fix time and version in bakta_io outputs

bakta/config.py

@@ -9,6 +9,7 @@
 from datetime import datetime
 from pathlib import Path
 
+import bakta
 import bakta.constants as bc
 
 
@@ -26,6 +27,7 @@
 debug = None
 
 # input / output configuration
+version = bakta.__version__
 db_path = None
 db_info = None
 tmp_path = None

bakta/db.py

@@ -86,10 +86,10 @@ def check(db_path: Path) -> dict:
     log.info('detected: major=%i, minor=%i, type=%s, date=%s', db_info['major'], db_info['minor'], db_info['type'], db_info['date'])
     if(db_info['major'] < bakta.__db_schema_version__):
         log.error('wrong database version detected! required=%i, detected=%i', bakta.__db_schema_version__, db_info['major'])
-        sys.exit(f"ERROR: wrong database version detected!\nBakta version {bakta.__version__} requires database version {bakta.__db_schema_version__}.x, but {db_info['major']}.{db_info['minor']} was detected. Please, update the database from https://doi.org/10.5281/zenodo.4247253")
+        sys.exit(f"ERROR: wrong database version detected!\nBakta version {cfg.version} requires database version {bakta.__db_schema_version__}.x, but {db_info['major']}.{db_info['minor']} was detected. Please, update the database from https://doi.org/10.5281/zenodo.4247253")
     elif(db_info['major'] > bakta.__db_schema_version__):
         log.error('wrong database version detected! required=%i, detected=%i', bakta.__db_schema_version__, db_info['major'])
-        sys.exit(f"ERROR: wrong database version detected!\nBakta version {bakta.__version__} requires database version {bakta.__db_schema_version__}.x, but {db_info['major']}.{db_info['minor']} was detected. Please, update Bakta or download a compatible database version from https://doi.org/10.5281/zenodo.4247253")
+        sys.exit(f"ERROR: wrong database version detected!\nBakta version {cfg.version} requires database version {bakta.__db_schema_version__}.x, but {db_info['major']}.{db_info['minor']} was detected. Please, update Bakta or download a compatible database version from https://doi.org/10.5281/zenodo.4247253")
 
     required_db_files = FILE_NAMES
     required_db_files.append('psc.dmnd' if db_info['type'] == 'full' else 'pscc.dmnd')
@@ -150,7 +150,7 @@ def main():
     parser = bu.init_parser(sub_command='_db')
     group_runtime = parser.add_argument_group('Runtime & auxiliary options')
     group_runtime.add_argument('--help', '-h', action='help', help='Show this help message and exit')
-    group_runtime.add_argument('--version', '-V', action='version', version=f'%(prog)s {bakta.__version__}')
+    group_runtime.add_argument('--version', '-V', action='version', version=f'%(prog)s {cfg.version}')
 
     subparsers = parser.add_subparsers(dest='subcommand', help='sub-command help')
     parser_list = subparsers.add_parser('list', help='List available database versions')  # add list sub-command options
@@ -166,7 +166,7 @@ def main():
     parser_update.add_argument('--tmp-dir', '-t', action='store', dest='tmp_dir', default=Path.cwd(), help='Temporary directory to download & extract (default = current working directory)')
 
     args = parser.parse_args()
-    print(f'Bakta software version: {bakta.__version__}')
+    print(f'Bakta software version: {cfg.version}')
     print(f'Required database schema version: {bakta.__db_schema_version__}\n')
     if(args.subcommand == 'list'):
         versions = fetch_db_versions()

bakta/io/gff.py

@@ -27,7 +27,7 @@ def write_features(data: dict, features_by_sequence: Dict[str, dict], gff3_path:
             fh.write(f"# organism {data['genome']['taxon']}\n")
 
         fh.write('# Annotated with Bakta\n')
-        fh.write(f'# Software: v{bakta.__version__}\n')
+        fh.write(f'# Software: v{cfg.version}\n')
         fh.write(f"# Database: v{cfg.db_info['major']}.{cfg.db_info['minor']}, {cfg.db_info['type']}\n")
         fh.write(f'# DOI: {bc.BAKTA_DOI}\n')
         fh.write(f'# URL: {bc.BAKTA_URL}\n')

bakta/io/insdc.py

@@ -9,7 +9,6 @@
 from Bio.Seq import Seq
 from Bio.SeqFeature import SeqFeature, FeatureLocation, CompoundLocation, AfterPosition, BeforePosition
 
