def get_events_from_db(uuid):
events = []
for event_mdl in Event.objects.filter(file_uuid_id=uuid):
event = [
'event',
premisrw.PREMIS_META,
(
'event_identifier',
('event_identifier_type', 'UUID'),
('event_identifier_value', event_mdl.event_id),
),
('event_type', event_mdl.event_type),
('event_date_time', event_mdl.event_datetime.isoformat()),
# String detailing the program and algorithm used and the program's
# version (and any notable parameters passed).
('event_detail', escape(event_mdl.event_detail)),
(
'event_outcome_information',
('event_outcome', event_mdl.event_outcome),
('event_outcome_detail',
('event_outcome_detail_note',
escape(event_mdl.event_outcome_detail))),
),
]
for agent_mdl in event_mdl.agents.all():
event.append(
('linking_agent_identifier', ('linking_agent_identifier_type',
agent_mdl.identifiertype),
('linking_agent_identifier_value',
agent_mdl.identifiervalue)))
events.append(tuple(event))
return events
def tasks(request, uuid):
job = models.Job.objects.get(jobuuid=uuid)
objects = job.task_set.all().order_by('-exitcode', '-endtime',
'-starttime', '-createdtime')
if (len(objects) == 0):
return tasks_subjobs(request, uuid)
# Filenames can be any encoding - we want to be able to display
# unicode, while just displaying unicode replacement characters
# for any other encoding present.
for item in objects:
item.filename = escape(item.filename)
item.arguments = escape(item.arguments)
item.stdout = escape(item.stdout)
item.stderror = escape(item.stderror)
page = helpers.pager(objects, django_settings.TASKS_PER_PAGE,
request.GET.get('page', None))
objects = page.object_list
# figure out duration in seconds
for object in objects:
object.duration = helpers.task_duration_in_seconds(object)
return render(request, 'main/tasks.html', locals())
def createFileSec(path, file_group_identifier, base_path, base_path_name, parentBranch, structMapParent, sip_uuid):
print("createFileSec: ", path, parentBranch, structMapParent, file=sys.stderr)
doneFirstRun = True
pathSTR = path.__str__()
pathSTR = path.__str__()
if pathSTR == base_path + "objects/": #IF it's it's the SIP folder, it's OBJECTS
pathSTR = "objects"
#pathSTR = string.replace(path.__str__(), "/tmp/" + sys.argv[2] + "/" + sys.argv[3], "objects", 1)
#if pathSTR + "/" == basePath: #if it's the very first run through (recursive function)
if path == base_path: #if it's the very first run through (recursive function)
pathSTR = os.path.basename(os.path.dirname(base_path))
#structMapParent.set("DMDID", "SIP-description")
#currentBranch = newChild(parentBranch, "fileGrp")
#currentBranch.set("USE", "directory")
# structMap directory
div = newChild(structMapParent, ns.metsBNS + "div")
createFileSec(os.path.join(path, "objects/"), file_group_identifier, base_path, base_path_name, parentBranch, div, sip_uuid)
doneFirstRun = False
filename = os.path.basename(pathSTR)
structMapParent.set("TYPE", "directory")
structMapParent.set("LABEL", escape(filename))
if doneFirstRun:
for item in each_child(path, file_group_identifier, base_path, base_path_name, sip_uuid):
if isinstance(item, File):
pathSTR = item.currentlocation.replace('%transferDirectory%', "", 1)
ID = "file-" + item.uuid.__str__()
# structMap file
fptr = newChild(structMapParent, ns.metsBNS + "fptr")
FILEID = "file-" + item.uuid.__str__()
fptr.set("FILEID", escape(FILEID))
