Minor fixes, feedback from the code review

- remove emg-backlog-schema as dependency
- address minor comments

.github/workflows/test.yml

@@ -34,7 +34,6 @@ jobs:
 
     - name: 🔧 - Install Dependencies
       run: |
-        pip install -U git+git://github.com/EBI-Metagenomics/emg-backlog-schema.git
         pip install -U git+git://github.com/EBI-Metagenomics/ena-api-handler.git
         pip install -U -r requirements.txt
         pip install -U -r requirements-test.txt

README.md

@@ -101,7 +101,6 @@ Install application::
     conda create -q -n myenv python=3.6.8
     source activate myenv
 
-    pip install -U git+git://github.com/EBI-Metagenomics/emg-backlog-schema.git;
     pip install -U git+git://github.com/EBI-Metagenomics/ena-api-handler.git
     pip install https://github.com/EBI-Metagenomics/emgapi/archive/$latestTag.tar.gz
 
@@ -133,7 +132,6 @@ How to install the webuploader (one off)?
     conda create -q -n myenv python=3.6.8
     source activate myenv
 
-    pip install -U git+git://github.com/EBI-Metagenomics/emg-backlog-schema.git
     pip install -U git+git://github.com/EBI-Metagenomics/ena-api-handler.git
 
     pip install -U -r https://raw.githubusercontent.com/EBI-Metagenomics/emgapi/webuploader/requirements-webuploader.txt

emgapianns/management/commands/create_study_summary.py

@@ -64,8 +64,12 @@ def handle(self, *args, **options):
         if not options['rootpath']:
             raise ValueError("rootpath (RESULTS_PRODUCTION_DIR setting) cannot by empty)")
 
+
         rootpath = os.path.abspath(options['rootpath'])
 
+        if not os.path.isdir(rootpath):
+            raise ValueError(f"rootpath {rootpath} is not a directory")
+
         gen = StudySummaryGenerator(accession=study_accession, pipeline=pipeline, rootpath=rootpath,
                                     database=database)
         gen.run()

emgapianns/management/commands/import_analysis.py

@@ -84,7 +84,7 @@ def add_arguments(self, parser):
                             help='Library strategy',
                             choices=['AMPLICON', 'WGS', 'ASSEMBLY', 'RNA-Seq', 'WGA'])
         parser.add_argument('--pipeline', help='Pipeline version',
-                            choices=['4.1', '5.0'], default='4.1')
+                            choices=['4.1', '5.0'], default='5.0')
         parser.add_argument('--database',
                             help='Target emg_db_name alias',
                             choices=['default', 'dev', 'prod'],
@@ -170,13 +170,15 @@ def __find_existing_result_dir(self, secondary_study_accession, run_accession, v
         # find version_{} folder
         result_folder = []
         if len(study_folder) == 0:
+            # TODO: replace with raise CommandError
             sys.exit('Could not find result directory for: {}'.format(secondary_study_accession))
         for cur_study_folder in study_folder:
             directory = os.path.join(cur_study_folder, 'version_{}/'.format(version))
             result_folder += self.__find_folder(directory, search_pattern=run_accession, maxdepth=3)
 
         # if len(result_folder) > 1: take the latest created version_{} folder
         if len(result_folder) == 0:
+            # TODO: replace with raise CommandError
             sys.exit('Could not find result directory for: {}'.format(run_accession))
         else:
             latest_folder = max(result_folder, key=os.path.getctime)

emgapianns/management/commands/import_sample.py

@@ -82,6 +82,7 @@ def create_or_update_sample(self, ena_db_model, api_data):
         except emg_models.Biome.DoesNotExist as exception:
             logger.exception(exception)
             logger.error(f'The supplied biome is not valid. Biome: "{self.biome}"')
+            # TODO: replace with raise CommandError
             sys.exit(1)
 
         logger.info('Creating sample {}'.format(accession))

emgapianns/management/lib/__init__.py

@@ -42,7 +42,7 @@ def add_arguments(self, parser):
                 '4.0',
                 '4.1',
                 '5.0'],
-            default='4.1'
+            default='5.0'
         )
 
     def handle(self, *args, **options):

emgapianns/management/lib/genome_util.py

@@ -51,6 +51,7 @@ def sanity_check_catalogue_dir(d):
         for e in errors:
             logger.error(e)
         logger.error('Validation failed, see errors above')
+        # TODO: replace with raise CommandError
         sys.exit(1)
 
 

emgapianns/management/lib/study_summary_generator.py

@@ -29,6 +29,7 @@ def __init__(self, accession, pipeline, rootpath, database):
 
     def run(self):
         if not os.path.exists(self.study_result_dir):
+            # TODO: replace with raise CommandError
             sys.exit(
                 "Study result directory for {} does not exist:\n{}".format(self.study_accession, self.study_result_dir))