def test_cat_files(self):
'''test cat_files'''
infiles = [
os.path.join(data_dir, 'test_common_cat_files.in.1'),
os.path.join(data_dir, 'test_common_cat_files.in.2'),
os.path.join(data_dir, 'test_common_cat_files.in.3'),
]
tmp_out = 'tmp.test.common_cat_files.out'
expected = os.path.join(data_dir, 'test_common_cat_files.out')
common.cat_files(infiles, tmp_out)
self.assertTrue(filecmp.cmp(expected, tmp_out, shallow=False))
os.unlink(tmp_out)
def test_cat_files(self):
'''test cat_files'''
infiles = [
os.path.join(data_dir, 'test_common_cat_files.in.1'),
os.path.join(data_dir, 'test_common_cat_files.in.2'),
os.path.join(data_dir, 'test_common_cat_files.in.3'),
]
tmp_out = 'tmp.test.common_cat_files.out'
expected = os.path.join(data_dir, 'test_common_cat_files.out')
common.cat_files(infiles, tmp_out)
self.assertTrue(filecmp.cmp(expected, tmp_out, shallow=False))
os.unlink(tmp_out)
def _run(self):
cwd = os.getcwd()
try:
os.chdir(self.outdir)
self.write_versions_file(cwd)
self._map_and_cluster_reads()
self.log_files = None
if len(self.cluster_to_dir) > 0:
got_insert_data_ok = self._set_insert_size_data()
if not got_insert_data_ok:
print('WARNING: not enough proper read pairs (found ' +
str(self.proper_pairs) +
') to determine insert size.',
file=sys.stderr)
print(
'This probably means that very few reads were mapped at all. No local assemblies will be run',
file=sys.stderr)
if self.verbose:
print(
'Not enough proper read pairs mapped to determine insert size. Skipping all assemblies.',
flush=True)
else:
if self.verbose:
print('{:_^79}'.format(' Assembling each cluster '))
print('Will run',
self.threads,
'cluster(s) in parallel',
flush=True)
self._init_and_run_clusters()
if self.verbose:
print('Finished assembling clusters\n')
else:
if self.verbose:
print('No reads mapped. Skipping all assemblies',
flush=True)
print(
'WARNING: no reads mapped to reference genes. Therefore no local assemblies will be run',
file=sys.stderr)
if not self.clusters_all_ran_ok:
raise Error('At least one cluster failed! Stopping...')
if self.verbose:
print('{:_^79}'.format(' Writing reports '), flush=True)
print('Making', self.report_file_all_tsv)
self._write_report(self.clusters, self.report_file_all_tsv)
if self.verbose:
print('Making', self.report_file_filtered)
rf = report_filter.ReportFilter(infile=self.report_file_all_tsv)
rf.run(self.report_file_filtered)
if self.verbose:
print()
print(
'{:_^79}'.format(' Writing fasta of assembled sequences '),
flush=True)
print(self.catted_assembled_seqs_fasta,
'and',
self.catted_genes_matching_refs_fasta,
flush=True)
self._write_catted_assembled_seqs_fasta(
self.catted_assembled_seqs_fasta)
self._write_catted_genes_matching_refs_fasta(
self.catted_genes_matching_refs_fasta)
self._write_catted_assemblies_fasta(self.catted_assemblies_fasta)
if self.log_files is not None:
clusters_log_file = os.path.join(self.outdir,
'log.clusters.gz')
if self.verbose:
print()
print('{:_^79}'.format(' Catting cluster log files '),
flush=True)
print('Writing file', clusters_log_file, flush=True)
common.cat_files(self.log_files, clusters_log_file)
if self.verbose:
print()
print('{:_^79}'.format(' Cleaning files '), flush=True)
self._clean()
Clusters._write_mlst_reports(self.mlst_profile_file,
self.report_file_filtered,
self.mlst_reports_prefix,
verbose=self.verbose)
if self.clusters_all_ran_ok and self.verbose:
print('\nAll done!\n')
finally:
os.chdir(cwd)
def _run(self):
cwd = os.getcwd()
os.chdir(self.outdir)
self.write_versions_file(cwd)
self._map_and_cluster_reads()
self.log_files = None
if len(self.cluster_to_dir) > 0:
got_insert_data_ok = self._set_insert_size_data()
if not got_insert_data_ok:
print('WARNING: not enough proper read pairs (found ' + str(self.proper_pairs) + ') to determine insert size.', file=sys.stderr)
print('This probably means that very few reads were mapped at all. No local assemblies will be run', file=sys.stderr)
if self.verbose:
print('Not enough proper read pairs mapped to determine insert size. Skipping all assemblies.', flush=True)
else:
if self.verbose:
print('{:_^79}'.format(' Assembling each cluster '))
print('Will run', self.threads, 'cluster(s) in parallel', flush=True)
self._init_and_run_clusters()
if self.verbose:
print('Finished assembling clusters\n')
else:
if self.verbose:
print('No reads mapped. Skipping all assemblies', flush=True)
print('WARNING: no reads mapped to reference genes. Therefore no local assemblies will be run', file=sys.stderr)
if not self.clusters_all_ran_ok:
raise Error('At least one cluster failed! Stopping...')
if self.verbose:
print('{:_^79}'.format(' Writing reports '), flush=True)
print('Making', self.report_file_all_tsv)
self._write_report(self.clusters, self.report_file_all_tsv)
if self.verbose:
print('Making', self.report_file_filtered)
rf = report_filter.ReportFilter(infile=self.report_file_all_tsv)
rf.run(self.report_file_filtered)
if self.verbose:
print()
print('{:_^79}'.format(' Writing fasta of assembled sequences '), flush=True)
print(self.catted_assembled_seqs_fasta, 'and', self.catted_genes_matching_refs_fasta, flush=True)
self._write_catted_assembled_seqs_fasta(self.catted_assembled_seqs_fasta)
self._write_catted_genes_matching_refs_fasta(self.catted_genes_matching_refs_fasta)
self._write_catted_assemblies_fasta(self.catted_assemblies_fasta)
if self.log_files is not None:
clusters_log_file = os.path.join(self.outdir, 'log.clusters.gz')
if self.verbose:
print()
print('{:_^79}'.format(' Catting cluster log files '), flush=True)
print('Writing file', clusters_log_file, flush=True)
common.cat_files(self.log_files, clusters_log_file)
if self.verbose:
print()
print('{:_^79}'.format(' Cleaning files '), flush=True)
self._clean()
Clusters._write_mlst_reports(self.mlst_profile_file, self.report_file_filtered, self.mlst_reports_prefix, verbose=self.verbose)
if self.clusters_all_ran_ok and self.verbose:
print('\nAll done!\n')
os.chdir(cwd)