# If the file already exists in the fileSec, don't create
# a second entry.
fileI = parentBranch.find('./mets:file[@ID="{}"]'.format(ID), namespaces=ns.NSMAP)
if fileI is None:
fileI = etree.SubElement(parentBranch, ns.metsBNS + "file")
filename = ''.join(quoteattr(pathSTR).split("\"")[1:-1])
fileI.set("ID", escape(ID))
Flocat = newChild(fileI, ns.metsBNS + "FLocat")
Flocat.set(ns.xlinkBNS + "href", escape(pathSTR))
Flocat.set("LOCTYPE", "OTHER")
Flocat.set("OTHERLOCTYPE", "SYSTEM")
# used when adding amdSecs at a later time
admid = "digiprov-" + item.uuid
fileI.set("ADMID", admid)
else:
div = newChild(structMapParent, ns.metsBNS + "div")
createFileSec(os.path.join(path, item), file_group_identifier, base_path, base_path_name, parentBranch, div, sip_uuid)
def createDigiprovMD(fileUUID):
ret = []
#EVENTS
sql = "SELECT pk, fileUUID, eventIdentifierUUID, eventType, eventDateTime, eventDetail, eventOutcome, eventOutcomeDetailNote, linkingAgentIdentifier FROM Events WHERE fileUUID = '" + fileUUID + "';"
rows = databaseInterface.queryAllSQL(sql)
for row in rows:
digiprovMD = etree.Element("digiprovMD")
ret.append(digiprovMD) #newChild(amdSec, "digiprovMD")
#digiprovMD.set("ID", "digiprov-"+ os.path.basename(filename) + "-" + fileUUID)
global globalDigiprovMDCounter
globalDigiprovMDCounter += 1
digiprovMD.set("ID", "digiprovMD_"+ globalDigiprovMDCounter.__str__())
mdWrap = newChild(digiprovMD,"mdWrap")
mdWrap.set("MDTYPE", "PREMIS:EVENT")
xmlData = newChild(mdWrap,"xmlData")
event = etree.SubElement(xmlData, "event", nsmap={None: premisNS})
event.set(xsiBNS+"schemaLocation", premisNS + " http://www.loc.gov/standards/premis/v2/premis-v2-2.xsd")
event.set("version", "2.2")
eventIdentifier = etree.SubElement(event, "eventIdentifier")
etree.SubElement(eventIdentifier, "eventIdentifierType").text = "UUID"
etree.SubElement(eventIdentifier, "eventIdentifierValue").text = row[2]
etree.SubElement(event, "eventType").text = row[3]
etree.SubElement(event, "eventDateTime").text = row[4].__str__().replace(" ", "T")
etree.SubElement(event, "eventDetail").text = escape(row[5])
eventOutcomeInformation = etree.SubElement(event, "eventOutcomeInformation")
etree.SubElement(eventOutcomeInformation, "eventOutcome").text = row[6]
eventOutcomeDetail = etree.SubElement(eventOutcomeInformation, "eventOutcomeDetail")
etree.SubElement(eventOutcomeDetail, "eventOutcomeDetailNote").text = escape(row[7])
if row[8]:
linkingAgentIdentifier = etree.SubElement(event, "linkingAgentIdentifier")
etree.SubElement(linkingAgentIdentifier, "linkingAgentIdentifierType").text = "Archivematica user pk"
etree.SubElement(linkingAgentIdentifier, "linkingAgentIdentifierValue").text = row[8].__str__()
#linkingAgentIdentifier
sql = """SELECT agentIdentifierType, agentIdentifierValue, agentName, agentType FROM Agents;"""
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
while row != None:
linkingAgentIdentifier = etree.SubElement(event, "linkingAgentIdentifier")
etree.SubElement(linkingAgentIdentifier, "linkingAgentIdentifierType").text = row[0]
etree.SubElement(linkingAgentIdentifier, "linkingAgentIdentifierValue").text = row[1]
row = c.fetchone()
sqlLock.release()
return ret
def createEvent(event_record):
""" Returns a PREMIS Event. """
event = etree.Element(ns.premisBNS + "event", nsmap={'premis': ns.premisNS})
event.set(ns.xsiBNS + "schemaLocation", ns.premisNS + " http://www.loc.gov/standards/premis/v2/premis-v2-2.xsd")
event.set("version", "2.2")
eventIdentifier = etree.SubElement(event, ns.premisBNS + "eventIdentifier")
etree.SubElement(eventIdentifier, ns.premisBNS + "eventIdentifierType").text = "UUID"
etree.SubElement(eventIdentifier, ns.premisBNS + "eventIdentifierValue").text = event_record.event_id
etree.SubElement(event, ns.premisBNS + "eventType").text = event_record.event_type
etree.SubElement(event, ns.premisBNS + "eventDateTime").text = event_record.event_datetime.isoformat()
etree.SubElement(event, ns.premisBNS + "eventDetail").text = escape(event_record.event_detail)
eventOutcomeInformation = etree.SubElement(event, ns.premisBNS + "eventOutcomeInformation")
etree.SubElement(eventOutcomeInformation, ns.premisBNS + "eventOutcome").text = event_record.event_outcome
eventOutcomeDetail = etree.SubElement(eventOutcomeInformation, ns.premisBNS + "eventOutcomeDetail")
etree.SubElement(eventOutcomeDetail, ns.premisBNS + "eventOutcomeDetailNote").text = escape(event_record.event_outcome_detail)
# linkingAgentIdentifier
for agent in event_record.agents.all():
linkingAgentIdentifier = etree.SubElement(event, ns.premisBNS + "linkingAgentIdentifier")
etree.SubElement(linkingAgentIdentifier, ns.premisBNS + "linkingAgentIdentifierType").text = agent.identifiertype
etree.SubElement(linkingAgentIdentifier, ns.premisBNS + "linkingAgentIdentifierValue").text = agent.identifiervalue
return event
def dir_obj_to_premis(dir_obj):
"""
Converts an Directory model object to a PREMIS object via metsrw.
