Merge branch 'EBIvariation:master' into docker-metadata

bin/retrieve_archives_from_lts.py

@@ -56,11 +56,11 @@ def main():
     # Load the config_file from default location
     load_config()
 
-    with ELOADRetrieval() as eload_retrieval:
-        eload_retrieval.retrieve_eloads_and_projects(args.eload, args.retrieve_associated_project, args.update_path,
-                                                     args.eload_dirs_files, args.project, args.project_dirs_files,
-                                                     args.eload_lts_dir, args.project_lts_dir, args.eload_retrieval_dir,
-                                                     args.project_retrieval_dir)
+    eload_retrieval = ELOADRetrieval()
+    eload_retrieval.retrieve_eloads_and_projects(args.eload, args.retrieve_associated_project, args.update_path,
+                                                 args.eload_dirs_files, args.project, args.project_dirs_files,
+                                                 args.eload_lts_dir, args.project_lts_dir, args.eload_retrieval_dir,
+                                                 args.project_retrieval_dir)
 
 
 if __name__ == "__main__":

bin/submission_status.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python
+
+# Copyright 2020 EMBL - European Bioinformatics Institute
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import logging
+from argparse import ArgumentParser
+
+from ebi_eva_common_pyutils.logger import logging_config as log_cfg
+
+from eva_submission.eload_status import EloadStatus
+from eva_submission.eload_validation import EloadValidation
+from eva_submission.submission_config import load_config
+
+logger = log_cfg.get_logger(__name__)
+
+
+def main():
+    argparse = ArgumentParser(description='Provide a submission status for any ELOAD based on what has been accessioned and loaded.')
+    argparse.add_argument('--eload', required=True, type=int, help='The ELOAD number for this submission')
+    argparse.add_argument('--debug', action='store_true', default=False,
+                          help='Set the script to output logging information at debug level')
+
+    args = argparse.parse_args()
+
+    log_cfg.add_stdout_handler()
+    if args.debug:
+        log_cfg.set_log_level(logging.DEBUG)
+
+    # Load the config_file from default location
+    load_config()
+
+    with EloadStatus(args.eload) as eload:
+        eload.status()
+
+
+if __name__ == "__main__":
+    main()

eva_submission/eload_brokering.py

@@ -1,3 +1,4 @@
+import csv
 import os
 import shutil
 import subprocess
@@ -144,10 +145,26 @@ def _get_valid_vcf_files(self):
             valid_vcf_files.extend(files) if files else None
         return valid_vcf_files
 
+    def _generate_csv_mappings(self):
+        vcf_files_mapping_csv = os.path.join(self.eload_dir, 'brokering_vcf_files_mapping.csv')
+        with open(vcf_files_mapping_csv, 'w', newline='') as file:
+            writer = csv.writer(file)
+            writer.writerow(['vcf', 'fasta', 'report', 'assembly_accession'])
+            sub_analyses = self.eload_cfg.query('submission', 'analyses')
+            valid_analyses = self.eload_cfg.query('validation', 'valid', 'analyses')
+            for analysis_alias in valid_analyses:
+                fasta = sub_analyses[analysis_alias]['assembly_fasta']
+                report = sub_analyses[analysis_alias]['assembly_report']
+                assembly_accession = sub_analyses[analysis_alias]['assembly_accession']
+                for vcf_file in valid_analyses[analysis_alias]['vcf_files']:
+                    writer.writerow([vcf_file, fasta, report, assembly_accession])
+        return vcf_files_mapping_csv
+
     def _run_brokering_prep_workflow(self):
         output_dir = self.create_nextflow_temp_output_directory()
+        cfg['executable']['python']['script_path'] = os.path.dirname(os.path.dirname(__file__))
         brokering_config = {
-            'vcf_files': self._get_valid_vcf_files(),
+            'vcf_files_mapping': self._generate_csv_mappings(),
             'output_dir': output_dir,
             'executable': cfg['executable']
         }