def purgeConstituents(self): # purge children for page in self.pages_from_rels: page = self.pages_from_rels[page] print "purging:",page.label fedora_handle.purge_object(page) return True
def purgeReaduxVirtualObjects(self):
sparql_response = fedora_handle.risearch.sparql_query('select $virtobj where {{ $virtobj <http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/isVirtualFor> <info:fedora/%s> . }}' % (self.pid))
for obj in sparql_response:
print "Purging virtual object: %s" % obj['virtobj']
fedora_handle.purge_object( obj['virtobj'].split("info:fedora/")[-1] )
return True
def ingest(self, book_obj, page_num):
# set book_obj to self
self.book_obj = book_obj
# using parent book, get datastreams from objMeta
page_dict = self.book_obj.pages_from_objMeta[page_num]
# new pid
npid = "wayne:%s_Page_%s" % (self.book_obj.pid.split(":")[1], page_num)
# creating new self
self.ohandle = fedora_handle.get_object(npid)
if self.ohandle.exists:
fedora_handle.purge_object(self.ohandle)
self.ohandle = fedora_handle.get_object(npid, create=True)
self.ohandle.save()
# label
self.ohandle.label = "%s - Page %s" % (self.book_obj.ohandle.label, page_num)
# write POLICY datastream
# NOTE: 'E' management type required, not 'R'
print "Using policy:",self.book_obj.objMeta['policy']
policy_suffix = self.book_obj.objMeta['policy'].split("info:fedora/")[1]
policy_handle = eulfedora.models.DatastreamObject(self.ohandle, "POLICY", "POLICY", mimetype="text/xml", control_group="E")
policy_handle.ds_location = "http://localhost/fedora/objects/%s/datastreams/POLICY_XML/content" % (policy_suffix)
policy_handle.label = "POLICY"
policy_handle.save()
# generic hash of target ids
target_ids = {
'IMAGE':'IMAGE_%d' % page_num,
'HTML':'HTML_%d' % page_num,
'ALTOXML':'ALTOXML_%d' % page_num
}
# for each file type in pages dict, pass page obj and process
for ds in page_dict:
if ds['ds_id'].startswith('IMAGE'):
self.processImage(ds)
if ds['ds_id'].startswith('HTML'):
self.processHTML(ds)
if ds['ds_id'].startswith('ALTOXML'):
self.processALTOXML(ds)
# write RDF relationships
self.ohandle.add_relationship("info:fedora/fedora-system:def/relations-external#hasContentModel", "info:fedora/CM:WSUebook_Page")
self.ohandle.add_relationship("info:fedora/fedora-system:def/relations-external#isConstituentOf", "info:fedora/%s" % self.book_obj.ohandle.pid)
self.ohandle.add_relationship("http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/pageOrder", page_num)
# save page object
return self.ohandle.save()
def ingestMissingPage(self, book_obj, page_num, from_bag=True):
# set book_obj to self
self.book_obj = book_obj
# new pid
npid = "wayne:%s_Page_%s" % (self.book_obj.pid.split(":")[1], page_num)
# creating new self
self.ohandle = fedora_handle.get_object(npid)
if self.ohandle.exists:
fedora_handle.purge_object(self.ohandle)
self.ohandle = fedora_handle.get_object(npid, create=True)
self.ohandle.save()
# label
self.ohandle.label = "%s - Page %s" % (self.book_obj.ohandle.label, page_num)
# write POLICY datastream
# NOTE: 'E' management type required, not 'R'
print "Using policy:",self.book_obj.objMeta['policy']
policy_suffix = self.book_obj.objMeta['policy'].split("info:fedora/")[1]
policy_handle = eulfedora.models.DatastreamObject(self.ohandle, "POLICY", "POLICY", mimetype="text/xml", control_group="E")
policy_handle.ds_location = "http://localhost/fedora/objects/%s/datastreams/POLICY_XML/content" % (policy_suffix)
policy_handle.label = "POLICY"
policy_handle.save()
print "Processing HTML placeholder"
generic_handle = eulfedora.models.FileDatastreamObject(self.ohandle, "HTML", "HTML", mimetype="text/html", control_group='M')
generic_handle.label = "HTML"
generic_handle.content = "<p>[Page %s Intentionally Left Blank]</p>" % (page_num)
generic_handle.save()