Returns:
lxml.etree._Element
"""
original_name = escape(dir_obj.originallocation)
object_identifiers = get_premis_object_identifiers(
dir_obj.uuid, dir_obj.identifiers.all())
premis_data = (("object", IE_PREMIS_META) + object_identifiers +
(("original_name", original_name), ))
return metsrw.plugins.premisrw.data_to_premis(
premis_data, premis_version=IE_PREMIS_META["version"])
def file_obj_to_premis(file_obj):
"""
Converts an File model object to a PREMIS event object via metsrw.
Returns:
lxml.etree._Element
"""
premis_digest_algorithm = convert_to_premis_hash_function(
file_obj.checksumtype)
format_data = get_premis_format_data(file_obj.fileid_set.all())
original_name = escape(file_obj.originallocation)
object_identifiers = get_premis_object_identifiers(
file_obj.uuid, file_obj.identifiers.all())
object_characteristics_extensions = get_premis_object_characteristics_extension(
file_obj.characterization_documents)
relationship_data = get_premis_relationship_data(
file_obj.related_is_source_of, file_obj.related_has_source)
object_characteristics = (
"object_characteristics",
("composition_level", "0"),
(
"fixity",
("message_digest_algorithm", premis_digest_algorithm),
("message_digest", file_obj.checksum),
),
("size", str(file_obj.size)),
format_data,
(
"creating_application",
(
"date_created_by_application",
file_obj.modificationtime.strftime("%Y-%m-%d"),
),
),
)
if object_characteristics_extensions:
object_characteristics += object_characteristics_extensions
premis_data = (("object", FILE_PREMIS_META) + object_identifiers +
(object_characteristics,
("original_name", original_name)) + relationship_data)
return metsrw.plugins.premisrw.data_to_premis(
premis_data, premis_version=FILE_PREMIS_META["version"])
def ingest_normalization_report(request, uuid, current_page=None):
jobs = models.Job.objects.filter(sipuuid=uuid, subjobof='')
sipname = utils.get_directory_name_from_job(jobs)
objects = getNormalizationReportQuery(sipUUID=uuid)
for o in objects:
o['location'] = archivematicaFunctions.escape(o['location'])
results_per_page = 10
if current_page == None:
current_page = 1
page = helpers.pager(objects, results_per_page, current_page)
hit_count = len(objects)
return render(request, 'ingest/normalization_report.html', locals())
def createDigiprovMD(fileUUID):
ret = []
# EVENTS
events = Event.objects.filter(file_uuid_id=fileUUID)
for event_record in events:
digiprovMD = etree.Element(ns.metsBNS + "digiprovMD")
ret.append(digiprovMD) #newChild(amdSec, "digiprovMD")
#digiprovMD.set("ID", "digiprov-"+ os.path.basename(filename) + "-" + fileUUID)
global globalDigiprovMDCounter
globalDigiprovMDCounter += 1
digiprovMD.set("ID", "digiprovMD_"+ globalDigiprovMDCounter.__str__())
mdWrap = etree.SubElement(digiprovMD, ns.metsBNS + "mdWrap")
mdWrap.set("MDTYPE", "PREMIS:EVENT")
xmlData = etree.SubElement(mdWrap, ns.metsBNS + "xmlData")
event = etree.SubElement(xmlData, ns.premisBNS + "event", nsmap={'premis': ns.premisNS})
event.set(ns.xsiBNS+"schemaLocation", ns.premisNS + " http://www.loc.gov/standards/premis/v2/premis-v2-2.xsd")
event.set("version", "2.2")
eventIdentifier = etree.SubElement(event, ns.premisBNS + "eventIdentifier")
etree.SubElement(eventIdentifier, ns.premisBNS + "eventIdentifierType").text = "UUID"
etree.SubElement(eventIdentifier, ns.premisBNS + "eventIdentifierValue").text = event_record.event_id
etree.SubElement(event, ns.premisBNS + "eventType").text = event_record.event_type
etree.SubElement(event, ns.premisBNS + "eventDateTime").text = event_record.event_datetime.isoformat()
etree.SubElement(event, ns.premisBNS + "eventDetail").text = escape(event_record.event_detail)
eventOutcomeInformation = etree.SubElement(event, ns.premisBNS + "eventOutcomeInformation")
etree.SubElement(eventOutcomeInformation, ns.premisBNS + "eventOutcome").text = event_record.event_outcome
eventOutcomeDetail = etree.SubElement(eventOutcomeInformation, ns.premisBNS + "eventOutcomeDetail")
etree.SubElement(eventOutcomeDetail, ns.premisBNS + "eventOutcomeDetailNote").text = escape(event_record.event_outcome_detail)
if event_record.linking_agent:
linkingAgentIdentifier = etree.SubElement(event, ns.premisBNS + "linkingAgentIdentifier")
etree.SubElement(linkingAgentIdentifier, ns.premisBNS + "linkingAgentIdentifierType").text = "Archivematica user pk"
etree.SubElement(linkingAgentIdentifier, ns.premisBNS + "linkingAgentIdentifierValue").text = str(event_record.linking_agent)
# linkingAgentIdentifier
for agent in Agent.objects.all():
linkingAgentIdentifier = etree.SubElement(event, ns.premisBNS + "linkingAgentIdentifier")
etree.SubElement(linkingAgentIdentifier, ns.premisBNS + "linkingAgentIdentifierType").text = agent.identifiertype
etree.SubElement(linkingAgentIdentifier, ns.premisBNS + "linkingAgentIdentifierValue").text = agent.identifiervalue
return ret
def create_premis_object(fileUUID):
"""
Create a PREMIS:OBJECT for fileUUID.