-import bakta
 import bakta.config as cfg
 import bakta.constants as bc
 import bakta.features.annotation as ba
@@ -27,7 +26,7 @@ def build_biopython_sequence_list(data: dict, features: Sequence[dict]):
             sequence_features = [feat for feat in features if feat['sequence'] == seq['id']] if 'sequence' in features[0] else [feat for feat in features if feat['contig'] == seq['id']]  # <1.10.0 compatibility
         comment = (
             'Annotated with Bakta',
-            f"Software: v{bakta.__version__}\n",
+            f"Software: v{cfg.version}\n",
             f"Database: v{cfg.db_info['major']}.{cfg.db_info['minor']}, {cfg.db_info['type']}\n",
             f'DOI: {bc.BAKTA_DOI}\n',
             f'URL: {bc.BAKTA_URL}\n',
@@ -49,7 +48,7 @@ def build_biopython_sequence_list(data: dict, features: Sequence[dict]):
         sequence_annotations = {
             'molecule_type': 'DNA',
             'source': data['genome'].get('taxon', ''),
-            'date': date.today().strftime('%d-%b-%Y').upper(),
+            'date': cfg.run_end.strftime('%d-%b-%Y').upper(),
             'topology': seq['topology'],
             'data_file_division': 'HGT' if seq['type'] == bc.REPLICON_CONTIG else 'BCT',
             # 'accession': '*',  # hold back until EMBL output bug is fixed in BioPython (https://github.com/biopython/biopython/pull/3572)
@@ -140,7 +139,7 @@ def build_biopython_sequence_list(data: dict, features: Sequence[dict]):
                     else:
                         inference.append('ab initio prediction:Prodigal:2.6')
                 else:
-                    inference.append(f"ab initio prediction:Bakta:{'.'.join(bakta.__version__.split('.')[0:2])}")
+                    inference.append(f"ab initio prediction:Bakta:{'.'.join(cfg.version.split('.')[0:2])}")
                 if('ncbi_nrp_id' in feature.get('ups', {})):
                     nrp_id = feature['ups']['ncbi_nrp_id']
                     inference.append(f'similar to AA sequence:{bc.DB_XREF_REFSEQ_NRP}:{nrp_id}')

bakta/io/json.py

@@ -32,7 +32,7 @@ def write_json(data: dict, features: Sequence[dict], json_path: Path):
                 psc.pop('db_xrefs')
 
     version = OrderedDict()
-    version['bakta'] = bakta.__version__
+    version['bakta'] = cfg.version
     version['db'] = {
         'version': f"{cfg.db_info['major']}.{cfg.db_info['minor']}",
         'type': cfg.db_info['type']

bakta/io/tsv.py

@@ -22,7 +22,7 @@ def write_features(sequences: Sequence[dict], features_by_sequence: Dict[str, di
 
     with tsv_path.open('wt') as fh:
         fh.write('# Annotated with Bakta\n')
-        fh.write(f'# Software: v{bakta.__version__}\n')
+        fh.write(f'# Software: v{cfg.version}\n')
         fh.write(f"# Database: v{cfg.db_info['major']}.{cfg.db_info['minor']}, {cfg.db_info['type']}\n")
         fh.write(f'# DOI: {bc.BAKTA_DOI}\n')
         fh.write(f'# URL: {bc.BAKTA_URL}\n')
@@ -82,7 +82,7 @@ def write_feature_inferences(sequences: Sequence[dict], features_by_sequence: Di
 
     with tsv_path.open('wt') as fh:
         fh.write('# Annotated with Bakta\n')
-        fh.write(f'# Software: v{bakta.__version__}\n')
+        fh.write(f'# Software: v{cfg.version}\n')
         fh.write(f"# Database: v{cfg.db_info['major']}.{cfg.db_info['minor']}, {cfg.db_info['type']}\n")
         fh.write(f'# DOI: {bc.BAKTA_DOI}\n')
         fh.write(f'# URL: {bc.BAKTA_URL}\n')
@@ -150,7 +150,7 @@ def write_protein_features(features: Sequence[dict], header_columns: Sequence[st
     log.info('write protein feature tsv: path=%s', tsv_path)
 
