def copy_file(orig_uuid):
"""Helper function that copies a file if given the original file's UUID
:param orig_uuid: UUID of file to copy.
:type orig_uuid: str.
:returns: UUID of newly copied file.
"""
orig_fsi = read(orig_uuid)
newfile_uuid = None
try:
newfile_uuid = create(orig_fsi.source, orig_fsi.sharename, orig_fsi.filetype, permanent=is_permanent(orig_uuid))
import_file(newfile_uuid, refresh=True)
except AttributeError:
pass
return newfile_uuid
def copy_file(orig_uuid):
"""Helper function that copies a file if given the original file's UUID
:param orig_uuid: UUID of file to copy.
:type orig_uuid: str.
:returns: UUID of newly copied file.
"""
orig_fsi = read(orig_uuid)
newfile_uuid = None
try:
newfile_uuid = create(
orig_fsi.source, orig_fsi.sharename, orig_fsi.filetype,
permanent=is_permanent(orig_uuid)
)
import_file(newfile_uuid, refresh=True)
except AttributeError:
pass
return newfile_uuid
def prepare(self, object):
data = super(NodeIndex, self).prepare(object)
annotations = AnnotatedNode.objects.filter(node=object)
uuid = str(object.study.id)
if object.assay is not None:
uuid += "_" + str(object.assay.id)
# create dynamic fields for each attribute
for annotation in annotations:
if annotation.attribute_subtype is None:
name = annotation.attribute_type
else:
name = annotation.attribute_subtype + "_" + annotation.attribute_type
if annotation.attribute_value_unit is None:
value = annotation.attribute_value
else:
value = annotation.attribute_value + " " + annotation.attribute_value_unit
# replace problematic characters in field names
name = string.replace(name, "/",
settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS)
name = string.replace(name, "(",
settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS)
name = string.replace(name, ")",
settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS)
name = string.replace(name, "#",
settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS)
name = string.replace(name, ",",
settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS)
name = string.replace(name, " ",
settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS)
name = string.replace(name, "'",
settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS)
key = name + "_" + uuid + "_s"
# a node might have multiple parents with different attribute values for a given attribute
# e.g. parentA Characteristic[cell type] = K562 and parentB Characteristic[cell type] = HeLa
# child nodes should inherit all attributes of their parents as a concatenation of the
# unique list
#
# old version (only one attribute kept):
# data[key] = value
if not key in data:
data[key] = set()
if value != "":
data[key].add(value)
else:
data[key].add("N/A")
# iterate over all keys in data and join sets into strings
for key, value in data.iteritems():
if type(value) is set:
data[key] = " + ".join(value)
# add type as dynamic field to get proper facet values
data[NodeIndex.TYPE_PREFIX + "_" + uuid + "_s"] = object.type
# add name as dynamic field to get proper facet values
data[NodeIndex.NAME_PREFIX + "_" + uuid + "_s"] = object.name
# add analysis_uuid as dynamic field to get proper facet values
if object.analysis_uuid is not None:
data[NodeIndex.ANALYSIS_UUID_PREFIX + "_" + uuid +
"_s"] = object.analysis_uuid
else:
data[NodeIndex.ANALYSIS_UUID_PREFIX + "_" + uuid + "_s"] = "N/A"
# add subanalysis as dynamic field to get proper facet values
if object.subanalysis is not None:
data[NodeIndex.SUBANALYSIS_PREFIX + "_" + uuid +
"_s"] = object.subanalysis
else:
data[NodeIndex.SUBANALYSIS_PREFIX + "_" + uuid + "_s"] = -1
# add workflow_output as dynamic field to get proper facet values
if object.workflow_output is not None:
data[NodeIndex.WORKFLOW_OUTPUT_PREFIX + "_" + uuid +
"_s"] = object.workflow_output
else:
data[NodeIndex.WORKFLOW_OUTPUT_PREFIX + "_" + uuid + "_s"] = "N/A"
# add file type as facet value
file_store_item = file_store_tasks.read(object.file_uuid)
if file_store_item:
data[NodeIndex.FILETYPE_PREFIX + "_" + uuid +
"_s"] = file_store_item.get_filetype()
else:
logger.warning("Unable to get file store item " +
str(object.file_uuid) + ". No file type available.")
data[NodeIndex.FILETYPE_PREFIX + "_" + uuid + "_s"] = ""
return data
def prepare(self, object):
data = super(NodeIndex, self).prepare(object)
annotations = AnnotatedNode.objects.filter( node=object )
uuid = str( object.study.id )
if object.assay is not None:
uuid += "_" + str( object.assay.id )
# create dynamic fields for each attribute
for annotation in annotations:
if annotation.attribute_subtype is None:
name = annotation.attribute_type
else:
name = annotation.attribute_subtype + "_" + annotation.attribute_type
if annotation.attribute_value_unit is None:
value = annotation.attribute_value
else:
value = annotation.attribute_value + " " + annotation.attribute_value_unit
# replace problematic characters in field names
name = string.replace( name, "/", settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS )
name = string.replace( name, "(", settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS )
name = string.replace( name, ")", settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS )
name = string.replace( name, "#", settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS )
name = string.replace( name, ",", settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS )
name = string.replace( name, " ", settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS )
name = string.replace( name, "'", settings.REFINERY_SOLR_SPACE_DYNAMIC_FIELDS )
key = name + "_" + uuid + "_s"
# a node might have multiple parents with different attribute values for a given attribute
# e.g. parentA Characteristic[cell type] = K562 and parentB Characteristic[cell type] = HeLa
# child nodes should inherit all attributes of their parents as a concatenation of the
# unique list
#
# old version (only one attribute kept):
# data[key] = value
if not key in data:
data[key] = set();
if value != "":
data[key].add( value )
else:
data[key].add( "N/A" )
# iterate over all keys in data and join sets into strings
for key, value in data.iteritems():
if type(value) is set:
data[key] = " + ".join(value)
# add type as dynamic field to get proper facet values
data[NodeIndex.TYPE_PREFIX + "_" + uuid + "_s"] = object.type
# add name as dynamic field to get proper facet values
data[NodeIndex.NAME_PREFIX + "_" + uuid + "_s"] = object.name
# add analysis_uuid as dynamic field to get proper facet values
if object.analysis_uuid is not None:
data[NodeIndex.ANALYSIS_UUID_PREFIX + "_" + uuid + "_s"] = object.analysis_uuid
else:
data[NodeIndex.ANALYSIS_UUID_PREFIX + "_" + uuid + "_s"] = "N/A"
# add subanalysis as dynamic field to get proper facet values
if object.subanalysis is not None:
data[NodeIndex.SUBANALYSIS_PREFIX + "_" + uuid + "_s"] = object.subanalysis
else:
data[NodeIndex.SUBANALYSIS_PREFIX + "_" + uuid + "_s"] = -1
# add workflow_output as dynamic field to get proper facet values
if object.workflow_output is not None:
data[NodeIndex.WORKFLOW_OUTPUT_PREFIX + "_" + uuid + "_s"] = object.workflow_output
else:
data[NodeIndex.WORKFLOW_OUTPUT_PREFIX + "_" + uuid + "_s"] = "N/A"
# add file type as facet value
file_store_item = file_store_tasks.read( object.file_uuid );
if file_store_item:
data[NodeIndex.FILETYPE_PREFIX + "_" + uuid + "_s"] = file_store_item.get_filetype()
else:
logger.warning( "Unable to get file store item " + str( object.file_uuid ) + ". No file type available." )
data[NodeIndex.FILETYPE_PREFIX + "_" + uuid + "_s"] = ""
return data
