def test_validate_negative_missing_keys(self):
filepath = self.get_data_path('placements-missing.json')
fmt = PlacementsFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError,
'found.*placements.*tree'):
fmt.validate()
def test_placements_format_to_dict(self):
transformer = self.get_transformer(PlacementsFormat, dict)
fp = pathlib.Path(self.temp_dir.name) / pathlib.Path('placements.json')
fp.write_text('{"foo": 1}')
input_ = PlacementsFormat(str(fp), mode='r')
with self.assertRaisesRegex(ValidationError, r'found \[\'foo\'\]'):
# A bit of a cop-out, but this means we were able to parse the
# JSON document.
input_.validate(level='max')
obs = transformer(input_)
self.assertEqual(obs, {'foo': 1})
def sepp(representative_sequences: DNASequencesDirectoryFormat,
reference_database: SeppReferenceDirFmt,
alignment_subset_size: int = 1000,
placement_subset_size: int = 5000,
threads: int = 1,
debug: bool = False,
) -> (NewickFormat, PlacementsFormat):
placements = 'q2-fragment-insertion_placement.json'
tree = 'q2-fragment-insertion_placement.tog.relabelled.tre'
placements_result = PlacementsFormat()
tree_result = NewickFormat()
with tempfile.TemporaryDirectory() as tmp:
_run(str(representative_sequences.file.view(DNAFASTAFormat)),
str(threads), tmp,
str(alignment_subset_size), str(placement_subset_size),
str(reference_database.alignment.path_maker()),
str(reference_database.phylogeny.path_maker()),
str(reference_database.raxml_info.path_maker()),
debug)
outtree = os.path.join(tmp, tree)
outplacements = os.path.join(tmp, placements)
_add_missing_branch_length(outtree)
shutil.copyfile(outtree, str(tree_result))
shutil.copyfile(outplacements, str(placements_result))
return tree_result, placements_result
def sepp(
representative_sequences: DNASequencesDirectoryFormat,
threads: int = 1,
alignment_subset_size: int = 1000,
placement_subset_size: int = 5000,
reference_alignment: AlignedDNASequencesDirectoryFormat = None,
reference_phylogeny: NewickFormat = None,
debug: bool = False,
) -> (NewickFormat, PlacementsFormat):
_sanity()
# check if sequences and tips in reference match
if not _reference_matches(reference_alignment, reference_phylogeny):
raise ValueError(
('Reference alignment and phylogeny do not match up. Please ensure'
' that all sequences in the alignment correspond to exactly one '
'tip name in the phylogeny.'))
placements = 'q2-fragment-insertion_placement.json'
tree = 'q2-fragment-insertion_placement.tog.relabelled.tre'
placements_result = PlacementsFormat()
tree_result = NewickFormat()
with tempfile.TemporaryDirectory() as tmp:
_run(str(representative_sequences.file.view(DNAFASTAFormat)),
str(threads), tmp, str(alignment_subset_size),
str(placement_subset_size), reference_alignment,
reference_phylogeny, debug)
outtree = os.path.join(tmp, tree)
outplacements = os.path.join(tmp, placements)
_add_missing_branch_length(outtree)
shutil.copyfile(outtree, str(tree_result))
shutil.copyfile(outplacements, str(placements_result))
return tree_result, placements_result
def test_validate_negative_array(self):
filepath = self.get_data_path('root-array.json')
fmt = PlacementsFormat(filepath, mode='r')
with self.assertRaisesRegex(ValidationError, 'JSON object'):
fmt.validate()
def test_validate_positive(self):
filepath = self.get_data_path('placements.json')
fmt = PlacementsFormat(filepath, mode='r')
fmt.validate()
self.assertTrue(True)