def test_dump(capsys, mocker, tmpdir):
tmpdir.join('data').mkdir()
dump(mocker.Mock(repos=CLTS(str(tmpdir))), test=True)
out, err = capsys.readouterr()
assert Path(str(tmpdir)).joinpath('data', 'graphemes.tsv').exists()
stats(mocker.Mock(repos=CLTS(str(tmpdir))))
out, err = capsys.readouterr()
assert 'Unique graphemes' in out
def main(args=None): # pragma: no cover
parser = ArgumentParserWithLogging('pyclts')
parser.add_argument(
"--repos",
default=CLTS(repos=Path(__file__).parent.parent.parent),
type=CLTS,
help="Path to clts repos.")
parser.add_argument("--format",
default="pipe",
help="Format of tabular output.")
parser.add_argument('--nonames',
help="do not report the sound names in the output",
action='store_true')
parser.add_argument('--filter',
help="only list generated sounds",
default='')
parser.add_argument('--data',
help="specify the transcription data you want to load",
default="phoible")
parser.add_argument(
'--system',
help="specify the transcription system you want to load",
default="bipa")
res = parser.main(args=args)
if args is None: # pragma: no cover
sys.exit(res)
def main(args): # pragma: no cover
data = Data()
clts_repos = Path(__file__).parent.parent.parent.parent.resolve() / 'clts-data'
clts_repos = CLTS(clts_repos)
print(clts_repos.repos)
version = 'v2.1.0' # assert_release(clts_repos.repos)
for rec in Database.from_file(args.cldf.bibpath, lowercase=True):
data.add(common.Source, rec.id, _obj=bibtex2source(rec))
dataset = common.Dataset(
id='clts',
name="CLTS {0}".format(version),
publisher_name="Max Planck Institute for Evolutionary Anthropology",
publisher_place="Leipzig",
publisher_url="http://www.eva.mpg.de",
license="http://creativecommons.org/licenses/by/4.0/",
contact='*****@*****.**',
domain='clts.clld.org',
jsondata={
'license_icon': 'cc-by.png',
'license_name': 'Creative Commons Attribution 4.0 International License'})
DBSession.add(dataset)
for i, name in enumerate([
'Johann-Mattis List',
'Cormac Anderson',
'Tiago Tresoldi',
'Robert Forkel',
]):
c = common.Contributor(id=slug(name), name=name)
dataset.editors.append(common.Editor(contributor=c, ord=i))
for line in args.cldf['data/features.tsv']:
data.add(
models.Feature,
line['ID'],
id=line['ID'],
name='{} {}: {}'.format(line['TYPE'], line['FEATURE'], line['VALUE']),
sound_type=line['TYPE'],
feature=line['FEATURE'],
value=line['VALUE'],
)
DBSession.add(models.SoundSegment(
id='NA',
name='<NA>',
description='<NA>',
type='marker',
generated=True,
unicode='',
color='#bbbbbb',
))
for line in args.cldf['data/sounds.tsv']:
s = data.add(
models.SoundSegment,
line['ID'],
id=line['ID'],
name=line['GRAPHEME'],
description=line['NAME'],
type=line['TYPE'],
generated=line['GENERATED'],
unicode=' / '.join(line['UNICODE']),
color=clts_repos.soundclass('color').resolve_sound(line['GRAPHEME']),
)
if s.color == '0':
s.color = '#bbbbbb'
assert s.color in LEGEND
DBSession.flush()
seen = set()
for line in args.cldf['data/sounds.tsv']:
for fid in line['FEATURES']:
spk, fpk = data['SoundSegment'][line['ID']].pk, data['Feature'][fid].pk
if (spk, fpk) not in seen:
DBSession.add(models.SoundSegmentFeature(soundsegment_pk=spk, feature_pk=fpk))
seen.add((spk, fpk))
english = data.add(
common.Language, 'eng',
id='eng',
name='English')
for line in args.cldf['sources/index.tsv']:
c = data.add(
models.Transcription,
line['NAME'],
id=line['NAME'],
name=line['NAME'],
description=line['DESCRIPTION'].replace(':bib:', '/sources/'),
datatype=getattr(models.Datatype, line['TYPE'])
)
for ref in line.get('REFS', []):
common.ContributionReference(source=data['Source'][ref], contribution=c)
sound_url_template = args.cldf['data/graphemes.tsv', 'SOUND'].valueUrl
image_url_template = args.cldf['data/graphemes.tsv', 'IMAGE'].valueUrl
for line in args.cldf['data/graphemes.tsv']:
key = line['DATASET'] + ':' + line['NAME'] + ':' + line['GRAPHEME']
if key not in data['Grapheme']:
sound_id = line['NAME'].replace(' ', '_')
vs = data['ValueSet'].get((line['DATASET'], line['NAME']))
if not vs:
try:
vs = data.add(
common.ValueSet,
(line['DATASET'], line['NAME']),
id=key,
description=line['NAME'],
language=english,
contribution=data['Transcription'][line['DATASET']],
parameter=data['SoundSegment'][sound_id]
)
except:
print(line)
raise
data.add(
models.Grapheme,
key,
id=key,
name=line['GRAPHEME'],
description=line['NAME'],
url=line['URL'].unsplit() if line['URL'] else None,
audio=sound_url_template.expand(line) if line['SOUND'] else None,
image=image_url_template.expand(line) if line['IMAGE'] else None,
valueset=vs
)
def test_make_app_data(capsys, mocker, tmpdir):
tmpdir.join('app').mkdir()
_make_app_data(mocker.Mock(repos=CLTS(str(tmpdir))), test=True)
assert Path(str(tmpdir)).joinpath('app', 'data.js').exists()
def test_stats(capsys, mocker, tmpdir):
dstats(mocker.Mock(system='bipa', repos=CLTS(str(tmpdir))))
out, err = capsys.readouterr()
assert 'id' in out
stats(mocker.Mock(system='bipa', repos=CLTS('.')))
def test_iter_sources(sources, tmpdir):
api = CLTS(repos=str(tmpdir))
srcs = list(api.iter_sources(type='td'))
assert len(srcs[0][1]) == 0
assert srcs[0][0]['NAME'] == 'test'