print "Processing IMAGE placeholder"
# passes 'from_bag' param
self.processImage(None, exists=False, page_num=page_num, from_bag=from_bag)
# write RDF relationships
self.ohandle.add_relationship("info:fedora/fedora-system:def/relations-external#hasContentModel", "info:fedora/CM:WSUebook_Page")
self.ohandle.add_relationship("info:fedora/fedora-system:def/relations-external#isConstituentOf", "info:fedora/%s" % self.book_obj.ohandle.pid)
self.ohandle.add_relationship("http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/pageOrder", page_num)
self.ohandle.add_relationship("http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/pageExists", False)
# create IMAGE, HTML, ALTOXML for missing page
print "Processing ALTOXML placeholder"
generic_handle = eulfedora.models.FileDatastreamObject(self.ohandle, 'ALTOXML', 'ALTOXML', mimetype="text/xml", control_group='M')
generic_handle.label = 'ALTOXML'
generic_handle.content = '<?xml version="1.0" encoding="UTF-8" standalone="yes"?><alto xmlns="http://www.loc.gov/standards/alto/ns-v2#" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.loc.gov/standards/alto/ns-v2# http://www.loc.gov/standards/alto/alto-v2.0.xsd"> <Description> <MeasurementUnit>pixel</MeasurementUnit> <OCRProcessing ID="IdOcr"> <ocrProcessingStep> <processingSoftware> <softwareCreator>ABBYY</softwareCreator> <softwareName>ABBYY Recognition Server</softwareName> <softwareVersion>4.0</softwareVersion> </processingSoftware> </ocrProcessingStep> </OCRProcessing> </Description> <Styles> <ParagraphStyle ID="StyleId-FFFFFFFF-FFFF-FFFF-FFFF-FFFFFFFFFFFF-" ALIGN="Left" LEFT="0" RIGHT="0" FIRSTLINE="0"/> </Styles> <Layout> <Page ID="Page1" PHYSICAL_IMG_NR="1"> <PrintSpace HEIGHT="%s" WIDTH="%s" VPOS="0" HPOS="0"/> </Page> </Layout></alto>' % (self.faux_width, self.faux_height)
generic_handle.save()
# save page object
return self.ohandle.save()
def purgeReaduxVirtualObjects(self):
readux_solr_handle = solrHandles.onDemand('readux')
sparql_response = fedora_handle.risearch.sparql_query('select $virtobj where {{ $virtobj <http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/isVirtualFor> <info:fedora/%s> . }}' % (self.pid))
for obj in sparql_response:
print "Purging virtual object: %s" % obj['virtobj']
fedora_handle.purge_object( obj['virtobj'].split("info:fedora/")[-1] )
print "Removing from Readux solr core..."
readux_solr_handle.delete_by_key(obj['virtobj'].split("info:fedora/")[-1], commit=False)
# commit solr purges
readux_solr_handle.commit()
return True
def reingestBag(self, removeExportTar = False): # get PID PID = self.pid print "Roundrip Ingesting:",PID # export bag, returning the file structure location of tar file export_tar = self.exportBag(returnTargetDir=True) print "Location of export tar file:",export_tar # purge self fedora_handle.purge_object(PID) # reingest exported tar file actions.bagIngest.ingestBag(actions.bagIngest.payloadExtractor(export_tar,'single')) # delete exported tar if removeExportTar == True: print "Removing export tar..." os.remove(export_tar) # return return PID,"Reingested."
def ingestBagAndPush(bag_dir, dest_repo, refresh_remote=True, overwrite=False, export_context='migrate'):
# DEBUG
print dir(localConfig)
# load bag_handle and ingest
print "Working on:",bag_dir
bag_handle = WSUDOR_ContentTypes.WSUDOR_Object(object_type="bag", payload=bag_dir)
if bag_dir == 'Could not load WSUDOR or Bag object.':
print "Aborting, bag_handle initiziation was unsuccessful."
return False
# validate bag for WSUDOR ingest
valid_results = bag_handle.validIngestBag()
if valid_results['verdict'] != True:
print "Bag is not valid for the following reasons, aborting.", valid_results
return False
# ingest bag & skip indexing
ingest_bag = bag_handle.ingestBag(indexObject=False)
# push to remote repo
print "sending object..."