Access the models for File, FileID, FPCommandOutput, Derivation
:param str fileUUID: UUID of the File to create an object for
:return: premis:object Element, suitable for inserting into mets:xmlData
"""
f = File.objects.get(uuid=fileUUID)
# PREMIS:OBJECT
object_elem = etree.Element(ns.premisBNS + "object", nsmap={'premis': ns.premisNS})
object_elem.set(ns.xsiBNS+"type", "premis:file")
object_elem.set(ns.xsiBNS+"schemaLocation", ns.premisNS + " http://www.loc.gov/standards/premis/v2/premis-v2-2.xsd")
object_elem.set("version", "2.2")
objectIdentifier = etree.SubElement(object_elem, ns.premisBNS + "objectIdentifier")
etree.SubElement(objectIdentifier, ns.premisBNS + "objectIdentifierType").text = "UUID"
etree.SubElement(objectIdentifier, ns.premisBNS + "objectIdentifierValue").text = fileUUID
objectCharacteristics = etree.SubElement(object_elem, ns.premisBNS + "objectCharacteristics")
etree.SubElement(objectCharacteristics, ns.premisBNS + "compositionLevel").text = "0"
fixity = etree.SubElement(objectCharacteristics, ns.premisBNS + "fixity")
etree.SubElement(fixity, ns.premisBNS + "messageDigestAlgorithm").text = f.checksumtype
etree.SubElement(fixity, ns.premisBNS + "messageDigest").text = f.checksum
etree.SubElement(objectCharacteristics, ns.premisBNS + "size").text = str(f.size)
for elem in create_premis_object_formats(fileUUID):
objectCharacteristics.append(elem)
for elem in create_premis_object_characteristics_extensions(fileUUID):
objectCharacteristics.append(elem)
etree.SubElement(object_elem, ns.premisBNS + "originalName").text = escape(f.originallocation)
for elem in create_premis_object_derivations(fileUUID):
object_elem.append(elem)
return object_elem
def ingest_normalization_report(request, uuid, current_page=None):
jobs = models.Job.objects.filter(sipuuid=uuid, subjobof='')
sipname = jobs.get_directory_name()
objects = getNormalizationReportQuery(sipUUID=uuid)
for o in objects:
o['location'] = archivematicaFunctions.escape(o['location'])
(o['preservation_derivative_validation_attempted'],
o['preservation_derivative_validation_failed'],
o['access_derivative_validation_attempted'],
o['access_derivative_validation_failed']
) = derivative_validation_report(o)
results_per_page = 10
if current_page is None:
current_page = 1
page = helpers.pager(objects, results_per_page, current_page)
hit_count = len(objects)
return render(request, 'ingest/normalization_report.html', locals())
def ingest_normalization_report(request, uuid, current_page=None):
jobs = models.Job.objects.filter(sipuuid=uuid)
sipname = jobs.get_directory_name()
objects = getNormalizationReportQuery(sipUUID=uuid)
for o in objects:
o["location"] = escape(o["location"])
(
o["preservation_derivative_validation_attempted"],
o["preservation_derivative_validation_failed"],
o["access_derivative_validation_attempted"],
o["access_derivative_validation_failed"],
) = derivative_validation_report(o)
results_per_page = 10
if current_page is None:
current_page = 1
page = helpers.pager(objects, results_per_page, current_page)
hit_count = len(objects)
return render(request, "ingest/normalization_report.html", locals())
def createTechMD(fileUUID):
ret = etree.Element("techMD")
techMD = ret #newChild(amdSec, "digiprovMD")
#digiprovMD.set("ID", "digiprov-"+ os.path.basename(filename) + "-" + fileUUID)
global globalTechMDCounter