     with tsv_path.open('wt') as fh:
-        fh.write(f'#Annotated with Bakta (v{bakta.__version__}): https://github.com/oschwengers/bakta\n')
+        fh.write(f'#Annotated with Bakta (v{cfg.version}): https://github.com/oschwengers/bakta\n')
         fh.write(f"#Database (v{cfg.db_info['major']}.{cfg.db_info['minor']}): https://doi.org/10.5281/zenodo.4247252\n")
         fh.write('\t'.join(header_columns))
         fh.write('\n')
@@ -166,7 +166,7 @@ def write_hypotheticals(hypotheticals: Sequence[dict], tsv_path: Path):
     log.info('write hypothetical tsv: path=%s', tsv_path)
 
     with tsv_path.open('wt') as fh:
-        fh.write(f'#Annotated with Bakta v{bakta.__version__}, https://github.com/oschwengers/bakta\n')
+        fh.write(f'#Annotated with Bakta v{cfg.version}, https://github.com/oschwengers/bakta\n')
         fh.write(f"#Database v{cfg.db_info['major']}.{cfg.db_info['minor']}, https://doi.org/10.5281/zenodo.4247252\n")
         fh.write('#Sequence Id\tStart\tStop\tStrand\tLocus Tag\tMol Weight [kDa]\tIso El. Point\tPfam hits\tDbxrefs\n')
         for hypo in hypotheticals:

bakta/json_io.py

@@ -38,7 +38,7 @@ def main():
     arg_group_general.add_argument('--verbose', '-v', action='store_true', help='Print verbose information')
     arg_group_general.add_argument('--debug', action='store_true', help='Run Bakta in debug mode. Temp data will not be removed.')
     arg_group_general.add_argument('--tmp-dir', action='store', default=None, dest='tmp_dir', help='Location for temporary files (default = system dependent auto detection)')
-    arg_group_general.add_argument('--version', '-V', action='version', version=f'%(prog)s {bakta.__version__}')
+    arg_group_general.add_argument('--version', '-V', action='version', version=f'%(prog)s {cfg.version}')
     args = parser.parse_args()
 
     ############################################################################
@@ -77,7 +77,7 @@ def main():
     log.info('verbose=%s', cfg.verbose)
 
     if(cfg.verbose):
-        print(f'Bakta v{bakta.__version__}')
+        print(f'Bakta v{cfg.version}')
         print('Options and arguments:')
         print(f'\tinput: {annotation_path}')
         print(f'\toutput: {cfg.output_path}')
@@ -103,6 +103,7 @@ def main():
         sequence_features.append(feature)
 
     # set global config objects based on information from imported JSON document
+    cfg.version = data['version']['bakta']
     cfg.db_info = {
         'type': data['version']['db']['type'],
         'major': data['version']['db']['version'].split('.')[0],
@@ -188,7 +189,7 @@ def main():
         fh_out.write(f"oriVs: {len([feat for feat in features if feat['type'] == bc.FEATURE_ORIV])}\n")
         fh_out.write(f"oriTs: {len([feat for feat in features if feat['type'] == bc.FEATURE_ORIT])}\n")
         fh_out.write('\nBakta:\n')
-        fh_out.write(f'Software: v{bakta.__version__}\n')
+        fh_out.write(f'Software: v{cfg.version}\n')
         fh_out.write(f"Database: v{cfg.db_info['major']}.{cfg.db_info['minor']}, {cfg.db_info['type']}\n")
         fh_out.write('DOI: 10.1099/mgen.0.000685\n')
         fh_out.write('URL: github.com/oschwengers/bakta\n')

bakta/main.py

@@ -58,7 +58,7 @@ def main():
     cfg.db_info = db.check(cfg.db_path)
     bu.test_dependencies()
     if(cfg.verbose):
-        print(f'Bakta v{bakta.__version__}')
+        print(f'Bakta v{cfg.version}')
         print('Options and arguments:')
         print(f'\tinput: {cfg.genome_path}')
         print(f"\tdb: {cfg.db_path}, version {cfg.db_info['major']}.{cfg.db_info['minor']}, {cfg.db_info['type']}")
@@ -614,7 +614,7 @@ def main():
         fh_out.write(f"oriVs: {len([feat for feat in features if feat['type'] == bc.FEATURE_ORIV])}\n")
         fh_out.write(f"oriTs: {len([feat for feat in features if feat['type'] == bc.FEATURE_ORIT])}\n")
         fh_out.write('\nBakta:\n')
-        fh_out.write(f'Software: v{bakta.__version__}\n')
+        fh_out.write(f'Software: v{cfg.version}\n')
         fh_out.write(f"Database: v{cfg.db_info['major']}.{cfg.db_info['minor']}, {cfg.db_info['type']}\n")
         fh_out.write('DOI: 10.1099/mgen.0.000685\n')
         fh_out.write('URL: github.com/oschwengers/bakta\n')