# Use object method
obj_handle = WSUDOR_ContentTypes.WSUDOR_Object(bag_handle.pid)
obj_handle.sendObject(dest_repo, refresh_remote=refresh_remote, overwrite=overwrite, export_context=export_context)
# delete local object
print "finally, removing object"
fedora_handle.purge_object(bag_handle.pid)
# remove from Solr
solr_handle.delete_by_key(bag_handle.pid)
return json.dumps({"Ingest Results for {bag_label}, PID: {bag_pid}".format(bag_label=bag_handle.label.encode('utf-8'),bag_pid=bag_handle.pid):True})
def purgeObject_worker(job_package): form_data = job_package['form_data'] pid = job_package['PID'] # get obj_handle obj_handle = WSUDOR_ContentTypes.WSUDOR_Object(pid) # check object state print obj_handle.ohandle.state if obj_handle.ohandle.state != "D": return "Skipping, object state not 'Deleted (D)'" print "purging Constituents if present" if getattr(obj_handle, 'purgeConstituents', None): obj_handle.purgeConstituents() # else, purge object from Fedora (object will be pulled via Messenging service) result = fedora_handle.purge_object(obj_handle.pid) return "%s purge result: %s" % (obj_handle.pid, result) # remove from Solr solr_handle.delete_by_key(obj_handle.pid)
def createObj_worker():
form_data = request.form
print form_data
# instantiate object with quick variables
known_values = {
"id": form_data["pid"],
"identifier": form_data["pid"].split(":")[-1],
"label": form_data["label"],
"content_type": "WSUDOR_%s" % (form_data["CM"]),
"policy": "%s" % (form_data["policy"]),
}
# instantiate ObjMeta object
om_handle = ObjMeta(**known_values)
# show relationships
om_handle.object_relationships = [
{
"predicate": "http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/hasSecurityPolicy",
"object": "info:fedora/%s" % (form_data["policy"]),
},
{
"predicate": "http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/hasSecurityPolicy",
"object": "info:fedora/%s" % (form_data["policy"]),
},
]
# prepare new working dir & recall original
working_dir = "/tmp/Ouroboros/" + str(uuid.uuid4())
print "creating working dir at", working_dir
# create if doesn't exist
if not os.path.exists(working_dir):
os.mkdir(working_dir)
os.system("mkdir %s/datastreams" % (working_dir))
# write objMeta
print "writing:", om_handle.toJSON()
om_handle.writeToFile("%s/objMeta.json" % (working_dir))
if "bagify" in form_data:
# bagify
print "bagifying"
bag = bagit.make_bag("%s" % (working_dir), {"Object PID": form_data["pid"]})
# ingest
if "ingest" in form_data:
# purge if already exists
if "purge" in form_data:
try:
print "purging object"
fedora_handle.purge_object(form_data["pid"])
except:
print "object not found, skipping purge"
# bagify
if "bagify" not in form_data:
print "bagifying"
bag = bagit.make_bag("%s" % (working_dir), {"Object PID": form_data["pid"]})
# open new handle
bag_handle = WSUDOR_ContentTypes.WSUDOR_GenObject(payload=working_dir, object_type="bag")
ingest_result = bag_handle.ingestBag()
# render
return render_template(
"createBag_confirm.html", status="result for %s was %s" % (form_data["pid"], ingest_result)
)
else:
return render_template("createBag_confirm.html", status=working_dir)
def bagIngest_worker(job_package):
bag_dir = job_package['bag_dir']
# load bag_handle and ingest
print "Working on:",bag_dir
bag_handle = WSUDOR_ContentTypes.WSUDOR_Object(bag_dir, object_type="bag")
if bag_dir == 'Could not load WSUDOR or Bag object.':
print "Aborting, bag_handle initiziation was unsuccessful."
