def test_check(capsys, api_copy):
commands.check(_args(api_copy, 'refs'))
args = _args(api_copy)
commands.check(args)
assert 'family' in capsys.readouterr()[0]
msgs = [a[0] for a, _ in args.log.error.call_args_list]
assert all('unregistered glottocode' in m for m in msgs)
assert len(msgs) == 5
copytree(api_copy.tree / 'abcd1234' / 'abcd1235',
api_copy.tree / 'abcd1235')
args = _args(api_copy)
commands.check(args)
msgs = [a[0] for a, _ in args.log.error.call_args_list]
assert any('duplicate glottocode' in m for m in msgs)
assert len(msgs) == 7
(api_copy.tree / 'abcd1235').rename(api_copy.tree / 'abcd1237')
args = _args(api_copy)
commands.check(args)
msgs = [a[0] for a, _ in args.log.error.call_args_list]
assert any('duplicate hid' in m for m in msgs)
assert len(msgs) == 9
def _do_test(config_files, inspector=None):
config = TEST_CASE.make_cfg([config_path(cf).as_posix() for cf in config_files])
xml = beastling.beastxml.BeastXml(config)
temp_filename = TEST_CASE.tmp_path('test').as_posix()
xml.write_file(temp_filename)
if os.environ.get('TRAVIS'):
et.parse(temp_filename)
else:
if not TEST_CASE.tmp_path('tests').exists():
copytree(tests_path(), TEST_CASE.tmp_path('tests'))
try:
if config_files in skip:
raise SkipTest
check_call(
['beast', '-java', '-overwrite', temp_filename],
cwd=TEST_CASE.tmp.as_posix(),
stdout=PIPE,
stderr=PIPE)
except CalledProcessError as e:
raise AssertionError(
"Beast run on {:} returned non-zero exit status "
"{:d}".format(
config_files, e.returncode))
if inspector:
inspector(TEST_CASE.tmp)
def test_Manifest(tmppath):
d = Path(__file__).parent
m = {k: v for k, v in Manifest.from_dir(d).items()}
copytree(d, tmppath / 'd')
assert m == Manifest.from_dir(tmppath / 'd')
copytree(d, tmppath / 'd' / 'd')
assert m != Manifest.from_dir(tmppath / 'd')
def test_copytree(self):
from clldutils.path import copytree
dst = self.tmp_path('a', 'b')
copytree(self.tmp_path(), dst)
self.assertTrue(dst.exists())
self.assertRaises(OSError, copytree, dst, dst)
def test_check(capsys, _main, mocker, api_copy):
_main('check --bib-only')
log = mocker.Mock()
_main('check --tree-only', log=log)
assert 'family' in capsys.readouterr()[0]
msgs = [a[0] for a, _ in log.error.call_args_list]
assert any('unregistered glottocode' in m for m in msgs)
assert any('missing reference' in m for m in msgs)
assert len(msgs) == 27
copytree(api_copy.tree / 'abcd1234' / 'abcd1235',
api_copy.tree / 'abcd1235')
log = mocker.Mock()
_main('check --tree-only', log=log)
msgs = [a[0] for a, _ in log.error.call_args_list]
assert any('duplicate glottocode' in m for m in msgs)
assert len(msgs) == 29
(api_copy.tree / 'abcd1235').rename(api_copy.tree / 'abcd1237')
log = mocker.Mock()
_main('check --tree-only', log=log)
msgs = [a[0] for a, _ in log.error.call_args_list]
assert any('duplicate hid' in m for m in msgs)
assert len(msgs) >= 9
def repos(tmppath, git_repo_factory):
repos = tmppath / 'lexibank-data'
copytree(Path(__file__).parent.joinpath('repos'), repos)
git_repo_factory(repos)
git_repo_factory(repos / 'datasets' / 'test_dataset')
git_repo_factory(repos / 'datasets' / 'test_dataset_cldf')
copy(Path(pylexibank.__file__).parent.joinpath('cldf-metadata.json'), repos)
yield repos
def test_copytree(tmppath):
from clldutils.path import copytree
dst = tmppath / 'a' / 'b'
copytree(tmppath, dst)
assert dst.exists()
with pytest.raises(OSError):
copytree(dst, dst)
def abvd_dataset(repos, tmpdir, glottolog, concepticon):
copytree(repos / 'datasets' / 'abvd', str(tmpdir.join('abvd')))
class Dataset(abvd.BVD):
id = 'x'
SECTION = 'y'
dir = Path(str(tmpdir.join('abvd')))
return Dataset(glottolog=glottolog, concepticon=concepticon)
def abvd_dataset(repos, tmp_path, glottolog, concepticon):
copytree(repos / 'datasets' / 'abvd', tmp_path / 'abvd')
class Dataset(abvd.BVD):
id = 'x'
SECTION = 'y'
dir = tmp_path / 'abvd'
return Dataset(glottolog=glottolog, concepticon=concepticon)
def sndcmp2_dataset(repos, tmpdir, glottolog, concepticon):
copytree(repos / 'datasets' / 'sndcmp', str(tmpdir.join('sndcmp')))
class Dataset(SNDCMP):
dir = str(tmpdir.join('sndcmp'))
id = "sndcmpvanuatu"
study_name = "Vanuatu"
source_id_array = ["Shimelman2019"]
create_cognates = False
return Dataset()
def setUp(self):
WithTempDir.setUp(self)
self.repos = self.tmp_path()
self.languoids = self.tmp_path('languoids')
copytree(Path(__file__).parent.joinpath('data', 'languoids'), self.languoids)
self.tree = self.languoids.joinpath('tree')
self.references = self.tmp_path('references')
copytree(Path(__file__).parent.joinpath('data', 'references'), self.references)
self.tmp_path('build').mkdir()
def sndcmp_dl_dataset(repos, tmpdir, glottolog, concepticon):
copytree(repos / 'datasets' / 'sndcmp', str(tmpdir.join('sndcmp')))
class Dataset(SNDCMP):
dir = str(tmpdir.join('sndcmp'))
id = "sndcmpbrazil"
study_name = "Brazil"
second_gloss_lang = None
source_id_array = ["xy"]
create_cognates = False
return Dataset()
def recode(args):
"""Assign a new glottocode to an existing languoid.