bakta/plot.py

@@ -99,7 +99,7 @@ def main():
     arg_group_general.add_argument('--verbose', '-v', action='store_true', help='Print verbose information')
     arg_group_general.add_argument('--debug', action='store_true', help='Run Bakta in debug mode. Temp data will not be removed.')
     arg_group_general.add_argument('--tmp-dir', action='store', default=None, dest='tmp_dir', help='Location for temporary files (default = system dependent auto detection)')
-    arg_group_general.add_argument('--version', action='version', version=f'%(prog)s {bakta.__version__}')
+    arg_group_general.add_argument('--version', action='version', version=f'%(prog)s {cfg.version}')
     args = parser.parse_args()
 
     ############################################################################
@@ -163,7 +163,7 @@ def main():
 
     bu.test_dependencies()
     if(cfg.verbose):
-        print(f'Bakta v{bakta.__version__}')
+        print(f'Bakta v{cfg.version}')
         print('Options and arguments:')
         print(f'\tinput: {annotation_path}')
         if(args.config): print(f'\tconfig: {args.config}')

bakta/proteins.py

@@ -51,7 +51,7 @@ def main():
     arg_group_general.add_argument('--debug', action='store_true', help='Run Bakta in debug mode. Temp data will not be removed.')
     arg_group_general.add_argument('--threads', '-t', action='store', type=int, default=0, help='Number of threads to use (default = number of available CPUs)')
     arg_group_general.add_argument('--tmp-dir', action='store', default=None, dest='tmp_dir', help='Location for temporary files (default = system dependent auto detection)')
-    arg_group_general.add_argument('--version', '-V', action='version', version=f'%(prog)s {bakta.__version__}')
+    arg_group_general.add_argument('--version', '-V', action='version', version=f'%(prog)s {cfg.version}')
     args = parser.parse_args()
 
     ############################################################################
@@ -108,7 +108,7 @@ def main():
 
     bu.test_dependencies()
     if(cfg.verbose):
-        print(f'Bakta v{bakta.__version__}')
+        print(f'Bakta v{cfg.version}')
         print('Options and arguments:')
         print(f'\tinput: {aa_path}')
         print(f"\tdb: {cfg.db_path}, version {cfg.db_info['major']}.{cfg.db_info['minor']}")

bakta/utils.py

@@ -54,7 +54,7 @@ def init_parser(sub_command: str=''):
     parser = argparse.ArgumentParser(
         prog=f'bakta{sub_command}',
         description='Rapid & standardized annotation of bacterial genomes, MAGs & plasmids',
-        epilog=f'Version: {bakta.__version__}\nDOI: {bc.BAKTA_DOI}\nURL: github.com/oschwengers/bakta\n\nCitation:\n{bc.BAKTA_CITATION}',
+        epilog=f'Version: {cfg.version}\nDOI: {bc.BAKTA_DOI}\nURL: github.com/oschwengers/bakta\n\nCitation:\n{bc.BAKTA_CITATION}',
         formatter_class=argparse.RawDescriptionHelpFormatter,
         add_help=False
     )
@@ -115,7 +115,7 @@ def parse_arguments():
     arg_group_general.add_argument('--debug', action='store_true', help='Run Bakta in debug mode. Temp data will not be removed.')
     arg_group_general.add_argument('--threads', '-t', action='store', type=int, default=0, help='Number of threads to use (default = number of available CPUs)')
     arg_group_general.add_argument('--tmp-dir', action='store', default=None, dest='tmp_dir', help='Location for temporary files (default = system dependent auto detection)')
-    arg_group_general.add_argument('--version', action='version', version=f'%(prog)s {bakta.__version__}')
+    arg_group_general.add_argument('--version', action='version', version=f'%(prog)s {cfg.version}')
     return parser.parse_args()
 
 
@@ -127,7 +127,7 @@ def setup_logger(output_path: Path, prefix: str, args: Namespace):
         datefmt='%H:%M:%S',
         level=logging.DEBUG if args.debug else logging.INFO
     )
-    log.info('version=%s', bakta.__version__)
+    log.info('version=%s', cfg.version)
     log.info('developer: Oliver Schwengers, github.com/oschwengers')
     log.info('command: %s', ' '.join(sys.argv))
     log.info('local time: %s', datetime.now().strftime('%Y-%m-%d %H:%M:%S'))