Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Separated out zip logic from send_image_data() #25

Merged
merged 1 commit into from
Mar 19, 2024
Merged

Separated out zip logic from send_image_data() #25

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"

[project]
name = "rubin.citsci"
version = "0.2.6"
version = "0.3.0"
readme = "README.md"
dependencies = [
"panoptes_client",
Expand Down
21 changes: 9 additions & 12 deletions src/rubin/citsci/pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -228,7 +228,7 @@ def check_status(self):
and a "manifest_url" of the URL where the manifest file was uploaded to.
"""

status_uri = "https://rsp-data-exporter" + self.dev_mode_url + "-dot-skyviewer.uw.r.appspot.com/citizen-science-ingest-status?guid=" + self.guid
status_uri = f"https://rsp-data-exporter{self.dev_mode_url}-dot-skyviewer.uw.r.appspot.com/citizen-science-ingest-status?guid={self.guid}"
raw_response = urllib.request.urlopen(status_uri).read()
response = raw_response.decode('UTF-8')
return json.loads(response)
Expand All @@ -240,7 +240,7 @@ def download_batch_metadata(self):
"""

project_id_str = str(self.project_id)
dl_response = "https://rsp-data-exporter" + self.dev_mode_url + "-dot-skyviewer.uw.r.appspot.com/active-batch-metadata?vendor_project_id=" + project_id_str
dl_response = f"https://rsp-data-exporter{self.dev_mode_url}-dot-skyviewer.uw.r.appspot.com/active-batch-metadata?vendor_project_id={project_id_str}"
raw_response = urllib.request.urlopen(dl_response).read()
response = raw_response.decode('UTF-8')
return json.loads(response)
Expand Down Expand Up @@ -274,8 +274,7 @@ def __upload_tabular_manifest(self, manifest_path):
blob.upload_from_filename(manifest_path)
return

# Validates that the RSP user is allowed to create a new subject set
def send_image_data(self, subject_set_name, batch_dir):
def send_image_data(self, subject_set_name, zip_path):
"""
Sends the new data batch to the Rubin EPO Data Center for public hosting
so that the data can be added to the target Zooniverse project.
Expand Down Expand Up @@ -306,7 +305,6 @@ def send_image_data(self, subject_set_name, batch_dir):
self.log_step("Checking batch status")
if self.__has_active_batch() == True:
raise CitizenSciencePipelineError("INCOMPLETE SUBJECT SET EXISTS! You cannot send another batch of data while a subject set is still active (not yet retired) on the Zooniverse platform - you can only send a new batch of data if all subject sets associated to a project have been completed.")
zip_path = self.__zip_image_cutouts(batch_dir)
self.__upload_cutouts(zip_path)
self.__create_new_subject_set(subject_set_name)

Expand Down Expand Up @@ -352,16 +350,15 @@ def __process_edc_response(self):
self.log_step("Transfer process complete, but further processing is required on the Zooniverse platform and you will receive an email at " + self.email)
return

def __zip_image_cutouts(self, batch_dir):
def zip_image_cutouts(self, batch_dir):
"""
This function is called as part of the send_image_data() workflow and should
not be accessed publicly as unexpected results will occur.
This function is responsible for zipping up all the cutouts that will be sent
to the Zooniverse, and returns the path to the zip file.
"""

self.guid = str(uuid.uuid4())
self.log_step("Zipping up all the astro cutouts - this can take a few minutes with large data sets, but unlikely more than 10 minutes.")
shutil.make_archive("./" + self.guid, 'zip', batch_dir)
return ["./" + self.guid + '.zip', self.guid + '.zip']
shutil.make_archive(f"./{self.guid}", 'zip', batch_dir)
return [f"./{self.guid}.zip", f"{self.guid}.zip"]

def __upload_cutouts(self, zip_path):
"""
Expand Down Expand Up @@ -392,7 +389,7 @@ def __alert_edc_of_new_citsci_data(self, tabular = False):

try:
resource = "citizen-science-image-ingest" if tabular == False else "citizen-science-tabular-ingest"
edc_endpoint = "https://rsp-data-exporter" + self.dev_mode_url + "-dot-skyviewer.uw.r.appspot.com/" + resource + "?email=" + self.email + "&vendor_project_id=" + project_id_str + "&guid=" + self.guid + "&vendor_batch_id=" + str(self.vendor_batch_id) + "&debug=True"
edc_endpoint = f"https://rsp-data-exporter{self.dev_mode_url}-dot-skyviewer.uw.r.appspot.com/{resource}?email={self.email}&vendor_project_id={project_id_str}&guid={self.guid}&vendor_batch_id={str(self.vendor_batch_id)}&debug=True"
# print(edc_endpoint)
response = urllib.request.urlopen(edc_endpoint, timeout=3600).read()
str(response)
Expand Down