def prepare(package_id, force=False):
packageInfo = collections.get("package").find_one({
"packageId" : package_id,
},{"_id" : 0})
# create a workspace package object if required
if packageInfo is None:
packageInfo = {
"packageId" : package_id
}
# quit if there is nothing todo
if not force and packageInfo.get("prepared") == True:
return {
"success" : True,
"message" : "already prepared, use force flag to force prepare"
}
# make sure we are not trying to prepare a package that has been deleted
ckanPackage = ckanPackageQuery.get(package_id)
if ckanPackage.get('state') == 'deleted':
raise Exception('Package has been deleted')
# get all package resources
resources = ckanResourceQuery.active(package_id)
status = []
for resource in resources:
# get path on disk for file as well as file extension
filepath = resourceUtil.get_path(resource.get('id'))
ext = _getFileExtension(resource.get('name'))
# extract zip contents if zip
if ext == "zip":
# TODO: we should be checking a zip hash before we go unzipping every time
results = extractZip(package_id, resource.get('id'), filepath, resource.get('name'))
for result in results:
status.append(result)
# extract 'normal' file (non-zip)
else:
result = importer.processFile(filepath, package_id, resource.get('id'), resource=resource)
status.append(result)
# respond with update of what we did (or did not) do.
packageInfo["runInfo"] = status
packageInfo["lastTouched"] = datetime.utcnow()
packageInfo["prepared"] = True
collections.get("package").update({"packageId":package_id}, packageInfo, upsert=True)
return packageInfo
def get(package_id):
# get all package resources
resources = ckanResourceQuery.active(package_id)
response = {
"package" : collections.get("package").find_one({
"packageId": package_id,
}, {"runInfo": 0, "_id": 0}),
"resources" : [],
"ckan" : {
"package" : ckanPackageQuery.get(package_id),
"resources" : resources
},
"pushed" : isPushed(package_id)
}
if response['package'] is None:
response['package'] = {}
# append information about the dataset resources to response
for resource in resources:
sheets = getResource(resource.get('id'))
upload = uploader.ResourceUpload(resource)
path = upload.get_path(resource['id'])
if os.path.exists(path):
resource['file_size'] = os.path.getsize(path)
else:
resource['file_size'] = 0
for sheet in sheets:
# we don't care about root excel files, only the sheets
if sheet.get('excel') == True or sheet.get('isZip') == True:
continue
response.get('resources').append(sheet)
return response