return False
# validate bag for WSUDOR ingest
valid_results = bag_handle.validIngestBag()
if valid_results['verdict'] != True:
print "Bag is not valid for the following reasons, aborting.", valid_results
return False
# optional flags
###########################################################################################
# overwrite
if 'overwrite' in job_package['form_data']:
print "purging object if exists"
if fedora_handle.get_object(bag_handle.pid).exists:
fedora_handle.purge_object(bag_handle.pid)
# push to remote
if 'push_remote' in job_package['form_data']:
# get options
# set destination repo
dest_repo = job_package['form_data']['dest_repo']
# get export context
export_context = job_package['form_data']['export_context']
# overwrite
if 'overwrite' in job_package['form_data']:
overwrite = True
else:
overwrite = False
# refresh remote
if 'refresh_remote' in job_package['form_data']:
refresh_remote = True
else:
refresh_remote = False
# omit checksums
if 'omit_checksums' in job_package['form_data']:
omit_checksums = True
else:
omit_checksums = False
# ingest bag
try:
# because we're sending remotely, not indexing locally
ingest_bag = bag_handle.ingestBag(indexObject=False)
except Exception, e:
raise Exception(e)
return False
# push to remote repo
print "sending object..."
# Use object method
obj_handle = WSUDOR_ContentTypes.WSUDOR_Object(bag_handle.pid)
obj_handle.sendObject(dest_repo, refresh_remote=refresh_remote, overwrite=overwrite, export_context=export_context, omit_checksums=omit_checksums)
# delete local object (and constituent objects)
print "purging Constituents if present"
if getattr(obj_handle, 'purgeConstituents', None):
obj_handle.purgeConstituents()
print "finally, removing object"
fedora_handle.purge_object(obj_handle.pid)
# remove from Solr
solr_handle.delete_by_key(obj_handle.pid)
# fire ingestWorkspace callback if checked
if 'origin' in job_package['form_data'] and job_package['form_data']['origin'] == 'ingestWorkspace' and ingest_bag == True:
print "firing ingest callback"
actions.actions.ingestBag_callback.apply_async(kwargs={'job_package':job_package}, queue=job_package['username'])
return json.dumps({"Ingest Results for %s, PID: %s" % (bag_handle.label.encode('utf-8'), bag_handle.pid):ingest_bag})
def createContainer_worker():
form_data = request.form
print form_data
unique_identifier = "LearningObject_%s" % str(uuid.uuid4())
pid = "wayne:"+unique_identifier
# instantiate object with quick variables
known_values = {
"id":pid,
"identifier":unique_identifier,
"label":form_data['label'],
"description":form_data['description'],
"creator":form_data['creator'],
"date":form_data['date'],
"content_type":"WSUDOR_LearningObject",
"policy":"info:fedora/wayne:WSUDORSecurity-permit-apia-unrestricted",
}
# instantiate ObjMeta object
om_handle = ObjMeta(**known_values)
# show relationships
om_handle.object_relationships = [
{
"predicate": "info:fedora/fedora-system:def/relations-external#isMemberOfCollection",
"object": form_data['collection']
},
{
"predicate": "http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/hasParent",
"object": form_data['collection']
},
{
"predicate": "http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/isDiscoverable",
"object": "info:fedora/True"
},
{
"predicate": "info:fedora/fedora-system:def/relations-external#hasContentModel",
"object": "info:fedora/CM:LearningObject"
},
{
"predicate": "http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/preferredContentModel",
"object": "info:fedora/CM:Container"
},
{
"predicate": "http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/hasSecurityPolicy",
"object": "info:fedora/wayne:WSUDORSecurity-permit-apia-unrestricted"
}
]
# add optional associated objects
if "associated_objects" in form_data:
print "writing associated object relationships"