globalTechMDCounter += 1
techMD.set("ID", "techMD_" + globalTechMDCounter.__str__())
mdWrap = newChild(techMD, "mdWrap")
mdWrap.set("MDTYPE", "PREMIS:OBJECT")
xmlData = newChild(mdWrap, "xmlData")
#premis = etree.SubElement( xmlData, "premis", nsmap={None: premisNS}, \
# attrib = { "{" + xsiNS + "}schemaLocation" : "info:lc/xmlns/premis-v2 http://www.loc.gov/standards/premis/premis.xsd" })
#premis.set("version", "2.0")
#premis = etree.SubElement( xmlData, "premis", attrib = {xsiBNS+"type": "premis:file"})
sql = "SELECT fileSize, checksum FROM Files WHERE fileUUID = '%s';" % (
fileUUID)
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
while row != None:
fileSize = row[0].__str__()
checksum = row[1].__str__()
row = c.fetchone()
sqlLock.release()
#OBJECT
object = etree.SubElement(xmlData, "object", nsmap={None: premisNS})
object.set(xsiBNS + "type", "file")
object.set(
xsiBNS + "schemaLocation",
premisNS + " http://www.loc.gov/standards/premis/v2/premis-v2-2.xsd")
object.set("version", "2.2")
objectIdentifier = etree.SubElement(object, "objectIdentifier")
etree.SubElement(objectIdentifier, "objectIdentifierType").text = "UUID"
etree.SubElement(objectIdentifier, "objectIdentifierValue").text = fileUUID
#etree.SubElement(object, "objectCategory").text = "file"
objectCharacteristics = etree.SubElement(object, "objectCharacteristics")
etree.SubElement(objectCharacteristics, "compositionLevel").text = "0"
fixity = etree.SubElement(objectCharacteristics, "fixity")
etree.SubElement(fixity, "messageDigestAlgorithm").text = "sha256"
etree.SubElement(fixity, "messageDigest").text = checksum
etree.SubElement(objectCharacteristics, "size").text = fileSize
sql = "SELECT formatName, formatVersion, formatRegistryName, formatRegistryKey FROM FilesIDs WHERE fileUUID = '%s';" % (
fileUUID)
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
if not row:
format = etree.SubElement(objectCharacteristics, "format")
formatDesignation = etree.SubElement(format, "formatDesignation")
etree.SubElement(formatDesignation, "formatName").text = "Unknown"
while row != None:
#print row
format = etree.SubElement(objectCharacteristics, "format")
#fileUUID = row[0]
formatDesignation = etree.SubElement(format, "formatDesignation")
etree.SubElement(formatDesignation, "formatName").text = row[0]
etree.SubElement(formatDesignation, "formatVersion").text = row[1]
formatRegistry = etree.SubElement(format, "formatRegistry")
etree.SubElement(formatRegistry, "formatRegistryName").text = row[2]
etree.SubElement(formatRegistry, "formatRegistryKey").text = row[3]
row = c.fetchone()
sqlLock.release()
objectCharacteristicsExtension = etree.SubElement(
objectCharacteristics, "objectCharacteristicsExtension")
sql = "SELECT FilesFits.FITSxml FROM FilesFits WHERE fileUUID = '" + fileUUID + "';"
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
#if not row:
# print >>sys.stderr, "Error no fits.", fileUUID
parser = etree.XMLParser(remove_blank_text=True)
while row != None:
#fits = etree.fromstring(row[0])
fits = etree.XML(row[0], parser)
objectCharacteristicsExtension.append(fits)
row = c.fetchone()
sqlLock.release()
sql = "SELECT Files.originalLocation FROM Files WHERE Files.fileUUID = '" + fileUUID + "';"
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
if not row:
print >> sys.stderr, "Error no fits."
