fixed bug that was stopping analysis_summary_json being populated on …

…import_qc_command; slight refactoring; excluded analysis_summary_json from serializer

emgapi/serializers.py

@@ -1021,6 +1021,7 @@ class Meta:
             'is_suppressed',
             'suppressed_at',
             'suppression_reason',
+            'analysis_summary_json'
         )
 
 

emgapianns/management/commands/import_extra_assembly_annotations.py

@@ -47,6 +47,8 @@ def add_arguments(self, parser):
     def handle(self, *args, **options):
         logger.info(options)
 
+        return
+
         self.results_directory = os.path.realpath(options.get('results_directory').strip())
 
         if not os.path.exists(self.results_directory):

emgapianns/management/commands/import_qc.py

@@ -81,19 +81,9 @@ def import_qc(reader, job, emg_db):
                 var = emg_models.AnalysisMetadataVariableNames.objects.using(emg_db) \
                     .get(var_name=row[0])
             if var is not None:
-                job_ann, created = emg_models.AnalysisJobAnn.objects.using(emg_db).update_or_create(
-                    job=job, var=var,
-                    defaults={'var_val_ucv': row[1]}
-                )
-                analysis_summary = job.analysis_summary_json or []
-                analysis_summary.append({
-                    'key': job_ann.var.var_name,
-                    'value': job_ann.var_val_ucv,
-                })
-                job.analysis_summary_json = analysis_summary
-                job.save()
-
-                anns.append(job_ann)
+                Command.update_analysis_summary(job, var.var_name, row[1])
+
+                # anns.append(job_ann)
         logger.info("Total %d Annotations for Run: %s" % (len(anns), job))
 
     @staticmethod
@@ -104,31 +94,29 @@ def import_rna_counts(rootpath, job, emg_db):
             with open(res) as tsvfile:
                 reader = csv.reader(tsvfile, delimiter='\t')
                 for row in reader:
-                    if not row: # skip empty lines at the end of the file
+                    if not row:  # skip empty lines at the end of the file
                         continue
                     try:
                         if row[0] == 'SSU count':
                             var_name = 'Predicted SSU sequences'
                         elif row[0] == 'LSU count':
                             var_name = 'Predicted LSU sequences'
                         elif not row[0]:
-                            continue # Skip empty value rows
+                            continue  # Skip empty value rows
                         else:
                             logging.error("Unsupported variable name {}".format(row[0]))
                             raise UnexpectedVariableName
 
                         var = emg_models.AnalysisMetadataVariableNames.objects.using(emg_db) \
                             .get(var_name=var_name)
 
-                        job_ann, created = emg_models.AnalysisJobAnn.objects.using(emg_db).update_or_create(
-                            job=job, var=var,
-                            defaults={'var_val_ucv': row[1]}
-                        )
+                        if var is not None:
+                            Command.update_analysis_summary(job, var.var_name, row[1])
                         logging.info("{} successfully loaded into the database.".format(row[0]))
 
                     except emg_models.AnalysisMetadataVariableNames.DoesNotExist:
                         logging.error("Could not find variable name {} in the database even "
-                                        "though it should be supported!".format(row[0]))
+                                      "though it should be supported!".format(row[0]))
                         raise UnexpectedVariableName
         else:
             logging.warning("RNA counts file does not exist: {}".format(res))
@@ -162,10 +150,8 @@ def import_orf_stats(rootpath, job, emg_db):
                         var = emg_models.AnalysisMetadataVariableNames.objects.using(emg_db) \
                             .get(var_name=var_name)
 
-                        job_ann, created = emg_models.AnalysisJobAnn.objects.using(emg_db).update_or_create(
-                            job=job, var=var,
-                            defaults={'var_val_ucv': row[1]}
-                        )
+                        if var is not None:
+                            Command.update_analysis_summary(job, var.var_name, row[1])
                         logging.info("{} successfully loaded into the database.".format(row[0]))
 
                     except emg_models.AnalysisMetadataVariableNames.DoesNotExist:
@@ -176,3 +162,13 @@ def import_orf_stats(rootpath, job, emg_db):
                         raise UnexpectedVariableName(msg)
         else:
             logging.warning("orf.stats file does not exist: {}".format(res))
+
+    @staticmethod
+    def update_analysis_summary(job, var_key, var_value):
+        analysis_summary = job.analysis_summary_json or []
+        analysis_summary.append({
+            'key': var_key,
+            'value': var_value,
+        })
+        job.analysis_summary_json = analysis_summary
+        job.save()

tests/webuploader/test_qc.py

@@ -159,8 +159,8 @@ def test_qc_multiple_pipelines(self, client, run_multiple_analysis, results):
 
 
             # print results
-            # assert len(rsp["data"]["attributes"]["analysis-summary"]) == 12
-            assert len(rsp["data"]["attributes"]["analysis-summary"]) == 7
+            assert len(rsp["data"]["attributes"]["analysis-summary"]) == 12
+
         else:
             assert len(rsp["data"]["attributes"]["analysis-summary"]) == 5