nci-cidc-api-modules 1.2.7__tar.gz → 1.2.8__tar.gz

{nci_cidc_api_modules-1.2.7/nci_cidc_api_modules.egg-info → nci_cidc_api_modules-1.2.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nci_cidc_api_modules
-Version: 1.2.7
+Version: 1.2.8
 Summary: SQLAlchemy data models and configuration tools used in the NCI CIDC API
 Home-page: https://github.com/NCI-CIDC/cidc-api-gae
 License: MIT license

{nci_cidc_api_modules-1.2.7 → nci_cidc_api_modules-1.2.8}/cidc_api/models/models.py

@@ -28,6 +28,7 @@ __all__ = [
     "JobFileCategories",
     "ValidationConfigs",
     "TRIAL_APPENDIX_A",
+    "TRIAL_APPENDIX_A_CELL_THAT_ENDS_THE_HEADER",
     "REQUEST_LETTER",
     "ADMIN_FILE_CATEGORIES",
     "FINAL_JOB_STATUS",
@@ -82,7 +83,6 @@ from sqlalchemy import (
     Boolean,
     CheckConstraint,
     Column,
-    Date,
     DateTime,
     Enum,
     ForeignKey,
@@ -150,6 +150,10 @@ from ..shared.gcloud_client import (
 os.environ["TZ"] = "UTC"
 logger = get_logger(__name__)
 
+# pylint: disable=protected-access,not-callable,no-value-for-parameter,too-many-positional-arguments
+# pylint: disable=unsubscriptable-object,singleton-comparison,broad-exception-raised,redefined-builtin
+# pylint: disable=arguments-renamed,logging-fstring-interpolation,disable=comparison-with-callable
+
 
 class FileGroups:
     pass
@@ -3391,8 +3395,8 @@ class PreprocessedFiles(CommonColumns):
         """
         if job_id is not None:
             return query.filter_by(job_id=job_id)
-        else:
-            return query.filter(cls.job_id.is_(None))
+
+        return query.filter(cls.job_id.is_(None))
 
 
 INGESTION_JOB_STATUSES = [
@@ -3415,6 +3419,7 @@ INGESTION_JOB_COLORS = {
 }
 # TODO If have "CANCELLED" concept or other final status, add here
 FINAL_JOB_STATUS = ["PUBLISHED"]
+TRIAL_APPENDIX_A_CELL_THAT_ENDS_THE_HEADER = "Entity"
 
 
 class IngestionJobs(CommonColumns):
@@ -3455,16 +3460,16 @@ class IngestionJobs(CommonColumns):
         df = gcs_xlsx_or_csv_file_to_pandas_dataframe(GOOGLE_CLINICAL_DATA_BUCKET, appendix_a.object_url)
         categories = []
         headers_ended = False
-        for index, row in df.iterrows():
+        for _index, row in df.iterrows():
             cell = str(row.iloc[0])
             if headers_ended:
-                if not cell == "nan" and cell not in categories and cell != "Specialized_Data":
+                if cell != "nan" and cell not in categories:
                     categories.append(cell)
-            elif cell == "PATIENT-LEVEL DATA":
+            elif cell == TRIAL_APPENDIX_A_CELL_THAT_ENDS_THE_HEADER:
                 headers_ended = True
-        if "Data_Dictionary" not in categories:
+        if "data_dictionary" not in categories:
             # Ensure Data_Dictionary is always a required file category
-            categories.append("Data_Dictionary")
+            categories.append("data_dictionary")
         return categories
 
     @classmethod
@@ -3608,7 +3613,16 @@ class FileValidationErrors(CommonColumns):
     @classmethod
     @with_default_session
     def get_errors_for_job_sorted_by_file_id(cls, job_id: int, session: Session = None) -> list["FileValidationErrors"]:
-        return session.query(cls).filter(cls.job_id == job_id).order_by(cls.file_id.asc()).all()
+        errors = (
+            session.query(cls)
+            .join(PreprocessedFiles)
+            .filter(PreprocessedFiles.status == "current")
+            .filter(cls.job_id == job_id)
+            .order_by(cls.file_id.asc())
+            .all()
+        )
+
+        return errors
 
 
 class ValidationConfigs(CommonColumns):

{nci_cidc_api_modules-1.2.7 → nci_cidc_api_modules-1.2.8/nci_cidc_api_modules.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nci_cidc_api_modules
-Version: 1.2.7
+Version: 1.2.8
 Summary: SQLAlchemy data models and configuration tools used in the NCI CIDC API
 Home-page: https://github.com/NCI-CIDC/cidc-api-gae
 License: MIT license