associated_objects = [obj.strip() for obj in form_data['associated_objects'].split(',')]
for obj in associated_objects:
if obj != '':
om_handle.object_relationships.append({
"predicate":"http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/learningObjectFor",
"object": "info:fedora/%s" % obj
})
# prepare new working dir & recall original
working_dir = "/tmp/Ouroboros/"+str(uuid.uuid4())
print "creating working dir at", working_dir
# create if doesn't exist
if not os.path.exists(working_dir):
os.mkdir(working_dir)
os.system("mkdir %s/datastreams" % (working_dir))
# write custom MODS
# prepare subjects
subjects = [subject.strip() for subject in form_data['subjects'].split(",")]
subject_string = ''
for subject in subjects:
if subject != '':
subject_string += '<mods:subject authority="lcsh"><mods:topic>%s</mods:topic></mods:subject>' % subject
raw_MODS = '''<?xml version="1.0" encoding="utf-8"?>
<mods:mods xmlns:mods="http://www.loc.gov/mods/v3" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" version="3.4" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-4.xsd">
<mods:titleInfo>
<mods:title>%(label)s</mods:title>
</mods:titleInfo>
<mods:abstract>%(description)s</mods:abstract>
%(subject_string)s
<mods:name authority="local" type="person">
<mods:namePart>%(creator)s</mods:namePart>
<mods:role>
<mods:roleTerm authority="marcrelator" type="text">creator</mods:roleTerm>
</mods:role>
</mods:name>
<mods:originInfo>
<mods:dateIssued encoding="w3cdtf" keyDate="yes">%(date)s</mods:dateIssued>
</mods:originInfo>
<mods:identifier type="local">%(identifier)s</mods:identifier>
<mods:extension>
<PID>%(id)s</PID>
</mods:extension>
<mods:accessCondition type="useAndReproduction">%(rights)s</mods:accessCondition>
</mods:mods>
''' % {
'label':om_handle.label,
'description':om_handle.description,
'creator':om_handle.creator,
'date':om_handle.date,
'id':om_handle.id,
'identifier':om_handle.identifier,
'subject_string':subject_string,
'rights':form_data['rights']
}
print raw_MODS
with open('%s/MODS.xml' % working_dir,'w') as f:
f.write(raw_MODS)
# write objMeta
print "writing:",om_handle.toJSON()
om_handle.writeToFile('%s/objMeta.json' % (working_dir))
# bagify
print 'bagifying'
bag = WSUDOR_bagger.make_bag(working_dir, {
'Object PID' : pid
})
# ingest
# purge if already exists
if 'purge' in form_data:
try:
print "purging object"
fedora_handle.purge_object(form_data['pid'])
except:
print "object not found, skipping purge"
# open new handle
bag_handle = WSUDOR_ContentTypes.WSUDOR_Object(payload=working_dir, object_type='bag')
ingest_result = bag_handle.ingestBag()
# cleanup
shutil.rmtree(working_dir)
# render
time.sleep(3)
return redirect('tasks/learningObj/container/%s' % pid)
def createDocument_worker(parent_PID):
form_data = request.form
print form_data
# open parent handle
obj = WSUDOR_ContentTypes.WSUDOR_Object(parent_PID)
unique_identifier = "LearningObject_File_%s" % str(uuid.uuid4())
pid = "wayne:"+unique_identifier
# instantiate object with quick variables
known_values = {
"id":pid,
"identifier":unique_identifier,
"label":form_data['label'],
"description":form_data['description'],
"creator":form_data['creator'],
"date":form_data['date'],
"content_type":"WSUDOR_%s" % form_data['CM'],
"policy":"info:fedora/wayne:WSUDORSecurity-permit-apia-unrestricted"
}
print known_values
# instantiate ObjMeta object
om_handle = ObjMeta(**known_values)
# show relationships
om_handle.object_relationships = [
{
"predicate": "http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/hasParent",
"object": "info:fedora/%s" % parent_PID
},
{
"predicate": "info:fedora/fedora-system:def/relations-external#isConstituentOf",
"object": "info:fedora/%s" % parent_PID
},
{
"predicate": "http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/isDiscoverable",
"object": "info:fedora/False"
},
{