while row != None:
etree.SubElement(object, "originalName").text = escape(row[0])
row = c.fetchone()
sqlLock.release()
#Derivations
sql = "SELECT sourceFileUUID, derivedFileUUID, relatedEventUUID FROM Derivations WHERE sourceFileUUID = '" + fileUUID + "';"
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
while row != None:
relationship = etree.SubElement(object, "relationship")
etree.SubElement(relationship, "relationshipType").text = "derivation"
etree.SubElement(relationship,
"relationshipSubType").text = "is source of"
relatedObjectIdentification = etree.SubElement(
relationship, "relatedObjectIdentification")
etree.SubElement(relatedObjectIdentification,
"relatedObjectIdentifierType").text = "UUID"
etree.SubElement(relatedObjectIdentification,
"relatedObjectIdentifierValue").text = row[1]
relatedEventIdentification = etree.SubElement(
relationship, "relatedEventIdentification")
etree.SubElement(relatedEventIdentification,
"relatedEventIdentifierType").text = "UUID"
etree.SubElement(relatedEventIdentification,
"relatedEventIdentifierValue").text = row[2]
row = c.fetchone()
sqlLock.release()
sql = "SELECT sourceFileUUID, derivedFileUUID, relatedEventUUID FROM Derivations WHERE derivedFileUUID = '" + fileUUID + "';"
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
while row != None:
relationship = etree.SubElement(object, "relationship")
etree.SubElement(relationship, "relationshipType").text = "derivation"
etree.SubElement(relationship,
"relationshipSubType").text = "has source"
relatedObjectIdentification = etree.SubElement(
relationship, "relatedObjectIdentification")
etree.SubElement(relatedObjectIdentification,
"relatedObjectIdentifierType").text = "UUID"
etree.SubElement(relatedObjectIdentification,
"relatedObjectIdentifierValue").text = row[0]
relatedEventIdentification = etree.SubElement(
relationship, "relatedEventIdentification")
etree.SubElement(relatedEventIdentification,
"relatedEventIdentifierType").text = "UUID"
etree.SubElement(relatedEventIdentification,
"relatedEventIdentifierValue").text = row[2]
row = c.fetchone()
sqlLock.release()
return ret
def createTechMD(fileUUID):
ret = etree.Element(ns.metsBNS + "techMD")
techMD = ret #newChild(amdSec, "digiprovMD")
#digiprovMD.set("ID", "digiprov-"+ os.path.basename(filename) + "-" + fileUUID)
global globalTechMDCounter
globalTechMDCounter += 1
techMD.set("ID", "techMD_"+ globalTechMDCounter.__str__())
mdWrap = etree.SubElement(techMD, ns.metsBNS + "mdWrap")
mdWrap.set("MDTYPE", "PREMIS:OBJECT")
xmlData = etree.SubElement(mdWrap, ns.metsBNS + "xmlData")
#premis = etree.SubElement( xmlData, "premis", nsmap={None: ns.premisNS}, \
# attrib = { "{" + ns.xsiNS + "}schemaLocation" : "info:lc/xmlns/premis-v2 http://www.loc.gov/standards/premis/premis.xsd" })
#premis.set("version", "2.0")
#premis = etree.SubElement( xmlData, "premis", attrib = {ns.xsiBNS+"type": "premis:file"})
f = File.objects.get(uuid=fileUUID)
fileSize = str(f.size)
checksum = f.checksum
#OBJECT
object = etree.SubElement(xmlData, ns.premisBNS + "object", nsmap={'premis': ns.premisNS})
object.set(ns.xsiBNS+"type", "premis:file")
object.set(ns.xsiBNS+"schemaLocation", ns.premisNS + " http://www.loc.gov/standards/premis/v2/premis-v2-2.xsd")
object.set("version", "2.2")
objectIdentifier = etree.SubElement(object, ns.premisBNS + "objectIdentifier")
etree.SubElement(objectIdentifier, ns.premisBNS + "objectIdentifierType").text = "UUID"
etree.SubElement(objectIdentifier, ns.premisBNS + "objectIdentifierValue").text = fileUUID
#etree.SubElement(object, "objectCategory").text = "file"
objectCharacteristics = etree.SubElement(object, ns.premisBNS + "objectCharacteristics")
etree.SubElement(objectCharacteristics, ns.premisBNS + "compositionLevel").text = "0"
fixity = etree.SubElement(objectCharacteristics, ns.premisBNS + "fixity")
etree.SubElement(fixity, ns.premisBNS + "messageDigestAlgorithm").text = "sha256"
etree.SubElement(fixity, ns.premisBNS + "messageDigest").text = checksum
etree.SubElement(objectCharacteristics, ns.premisBNS + "size").text = fileSize
files = FileID.objects.filter(file_id=fileUUID)
if not files.exists():
format = etree.SubElement(objectCharacteristics, ns.premisBNS + "format")
formatDesignation = etree.SubElement(format, ns.premisBNS + "formatDesignation")
etree.SubElement(formatDesignation, ns.premisBNS + "formatName").text = "Unknown"
for row in files.values_list('format_name', 'format_version', 'format_registry_name', 'format_registry_key'):
#print row
format = etree.SubElement(objectCharacteristics, ns.premisBNS + "format")
formatDesignation = etree.SubElement(format, ns.premisBNS + "formatDesignation")
etree.SubElement(formatDesignation, ns.premisBNS + "formatName").text = row[0]
etree.SubElement(formatDesignation, ns.premisBNS + "formatVersion").text = row[1]
formatRegistry = etree.SubElement(format, ns.premisBNS + "formatRegistry")
etree.SubElement(formatRegistry, ns.premisBNS + "formatRegistryName").text = row[2]
etree.SubElement(formatRegistry, ns.premisBNS + "formatRegistryKey").text = row[3]
objectCharacteristicsExtension = etree.SubElement(objectCharacteristics, ns.premisBNS + "objectCharacteristicsExtension")
parser = etree.XMLParser(remove_blank_text=True)
documents = FPCommandOutput.objects.filter(file_id=fileUUID, rule__purpose__in=['characterization', 'default_characterization']).values_list('content')
for document, in documents:
