Skip to content

fix/self_reference_validation #71

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

Merged
merged 2 commits into from
Apr 29, 2025
Merged

fix/self_reference_validation #71

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
18637d0
fix/self_reference_validation
tomreitz Mar 10, 2025
b8ad7f9
fix bugs line_number bugs
Mar 10, 2025
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
27 changes: 22 additions & 5 deletions lightbeam/validate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,7 +146,7 @@ def load_references_structure(self, swagger, definition):
prefixes_to_remove = ["#/definitions/", "#/components/schemas/"]
for k in schema["properties"].keys():
if k.endswith("Reference"):
original_endpoint = util.pluralize_endpoint(k.replace("Reference", ""))
original_endpoint = self.resolve_reference_to_endpoint(k)

# this deals with the fact that an educationOrganizationReference may be to a school, LEA, etc.:
endpoints_to_check = self.EDFI_GENERICS_TO_RESOURCES_MAPPING.get(original_endpoint, [original_endpoint])
Expand Down Expand Up @@ -217,10 +217,12 @@ async def validate_endpoint(self, endpoint):

for file_name in data_files:
self.logger.info(f"validating {file_name} against {definition} schema...")
file_counter = 0
with open(file_name) as file:
for i, line in enumerate(file):
line_number = i + 1
total_counter += 1
file_counter += 1
data = line.strip()

tasks.append(asyncio.create_task(
Expand Down Expand Up @@ -255,7 +257,7 @@ async def validate_endpoint(self, endpoint):
num_others = self.lightbeam.num_errors - self.MAX_VALIDATION_ERRORS_TO_DISPLAY
if self.lightbeam.num_errors > self.MAX_VALIDATION_ERRORS_TO_DISPLAY:
self.logger.warn(f"... and {num_others} others!")
self.logger.warn(f"... VALIDATION ERRORS on {self.lightbeam.num_errors} of {line_counter} lines in {file_name}; see details above.")
self.logger.warn(f"... VALIDATION ERRORS on {self.lightbeam.num_errors} of {file_counter} lines in {file_name}; see details above.")

# free up some memory
self.uniqueness_hashes = {}
Expand Down Expand Up @@ -298,7 +300,7 @@ async def do_validate_payload(self, endpoint, file_name, data, line_number):
if "uniqueness" in self.validation_methods:
error_message = self.violates_uniqueness(endpoint, payload, path="")
if error_message != "":
self.log_validation_error(endpoint, file_name, line_counter, "uniqueness", error_message)
self.log_validation_error(endpoint, file_name, line_number, "uniqueness", error_message)

# check references values are valid
if "references" in self.validation_methods and "Descriptor" not in endpoint: # Descriptors have no references
Expand Down Expand Up @@ -409,7 +411,7 @@ def has_invalid_references(self, payload, path=""):
if value!="": return value
elif isinstance(payload[k], dict) and k.endswith("Reference"):
is_valid_reference = False
original_endpoint = util.pluralize_endpoint(k.replace("Reference",""))
original_endpoint = self.resolve_reference_to_endpoint(k)

# this deals with the fact that an educationOrganizationReference may be to a school, LEA, etc.:
endpoints_to_check = self.EDFI_GENERICS_TO_RESOURCES_MAPPING.get(original_endpoint, [original_endpoint])
Expand All @@ -434,6 +436,19 @@ def has_invalid_references(self, payload, path=""):
return f"payload contains an invalid {k} " + (" (at "+path+"): " if path!="" else ": ") + json.dumps(params)
return ""

@staticmethod
def resolve_reference_to_endpoint(referenceName):
endpoint = referenceName
# remove final "Reference"
if endpoint.endswith("Reference"):
endpoint = endpoint[:-1*len("Reference")]
# remove leading "parent" if whole endpoint name isn't just "parent"
# (this handles things like parentObjectiveAssessmentReference)
if endpoint.startswith("parent") and endpoint!="parent":
endpoint = endpoint[len("parent"):]
endpoint = endpoint[0].lower() + endpoint[1:]
return util.pluralize_endpoint(endpoint)

# Tells you if a specified descriptor value is valid or not
def is_valid_descriptor_value(self, namespace, codeValue):
for row in self.lightbeam.api.descriptor_values:
Expand All @@ -444,7 +459,9 @@ def is_valid_descriptor_value(self, namespace, codeValue):
@staticmethod
def get_cache_key(payload):
cache_key = ''
for k in payload.keys():
payload_keys = list(payload.keys())
payload_keys.sort()
for k in payload_keys:
cache_key += f"{payload[k]}~~~"
return cache_key

Expand Down