glottolog recode <code>
"""
lang = find_languoid(glottocode=args.args[0])
if not lang:
raise ParserError('languoid not found')
lang.id = Glottocode.from_name(lang.name)
new_dir = lang.dir.parent.joinpath(lang.id)
copytree(lang.dir, new_dir)
lang.write_info(new_dir)
remove(new_dir.joinpath('%s.ini' % args.args[0]))
rmtree(lang.dir)
print("%s -> %s" % (args.args[0], lang.id))
def recode(args):
"""Assign a new glottocode to an existing languoid.
glottolog recode <code>
"""
lang = args.repos.languoid(args.args[0])
if not lang:
raise ParserError('languoid not found')
lang.id = Glottocode.from_name(lang.name)
new_dir = lang.dir.parent.joinpath(lang.id)
copytree(lang.dir, new_dir)
lang.write_info(new_dir)
remove(new_dir.joinpath('%s.ini' % args.args[0]))
rmtree(lang.dir)
print("%s -> %s" % (args.args[0], lang.id))
def setUp(self):
WithTempDir.setUp(self)
self.repos = self.tmp_path()
self.languoids = self.tmp_path('languoids')
copytree(
Path(__file__).parent.joinpath('data', 'languoids'),
self.languoids)
self.tree = self.languoids.joinpath('tree')
self.references = self.tmp_path('references')
copytree(
Path(__file__).parent.joinpath('data', 'references'),
self.references)
self.tmp_path('build').mkdir()
def test_check(self):
from pyglottolog.commands import check
with capture(check, self._args('refs')):
pass
with capture(check, self._args()) as out:
self.assertIn('family', out)
for call in self.log.error.call_args_list:
self.assertIn('unregistered glottocode', call[0][0])
self.assertEqual(self.log.error.call_count, 4)
copytree(self.api.tree.joinpath('abcd1234', 'abcd1235'),
self.api.tree.joinpath('abcd1235'))
with capture(check, self._args()):
self.assertIn(
'duplicate glottocode',
''.join(c[0][0] for c in self.log.error.call_args_list))
self.assertEqual(self.log.error.call_count, 6)
def sndcmp_dataset(repos, tmpdir, glottolog, concepticon):
copytree(repos / 'datasets' / 'sndcmp', str(tmpdir.join('sndcmp')))
class CustomConcept(SNDCMPConcept):
Bislama_Gloss = attr.ib(default=None)
class Dataset(SNDCMP):
dir = str(tmpdir.join('sndcmp'))
id = "sndcmpvanuatu"
study_name = "Vanuatu"
second_gloss_lang = "Bislama"
source_id_array = ["Shimelman2019"]
create_cognates = True
concept_class = CustomConcept
form_placeholder = 'P'
only_proto_forms = True
def get_source_id_array(self, lexeme):
return ['ab']
return Dataset()
def lff2tree(tree=TREE, outdir=None, test=False):
"""
- get mapping glottocode -> Languoid from old tree
- assemble new directory tree
- for each path component in lff/dff:
- create new dir
- copy info file from old tree (possibly updating the name) or
- create info file
- for each language/dialect in lff/dff:
- create new dir
- copy info file from old tree (possibly updating the name) or
- create info file
- rm old tree
- copy new tree
"""
out = Path(outdir or build_path('tree'))
if not out.parent.exists():
out.parent.mkdir()
if out.exists():
rmtree(out)
out.mkdir()
old_tree = {l.id: l for l in walk_tree(tree)} if tree else {}
languages = {}
for lang in read_lff('language'):
languages[lang.id] = lang
lang2tree(lang, lang.lineage, out, old_tree)
for lang in read_lff('dialect'):
if not lang.lineage or lang.lineage[0][1] not in languages:
raise ValueError('unattached dialect')
lang2tree(
lang, languages[lang.lineage[0][1]].lineage + lang.lineage, out, old_tree)
if not test:
rmtree(TREE, ignore_errors=True)
copytree(out, TREE)
def api_copy(tmpdir, repos_path):
"""Glottolog instance from isolated directory copy."""
repos_copy = str(tmpdir / 'repos')
path.copytree(str(repos_path), repos_copy)
return pyglottolog.Glottolog(repos_copy)
def setUp(self):
WithTempDir.setUp(self)
self.repos = self.tmp_path('repos')
copytree(Path(__file__).parent.joinpath('data'), self.repos)
self.api = Glottolog(self.repos)
def sndcmp_dir(tmp_path, repos):
copytree(repos / 'datasets' / 'sndcmp', tmp_path / 'sndcmp')
return tmp_path / 'sndcmp'
def repos(tmpd):
repos = tmpd / 'lexibank-data'
copytree(Path(__file__).parent.joinpath('repos'), repos)
copy(
Path(pylexibank.__file__).parent.joinpath('cldf-metadata.json'), repos)
yield repos
def bibfiles_copy(tmpdir, references_path):
references_copy = tmpdir / 'references'
path.copytree(str(references_path), str(references_copy))
return pyglottolog.references.BibFiles.from_path(str(references_copy))
def test_dataset(tmppath):
copytree(
Path(__file__).parent / 'repo_data' / 'test_dataset',
tmppath / 'test_dataset')
return tmppath / 'test_dataset' / 'td.py'