# This needs to be converted into an str because lxml doesn't accept
# XML documents in unicode strings if the document contains an
# encoding declaration.
output = etree.XML(document.encode("utf-8"), parser)
objectCharacteristicsExtension.append(output)
try:
f = File.objects.get(uuid=fileUUID)
except File.DoesNotExist:
print >>sys.stderr, "Error: no location found."
else:
etree.SubElement(object, ns.premisBNS + "originalName").text = escape(f.originallocation)
# Derivations
derivations = Derivation.objects.filter(source_file_id=fileUUID, event__isnull=False)
for derivation in derivations:
relationship = etree.SubElement(object, ns.premisBNS + "relationship")
etree.SubElement(relationship, ns.premisBNS + "relationshipType").text = "derivation"
etree.SubElement(relationship, ns.premisBNS + "relationshipSubType").text = "is source of"
relatedObjectIdentification = etree.SubElement(relationship, ns.premisBNS + "relatedObjectIdentification")
etree.SubElement(relatedObjectIdentification, ns.premisBNS + "relatedObjectIdentifierType").text = "UUID"
etree.SubElement(relatedObjectIdentification, ns.premisBNS + "relatedObjectIdentifierValue").text = derivation.derived_file_id
relatedEventIdentification = etree.SubElement(relationship, ns.premisBNS + "relatedEventIdentification")
etree.SubElement(relatedEventIdentification, ns.premisBNS + "relatedEventIdentifierType").text = "UUID"
etree.SubElement(relatedEventIdentification, ns.premisBNS + "relatedEventIdentifierValue").text = derivation.event_id
derivations = Derivation.objects.filter(derived_file_id=fileUUID, event__isnull=False)
for derivation in derivations:
relationship = etree.SubElement(object, ns.premisBNS + "relationship")
etree.SubElement(relationship, ns.premisBNS + "relationshipType").text = "derivation"
etree.SubElement(relationship, ns.premisBNS + "relationshipSubType").text = "has source"
relatedObjectIdentification = etree.SubElement(relationship, ns.premisBNS + "relatedObjectIdentification")
etree.SubElement(relatedObjectIdentification, ns.premisBNS + "relatedObjectIdentifierType").text = "UUID"
etree.SubElement(relatedObjectIdentification, ns.premisBNS + "relatedObjectIdentifierValue").text = derivation.source_file_id
relatedEventIdentification = etree.SubElement(relationship, ns.premisBNS + "relatedEventIdentification")
etree.SubElement(relatedEventIdentification, ns.premisBNS + "relatedEventIdentifierType").text = "UUID"
etree.SubElement(relatedEventIdentification, ns.premisBNS + "relatedEventIdentifierValue").text = derivation.event_id
return ret
def createTechMD(fileUUID):
ret = etree.Element("techMD")
techMD = ret #newChild(amdSec, "digiprovMD")
#digiprovMD.set("ID", "digiprov-"+ os.path.basename(filename) + "-" + fileUUID)
global globalTechMDCounter
globalTechMDCounter += 1
techMD.set("ID", "techMD_"+ globalTechMDCounter.__str__())
mdWrap = newChild(techMD,"mdWrap")
mdWrap.set("MDTYPE", "PREMIS:OBJECT")
xmlData = newChild(mdWrap, "xmlData")
#premis = etree.SubElement( xmlData, "premis", nsmap={None: premisNS}, \
# attrib = { "{" + xsiNS + "}schemaLocation" : "info:lc/xmlns/premis-v2 http://www.loc.gov/standards/premis/premis.xsd" })
#premis.set("version", "2.0")
#premis = etree.SubElement( xmlData, "premis", attrib = {xsiBNS+"type": "premis:file"})
sql = "SELECT fileSize, checksum FROM Files WHERE fileUUID = '%s';" % (fileUUID)
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
while row != None:
fileSize = row[0].__str__()
checksum = row[1].__str__()
row = c.fetchone()
sqlLock.release()
#OBJECT
object = etree.SubElement(xmlData, "object", nsmap={None: premisNS})
object.set( xsiBNS+"type", "file")
object.set(xsiBNS+"schemaLocation", premisNS + " http://www.loc.gov/standards/premis/v2/premis-v2-2.xsd")
object.set("version", "2.2")
objectIdentifier = etree.SubElement(object, "objectIdentifier")
etree.SubElement(objectIdentifier, "objectIdentifierType").text = "UUID"
etree.SubElement(objectIdentifier, "objectIdentifierValue").text = fileUUID
#etree.SubElement(object, "objectCategory").text = "file"
objectCharacteristics = etree.SubElement(object, "objectCharacteristics")
