def test_convert_newlines_non_utf():
fname = get_test_fname("dosimzml")
rval = convert_newlines(fname,
tmp_prefix="gxtest",
tmp_dir=tempfile.gettempdir(),
in_place=False)
new_file = rval[1]
assert open(new_file, "rb").read() == open(get_test_fname("1imzml"),
"rb").read()
def test_sniff_compressed_dynamic_datatypes_default_on():
# With auto sniffing on, verify the sniffers work and the files match what is expected
# when coming from guess_ext.
datatypes_registry = example_datatype_registry_for_sample(sniff_compressed_dynamic_datatypes_default=True)
fastqsangergz_datatype = datatypes_registry.get_datatype_by_extension('fastqsanger.gz')
fname = sniff.get_test_fname('1.fastqsanger.gz')
assert fastqsangergz_datatype.sniff(fname)
sniff_order = datatypes_registry.sniff_order
fname = sniff.get_test_fname('1.fastqsanger.gz')
assert sniff.guess_ext(fname, sniff_order) == 'fastqsanger.gz'
fname = sniff.get_test_fname('1.fastqsanger.bz2')
assert sniff.guess_ext(fname, sniff_order) == 'fastqsanger.bz2'
def test_sniff_compressed_dynamic_datatypes_default_off():
# Redo last tests with auto compressed sniffing disabled and they should not longer result from guess_ext.
datatypes_registry = example_datatype_registry_for_sample(sniff_compressed_dynamic_datatypes_default=False)
# sniffer still returns True for these files...
fastqsangergz_datatype = datatypes_registry.get_datatype_by_extension('fastqsanger.gz')
fname = sniff.get_test_fname('1.fastqsanger.gz')
assert fastqsangergz_datatype.sniff(fname)
# but they don't report as matching the specified sniff_order.
sniff_order = datatypes_registry.sniff_order
fname = sniff.get_test_fname('1.fastqsanger.gz')
assert 'fastq' not in sniff.guess_ext(fname, sniff_order)
fname = sniff.get_test_fname('1.fastqsanger.bz2')
assert 'fastq' not in sniff.guess_ext(fname, sniff_order)
def test_sniff_compressed_dynamic_datatypes_default_on():
# With auto sniffing on, verify the sniffers work and the files match what is expected
# when coming from guess_ext.
datatypes_registry = example_datatype_registry_for_sample(
sniff_compressed_dynamic_datatypes_default=True)
fastqsangergz_datatype = datatypes_registry.get_datatype_by_extension(
'fastqsanger.gz')
fname = sniff.get_test_fname('1.fastqsanger.gz')
assert fastqsangergz_datatype.sniff(fname)
sniff_order = datatypes_registry.sniff_order
fname = sniff.get_test_fname('1.fastqsanger.gz')
assert sniff.guess_ext(fname, sniff_order) == 'fastqsanger.gz'
fname = sniff.get_test_fname('1.fastqsanger.bz2')
assert sniff.guess_ext(fname, sniff_order) == 'fastqsanger.bz2'
def test_sniff_compressed_dynamic_datatypes_default_off():
# Redo last tests with auto compressed sniffing disabled and they should not longer result from guess_ext.
datatypes_registry = example_datatype_registry_for_sample(
sniff_compressed_dynamic_datatypes_default=False)
# sniffer still returns True for these files...
fastqsangergz_datatype = datatypes_registry.get_datatype_by_extension(
'fastqsanger.gz')
fname = sniff.get_test_fname('1.fastqsanger.gz')
assert fastqsangergz_datatype.sniff(fname)