"predicate": "http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/preferredContentModel",
"object": "info:fedora/CM:%s" % form_data['CM']
},
{
"predicate": "http://digital.library.wayne.edu/fedora/objects/wayne:WSUDOR-Fedora-Relations/datastreams/RELATIONS/content/hasSecurityPolicy",
"object": "info:fedora/wayne:WSUDORSecurity-permit-apia-unrestricted"
}
]
# prepare new working dir & recall original
working_dir = "/tmp/Ouroboros/"+str(uuid.uuid4())
print "creating working dir at", working_dir
# create if doesn't exist
if not os.path.exists(working_dir):
os.mkdir(working_dir)
os.system("mkdir %s/datastreams" % (working_dir))
# write custom MODS
# prepare subjects
subjects = [subject.strip() for subject in form_data['subjects'].split(",")]
subject_string = ''
for subject in subjects:
if subject != '':
subject_string += '<mods:subject authority="lcsh"><mods:topic>%s</mods:topic></mods:subject>' % subject
raw_MODS = '''<?xml version="1.0" encoding="utf-8"?>
<mods:mods xmlns:mods="http://www.loc.gov/mods/v3" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" version="3.4" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-4.xsd">
<mods:titleInfo>
<mods:title>%(label)s</mods:title>
</mods:titleInfo>
<mods:abstract>%(description)s</mods:abstract>
%(subject_string)s
<mods:name authority="local" type="person">
<mods:namePart>%(creator)s</mods:namePart>
<mods:role>
<mods:roleTerm authority="marcrelator" type="text">creator</mods:roleTerm>
</mods:role>
</mods:name>
<mods:originInfo>
<mods:dateCreated>%(date)s</mods:dateCreated>
</mods:originInfo>
<mods:identifier type="local">%(identifier)s</mods:identifier>
<mods:extension>
<PID>%(id)s</PID>
</mods:extension>
<mods:accessCondition type="useAndReproduction">%(rights)s</mods:accessCondition>
</mods:mods>
''' % {
'label':om_handle.label,
'description':om_handle.description,
'creator':om_handle.creator,
'date':om_handle.date,
'id':om_handle.id,
'identifier':om_handle.identifier,
'subject_string':subject_string,
'rights':form_data['rights']
}
print raw_MODS
with open('%s/MODS.xml' % working_dir,'w') as f:
f.write(raw_MODS)
# write datastream
# Identify datastreams folder
datastreams_dir = working_dir + "/datastreams"
target_filename = '%s/%s' % (datastreams_dir,form_data['filename'])
# retrieve uploaded / pasted / content and write to disk
if form_data['dataType'] == 'dsLocation':
file_data = requests.get(form_data['dsLocation'])
with open(target_filename) as f:
f.write(file_data.content)
elif form_data['dataType'] == 'upload':
# writes to temp file in /tmp/Ouroboros
if 'upload' in request.files and request.files['upload'].filename != '':
print "Form provided file, uploading and reading file to variable"
with open(target_filename,'w') as fhand:
fhand.write(request.files['upload'].read())
else:
print "file could not be found"
return False
filename = form_data['filename']
label = form_data['label']
order = 1
# get extension, ds_id
mimetypes.init()
ds_id, ext = filename.split(".")
# create datastream dictionary
ds_dict = {
"filename": filename,
"ds_id": ds_id,
"mimetype": mimetypes.types_map[".%s" % ext],
"label": label,
"internal_relationships": {},
'order': order
}
om_handle.datastreams.append(ds_dict)
om_handle.isRepresentedBy = ds_id
# write objMeta
print "writing:",om_handle.toJSON()
om_handle.writeToFile('%s/objMeta.json' % (working_dir))
# bagify
print 'bagifying'
bag = WSUDOR_bagger.make_bag(working_dir, {
'Object PID' : pid
})
# ingest
# purge if already exists
if 'purge' in form_data:
try:
print "purging object"
fedora_handle.purge_object(form_data['pid'])
except:
print "object not found, skipping purge"
# open new handle
bag_handle = WSUDOR_ContentTypes.WSUDOR_Object(payload=working_dir, object_type='bag')
ingest_result = bag_handle.ingestBag()
# cleanup
# shutil.rmtree(working_dir)
# render
time.sleep(3)
return redirect('tasks/learningObj/container/%s' % parent_PID)