def test_rna_fasta_format_id_starts_with_space(self):
filepath = self.get_data_path(
'dna-sequences-id-starts-with-space.fasta')
format = RNAFASTAFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError, '1 starts with a space'):
format.validate()
def test_rna_fasta_format_consecutive_IDs(self):
filepath = self.get_data_path('dna-sequences-consecutive-ids.fasta')
format = RNAFASTAFormat(filepath, mode='r')
with self.assertRaisesRegex(
ValidationError, 'consecutive descriptions.*1'):
format.validate()
def test_rna_fasta_format_invalid_characters(self):
filepath = self.get_data_path('not-rna-sequences.fasta')
format = RNAFASTAFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError, "Invalid character '1' "
".*0 on line 2"):
format.validate()
def test_rna_fasta_format_empty_file(self):
filepath = os.path.join(self.temp_dir.name, 'empty')
with open(filepath, 'w') as fh:
fh.write('\n')
format = RNAFASTAFormat(filepath, mode='r')
format.validate()
def test_cull_seqs_rna_default_params(self):
# Test default params work with RNA seqs as input
rna_path = self.get_data_path('cleanseq-test-1-rna.fasta')
rna_seqs = RNAFASTAFormat(rna_path, mode='r').view(DNAIterator)
obs = cull_seqs(rna_seqs)
obs_ids = {seq.metadata['id'] for seq in obs.view(DNAIterator)}
exp_ids = {'Ambig2', 'cleanseq'}
self.assertEqual(obs_ids, exp_ids)
def get_silva_data(ctx,
version='138.1',
target='SSURef_NR99',
include_species_labels=False,
rank_propagation=True,
ranks=None,
download_sequences=True):
# download data from SILVA
print('Downloading raw files may take some time... get some coffee.')
queries = _assemble_silva_data_urls(version, target, download_sequences)
results = _retrieve_data_from_silva(queries)
# parse taxonomy
parse_taxonomy = ctx.get_action('rescript', 'parse_silva_taxonomy')
taxonomy, = parse_taxonomy(taxonomy_tree=results['taxonomy tree'],
taxonomy_map=results['taxonomy map'],
taxonomy_ranks=results['taxonomy ranks'],
include_species_labels=include_species_labels,
ranks=ranks,
rank_propagation=rank_propagation)
# if skipping sequences, need to output an empty sequence file.
if not download_sequences:
results['sequences'] = qiime2.Artifact.import_data(
'FeatureData[RNASequence]', RNAFASTAFormat())
return results['sequences'], taxonomy
def test_rna_fasta_format_no_id(self):
filepath = self.get_data_path('dna-sequences-no-id.fasta')
format = RNAFASTAFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError, '1.*missing an ID'):
format.validate()
def test_rna_fasta_format_duplicate_ids(self):
filepath = self.get_data_path('rna-sequences-with-duplicate-ids.fasta')
format = RNAFASTAFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError, '6.*duplicate.*1'):
format.validate()
def test_rna_fasta_format_bom_fails(self):
filepath = self.get_data_path('dna-with-bom-fails.fasta')
format = RNAFASTAFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError, 'First line'):
format.validate()
def test_rna_fasta_format_corrupt_characters(self):
filepath = self.get_data_path('dna-sequences-corrupt-characters.fasta')
format = RNAFASTAFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError, 'utf-8.*2'):
format.validate()
def test_rna_fasta_format_missing_initial_ID(self):
filepath = self.get_data_path('dna-sequences-first-line-not-id.fasta')
format = RNAFASTAFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError, 'First line'):
format.validate()
def test_rna_fasta_format_validate_negative(self):
filepath = self.get_data_path('not-rna-sequences')
format = RNAFASTAFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError, 'RNAFASTA'):
format.validate()
def test_rna_fasta_format_bom_passes(self):
filepath = self.get_data_path('rna-with-bom-passes.fasta')
format = RNAFASTAFormat(filepath, mode='r')
format.validate()
def test_rna_fasta_format_validate_positive(self):
filepath = self.get_data_path('rna-sequences.fasta')
format = RNAFASTAFormat(filepath, mode='r')
format.validate()
