgz', **kwds)

Bases: BagDirectoryModelExportStore

app: Optional[StoreAppProtocol]

file_sources: Optional[ConfiguredFileSources]

included_datasets: Dict[DatasetInstance, Tuple[DatasetInstance, bool]]

included_collections: List[Union[DatasetCollection, HistoryDatasetCollectionAssociation]]

included_libraries: List[Library]

included_library_folders: List[LibraryFolder]

included_invocations: List[WorkflowInvocation]

collection_datasets: Set[int]

collections_attrs: List[Union[DatasetCollection, HistoryDatasetCollectionAssociation]]

dataset_id_to_path: Dict[int, Tuple[Optional[str], Optional[str]]]

job_output_dataset_associations: Dict[int, Dict[str, DatasetInstance]]

__init__(uri, bag_archiver='tgz', **kwds)

Parameters

• export_directory – path to export directory. Will be created if it does not exist.

• app – Galaxy App or app-like object. Must be provided if for_edit and/or serialize_dataset_objects are True

• for_edit – Allow modifying existing HDA and dataset metadata during import.

• serialize_dataset_objects – If True will encode IDs using the host secret. Defaults for_edit.

• export_files – How files should be exported, can be ‘symlink’, ‘copy’ or None, in which case files will not be serialized.

• serialize_jobs – Include job data in model export. Not needed for set_metadata script.

galaxy.model.store.get_export_store_factory(app, download_format: str, export_files=None, user_context=None) → Callable[[str], ModelExportStore]

galaxy.model.store.tar_export_directory(export_directory: str, out_file: str, gzip: bool) → None

galaxy.model.store.get_export_dataset_filename(name, ext, hid)

Builds a filename for a dataset using its name an extension.

galaxy.model.store.imported_store_for_metadata(directory, object_store=None)

galaxy.model.store.source_to_import_store(source: Union[str, dict], app: StoreAppProtocol, import_options: Optional[ImportOptions], model_store_format: Optional[ModelStoreFormat] = None, user_context=None) → ModelImportStore

galaxy.model.store.payload_to_source_uri(payload) → str

Submodules

galaxy.model.store.build_objects module

galaxy.model.store.build_objects.main(argv=None)

galaxy.model.store.discover module

Utilities for discovering files to add to a model store.

Working with input “JSON” format used for Fetch API, galaxy.json imports, etc… High-level utilities in this file can be used during job output discovery or for persisting Galaxy model objects corresponding to files in other contexts.

exception galaxy.model.store.discover.MaxDiscoveredFilesExceededError

Bases: ValueError

class galaxy.model.store.discover.ModelPersistenceContext

Bases: object

Class for creating datasets while finding files.

This class implement the create_dataset method that takes care of populating metadata required for datasets and other potential model objects.

job_working_directory: str

max_discovered_files = inf

discovered_file_count: int

create_dataset(ext, designation, visible, dbkey, name, filename=None, extra_files=None, metadata_source_name=None, info=None, library_folder=None, link_data=False, primary_data=None, init_from=None, dataset_attributes=None, tag_list=None, sources=None, hashes=None, created_from_basename=None, final_job_state='ok', creating_job_id=None, storage_callbacks=None)

finalize_storage(primary_data, dataset_attributes, extra_files, filename, link_data)

static set_datasets_metadata(datasets, datasets_attributes=None)

populate_collection_elements(collection, root_collection_builder, discovered_files, name=None, metadata_source_name=None, final_job_state='ok')

add_tags_to_datasets(datasets, tag_lists)

update_object_store_with_datasets(datasets, paths, extra_files)

abstract property tag_handler

Return a galaxy.model.tags.TagHandler-like object for persisting tags.

abstract property user

If bound to a database, return the user the datasets should be created for.

Return None otherwise.

abstract property sa_session: Optional[scoped_session]

If bound to a database, return the SQL Alchemy session.

Return None otherwise.

abstract property permission_provider: PermissionProvider

If bound to a database, return the SQL Alchemy session.

Return None otherwise.

get_implicit_collection_jobs_association_id() → Optional[str]

No-op, no job context.

abstract property job: Optional[Job]

Return associated job object if bound to a job finish context connected to a database.

abstract property metadata_source_provider: MetadataSourceProvider

Return associated MetadataSourceProvider object.

abstract property object_store: ObjectStore

Return object store to use for populating discovered dataset contents.

abstract property flush_per_n_datasets: Optional[int]

property input_dbkey: str

abstract add_library_dataset_to_folder(library_folder, ld)

Add library dataset to persisted library folder.

abstract create_library_folder(parent_folder, name, description)

Create a library folder ready from supplied attributes for supplied parent.

abstract add_output_dataset_association(name, dataset)

If discovering outputs for a job, persist output dataset association.

add_datasets_to_history(datasets, for_output_dataset=None)

Add datasets to the history this context points at.

job_id()

persist_object(obj)

Add the target to the persistence layer.

persist_library_folder(library_folder)

Add library folder to sessionless export. Noop for session export.

flush()

If database bound, flush the persisted objects to ensure IDs.

increment_discovered_file_count()

class galaxy.model.store.discover.PermissionProvider

Bases: object

Interface for working with permissions while importing datasets with ModelPersistenceContext.

property permissions

set_default_hda_permissions(primary_data)

abstract copy_dataset_permissions(init_from, primary_data)

Copy dataset permissions from supplied input dataset.

class galaxy.model.store.discover.UnusedPermissionProvider

Bases: PermissionProvider

copy_dataset_permissions(init_from, primary_data)

Throws NotImplementedError.