# but they don't report as matching the specified sniff_order.
sniff_order = datatypes_registry.sniff_order
fname = sniff.get_test_fname('1.fastqsanger.gz')
assert 'fastq' not in sniff.guess_ext(fname, sniff_order)
fname = sniff.get_test_fname('1.fastqsanger.bz2')
assert 'fastq' not in sniff.guess_ext(fname, sniff_order)
def assert_converts_to_1234_convert(content, block_size=1024):
fname = get_test_fname('temp2.txt')
with open(fname, 'w') as fh:
fh.write(content)
rval = convert_newlines(fname,
tmp_prefix="gxtest",
tmp_dir=tempfile.gettempdir(),
block_size=block_size)
actual_contents = open(fname).read()
assert '1 2\n3 4\n' == actual_contents, actual_contents
assert rval == (2, None), "rval != %s for %s" % (rval, content)
def get_input_files(*args):
temp_dir = tempfile.mkdtemp()
test_files = []
try:
for filename in args:
shutil.copy(get_test_fname(filename), temp_dir)
test_files.append(os.path.join(temp_dir, filename))
md5_sums = [md5_hash_file(f) for f in test_files]
yield test_files
new_md5_sums = [md5_hash_file(f) for f in test_files]
for old_hash, new_hash, f in zip(md5_sums, new_md5_sums, test_files):
assert old_hash == new_hash, 'Unexpected change of content for file %s' % f
finally:
shutil.rmtree(temp_dir, ignore_errors=True)
def get_input_files(*args):
temp_dir = tempfile.mkdtemp()
test_files = []
try:
for filename in args:
shutil.copy(get_test_fname(filename), temp_dir)
test_files.append(os.path.join(temp_dir, filename))
md5_sums = [md5_hash_file(f) for f in test_files]
yield test_files
new_md5_sums = [md5_hash_file(f) for f in test_files]
for old_hash, new_hash, f in zip(md5_sums, new_md5_sums, test_files):
assert old_hash == new_hash, 'Unexpected change of content for file %s' % f
finally:
shutil.rmtree(temp_dir, ignore_errors=True)
if line.lstrip().startswith('</cml>'):
continue
if line.lstrip().startswith('<molecule'):
molecule_found = True
if molecule_found:
out.write(line)
out.write("</cml>\n")
merge = staticmethod(merge)
if __name__ == '__main__':
"""
TODO: We need to figure out, how to put example files under /lib/galaxy/datatypes/test/ from a toolshed, so that doctest can work properly.
"""
inchi = get_test_fname('drugbank_drugs.inchi')
smiles = get_test_fname('drugbank_drugs.smi')
sdf = get_test_fname('drugbank_drugs.sdf')
fps = get_test_fname('50_chemfp_fingerprints_FPS1.fps')
pdb = get_test_fname('2zbz.pdb')
cml = get_test_fname('/home/bag/Downloads/approved.cml')
print 'CML test'
print CML().sniff(cml), 'cml'
print CML().sniff(inchi)
print CML().sniff(pdb)
CML().split()
"""
print 'SMILES test'
print SMILES().sniff(smiles), 'smi'
print SMILES().sniff(inchi)
# we found two required header lines, the next line should start with <molecule >
if line.lstrip().startswith('</cml>'):
continue
if line.lstrip().startswith('<molecule'):
molecule_found = True
if molecule_found:
out.write( line )
out.write("</cml>\n")
merge = staticmethod(merge)
if __name__ == '__main__':
"""
TODO: We need to figure out, how to put example files under /lib/galaxy/datatypes/test/ from a toolshed, so that doctest can work properly.
"""
inchi = get_test_fname('drugbank_drugs.inchi')
smiles = get_test_fname('drugbank_drugs.smi')
sdf = get_test_fname('drugbank_drugs.sdf')
fps = get_test_fname('50_chemfp_fingerprints_FPS1.fps')
pdb = get_test_fname('2zbz.pdb')
cml = get_test_fname('/home/bag/Downloads/approved.cml')
print 'CML test'
print CML().sniff(cml), 'cml'
print CML().sniff(inchi)
print CML().sniff(pdb)
CML().split()
"""
print 'SMILES test'
print SMILES().sniff(smiles), 'smi'
print SMILES().sniff(inchi)
def _run_validation(extension, file_name):
datatype = datatypes_registry.datatypes_by_extension[extension]
validation = validate(MockDataset(get_test_fname(file_name), datatype))
return validation
def _truncate(file_name, bytes=10):
o = tempfile.NamedTemporaryFile(delete=False)
with open(get_test_fname(file_name), "rb") as f:
contents = f.read()
o.write(contents[0:-bytes])
return o.name
