diff extract_tables.py @ 1:57251c760cab draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ena_upload commit ffea061c1ad6e7291abfe220230dbdbe8d19a2bd"
author iuc
date Fri, 30 Apr 2021 12:09:25 +0000
parents 382518f24d6d
children 6f6537780379
line wrap: on
line diff
--- a/extract_tables.py	Sat Nov 28 09:45:44 2020 +0000
+++ b/extract_tables.py	Fri Apr 30 12:09:25 2021 +0000
@@ -3,6 +3,11 @@
 import pathlib
 from datetime import datetime
 
+"""
+Parse the configfile generated by the Galaxy tool.
+This file is JSON-formatted and should be converted to a set of tabular files.
+"""
+
 FILE_FORMAT = 'fastq'
 
 parser = argparse.ArgumentParser()
@@ -78,11 +83,15 @@
                                                'submission_date_ENA']) + '\n')
             run_index = 0
             # exp['runs'] is a list of lists
-            for run in exp['runs']:
+            for (base_run, run_files) in exp['runs']:
                 run_index += 1
-                run_alias = '.'.join(['run_' + str(run_index), str(exp_index), str(sample_index)]) \
-                            + '_' + timestamp
-                for file_entry in run:
+                if base_run != '':
+                    run_alias = base_run
+                else:
+                    # no alias provided, generated a unique one
+                    run_alias = '_'.join(['run_' + str(run_index), str(exp_index),
+                                          str(sample_index)]) + '_' + timestamp
+                for file_entry in run_files:
                     runs_table.write('\t'.join([run_alias, action, 'ena_run_accession', exp_alias,
                                                 file_entry, FILE_FORMAT, 'file_checksum',
                                                 'submission_date_ENA']) + '\n')