This should only be called as part of job output collection where there should be a session available to initialize this from.

class galaxy.model.store.discover.MetadataSourceProvider

Bases: object

Interface for working with fetching input dataset metadata with ModelPersistenceContext.

abstract get_metadata_source(input_name)

Get metadata for supplied input_name.

class galaxy.model.store.discover.UnusedMetadataSourceProvider

Bases: MetadataSourceProvider

get_metadata_source(input_name)

Throws NotImplementedError.

This should only be called as part of job output collection where one can actually collect metadata from inputs, this is unused in the context of SessionlessModelPersistenceContext.

class galaxy.model.store.discover.SessionlessModelPersistenceContext(object_store, export_store, working_directory)

Bases: ModelPersistenceContext

A variant of ModelPersistenceContext that persists to an export store instead of database directly.

__init__(object_store, export_store, working_directory)

discovered_file_count: int

job_working_directory: str

property tag_handler

Return a galaxy.model.tags.TagHandler-like object for persisting tags.

property sa_session

If bound to a database, return the SQL Alchemy session.

Return None otherwise.

property user

If bound to a database, return the user the datasets should be created for.

Return None otherwise.

property job

Return associated job object if bound to a job finish context connected to a database.

property permission_provider: UnusedPermissionProvider

If bound to a database, return the SQL Alchemy session.

Return None otherwise.

property metadata_source_provider: UnusedMetadataSourceProvider

Return associated MetadataSourceProvider object.

property object_store: ObjectStore

Return object store to use for populating discovered dataset contents.

property flush_per_n_datasets: Optional[int]

add_tags_to_datasets(datasets, tag_lists)

add_library_dataset_to_folder(library_folder, ld)

Add library dataset to persisted library folder.

get_library_folder(destination)

get_hdca(object_id)

create_hdca(name, structure)

create_library_folder(parent_folder, name, description)

Create a library folder ready from supplied attributes for supplied parent.

persist_library_folder(library_folder)

Add library folder to sessionless export. Noop for session export.

add_datasets_to_history(datasets, for_output_dataset=None)

Add datasets to the history this context points at.

persist_object(obj)

No-op right now for the sessionless variant of this.

This works currently because either things are added to a target history with add_datasets_to_history or the parent LibraryFolder was added to the export store in persist_target_to_export_store.

flush()

No-op for the sessionless variant of this, no database to flush.

add_output_dataset_association(name, dataset)

No-op, no job context to persist this association for.

get_implicit_collection_jobs_association_id()

No-op, no job context.

galaxy.model.store.discover.persist_extra_files(object_store, src_extra_files_path, primary_data)

galaxy.model.store.discover.persist_target_to_export_store(target_dict, export_store, object_store, work_directory)

galaxy.model.store.discover.persist_elements_to_hdca(model_persistence_context: ModelPersistenceContext, elements, hdca, collector=None)

galaxy.model.store.discover.persist_elements_to_folder(model_persistence_context, elements, library_folder)

galaxy.model.store.discover.persist_hdas(elements, model_persistence_context, final_job_state='ok')

galaxy.model.store.discover.get_required_item(from_dict, key, message)

galaxy.model.store.discover.validate_and_normalize_target(obj)

galaxy.model.store.discover.replace_request_syntax_sugar(obj)

class galaxy.model.store.discover.DiscoveredFile(path, collector, match)

Bases: tuple

property path

Alias for field number 0

property collector

Alias for field number 1

property match

Alias for field number 2

discovered_state(element: Dict[str, Any], final_job_state='ok') → DiscoveredResultState

class galaxy.model.store.discover.DiscoveredResultState(info, state)

Bases: tuple

property info

Alias for field number 0

property state

Alias for field number 1

class galaxy.model.store.discover.DiscoveredDeferredFile(collector, match)

Bases: tuple

property collector

Alias for field number 0

property match

Alias for field number 1

discovered_state(element: Dict[str, Any], final_job_state='ok') → DiscoveredResultState

property path

galaxy.model.store.discover.discovered_file_for_element(dataset, model_persistence_context: ModelPersistenceContext, parent_identifiers=None, collector=None) → Union[DiscoveredFile, DiscoveredDeferredFile, DiscoveredFileError]

galaxy.model.store.discover.discover_target_directory(dir_name, job_working_directory)

class galaxy.model.store.discover.JsonCollectedDatasetMatch(as_dict, collector: Optional[Any], filename, path=None, parent_identifiers=None)

Bases: object

__init__(as_dict, collector: Optional[Any], filename, path=None, parent_identifiers=None)

property designation

property element_identifiers

property raw_element_identifiers

property name

Return name or None if not defined by the discovery pattern.

property dbkey

property ext

property visible

property link_data

property tag_list

property object_id

property sources

property hashes

property created_from_basename

property extra_files

property effective_state

class galaxy.model.store.discover.RegexCollectedDatasetMatch(re_match, collector: Optional[Any], filename, path=None)

Bases: JsonCollectedDatasetMatch

__init__(re_match, collector: Optional[Any], filename, path=None)

class galaxy.model.store.discover.DiscoveredFileError(error_message, collector, match, path)

Bases: tuple

property error_message

Alias for field number 0

property collector

Alias for field number 1

property match

Alias for field number 2

property path

Alias for field number 3

discovered_state(element: Dict[str, Any], final_job_state='ok') → DiscoveredResultState

galaxy.model.store.load_objects module

galaxy.model.store.load_objects.main(argv=None)