etree.SubElement(objectCharacteristics, "compositionLevel").text = "0"
fixity = etree.SubElement(objectCharacteristics, "fixity")
etree.SubElement(fixity, "messageDigestAlgorithm").text = "sha256"
etree.SubElement(fixity, "messageDigest").text = checksum
etree.SubElement(objectCharacteristics, "size").text = fileSize
sql = "SELECT formatName, formatVersion, formatRegistryName, formatRegistryKey FROM FilesIDs WHERE fileUUID = '%s';" % (fileUUID)
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
if not row:
format = etree.SubElement(objectCharacteristics, "format")
formatDesignation = etree.SubElement(format, "formatDesignation")
etree.SubElement(formatDesignation, "formatName").text = "Unknown"
while row != None:
#print row
format = etree.SubElement(objectCharacteristics, "format")
#fileUUID = row[0]
formatDesignation = etree.SubElement(format, "formatDesignation")
etree.SubElement(formatDesignation, "formatName").text = row[0]
etree.SubElement(formatDesignation, "formatVersion").text = row[1]
formatRegistry = etree.SubElement(format, "formatRegistry")
etree.SubElement(formatRegistry, "formatRegistryName").text = row[2]
etree.SubElement(formatRegistry, "formatRegistryKey").text = row[3]
row = c.fetchone()
sqlLock.release()
objectCharacteristicsExtension = etree.SubElement(objectCharacteristics, "objectCharacteristicsExtension")
sql = "SELECT FilesFits.FITSxml FROM FilesFits WHERE fileUUID = '" + fileUUID + "';"
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
#if not row:
# print >>sys.stderr, "Error no fits.", fileUUID
parser = etree.XMLParser(remove_blank_text=True)
while row != None:
#fits = etree.fromstring(row[0])
fits = etree.XML(row[0], parser)
objectCharacteristicsExtension.append(fits)
row = c.fetchone()
sqlLock.release()
sql = "SELECT Files.originalLocation FROM Files WHERE Files.fileUUID = '" + fileUUID + "';"
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
if not row:
print >>sys.stderr, "Error no fits."
while row != None:
etree.SubElement(object, "originalName").text = escape(row[0])
row = c.fetchone()
sqlLock.release()
#Derivations
sql = "SELECT sourceFileUUID, derivedFileUUID, relatedEventUUID FROM Derivations WHERE sourceFileUUID = '" + fileUUID + "';"
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
while row != None:
relationship = etree.SubElement(object, "relationship")
etree.SubElement(relationship, "relationshipType").text = "derivation"
etree.SubElement(relationship, "relationshipSubType").text = "is source of"
relatedObjectIdentification = etree.SubElement(relationship, "relatedObjectIdentification")
etree.SubElement(relatedObjectIdentification, "relatedObjectIdentifierType").text = "UUID"
etree.SubElement(relatedObjectIdentification, "relatedObjectIdentifierValue").text = row[1]
relatedEventIdentification = etree.SubElement(relationship, "relatedEventIdentification")
etree.SubElement(relatedEventIdentification, "relatedEventIdentifierType").text = "UUID"
etree.SubElement(relatedEventIdentification, "relatedEventIdentifierValue").text = row[2]
row = c.fetchone()
sqlLock.release()
sql = "SELECT sourceFileUUID, derivedFileUUID, relatedEventUUID FROM Derivations WHERE derivedFileUUID = '" + fileUUID + "';"
c, sqlLock = databaseInterface.querySQL(sql)
row = c.fetchone()
while row != None:
relationship = etree.SubElement(object, "relationship")
etree.SubElement(relationship, "relationshipType").text = "derivation"
etree.SubElement(relationship, "relationshipSubType").text = "has source"
relatedObjectIdentification = etree.SubElement(relationship, "relatedObjectIdentification")
etree.SubElement(relatedObjectIdentification, "relatedObjectIdentifierType").text = "UUID"
etree.SubElement(relatedObjectIdentification, "relatedObjectIdentifierValue").text = row[0]
relatedEventIdentification = etree.SubElement(relationship, "relatedEventIdentification")
etree.SubElement(relatedEventIdentification, "relatedEventIdentifierType").text = "UUID"
etree.SubElement(relatedEventIdentification, "relatedEventIdentifierValue").text = row[2]
row = c.fetchone()
sqlLock.release()
return ret
