def test_datapackage_declare(self):
from tempfile import NamedTemporaryFile
import datapackage
from os import unlink
doc = MetatabDoc(test_data('datapackage_ex2.csv'))
d = doc.as_dict()
f = open('/tmp/package.json', 'w') # NamedTemporaryFile(delete=False)
f.write(json.dumps(d, indent=4))
f.close()
try:
dp = datapackage.DataPackage(f.name)
dp.validate()
except:
with open(f.name) as f2:
print(f2.read())
raise
print(f.name)
# unlink(f.name)
doc = MetatabDoc(test_data('example1.csv'))
from metatab.datapackage import convert_to_datapackage
print(json.dumps(convert_to_datapackage(doc), indent=4))
def test_datapackage_convert(self):
import datapackage
from metatab.datapackage import convert_to_datapackage
doc = MetatabDoc(test_data('example1.csv'))
dp = convert_to_datapackage(doc)
print(json.dumps(dp, indent=4))
dp = datapackage.DataPackage(dp)
dp.validate()
def _write_dpj(self):
from metatab.datapackage import convert_to_datapackage
from metatab import ConversionError
try:
dpj = convert_to_datapackage(self._doc)
except ConversionError as e:
self.warn(
("Error while writing datapackage.json. Skipping: " + str(e)))
return
self.zf.writestr(self.package_name + '/datapackage.json',
json.dumps(dpj, indent=4))
def metatab_build_handler(m):
if m.args.create is not False:
template = m.args.create if m.args.create else 'metatab'
if not exists(m.mt_file):
doc = make_metatab_file(template)
doc['Root']['Identifier'] = six.text_type(uuid4())
doc['Root']['Created'] = datetime_now()
write_doc(doc, m.mt_file)
prt('Created', m.mt_file)
else:
err('File', m.mt_file, 'already exists')
if m.args.add:
update_name(m.mt_file, fail_on_missing=False, report_unchanged=False)
add_resource(m.mt_file, m.args.add, cache=m.cache)
if False: # m.args.resources:
update_name(m.mt_file, fail_on_missing=False, report_unchanged=False)
doc = MetatabDoc(m.mt_file)
try:
doc['Schema'].clean()
except KeyError:
pass
for t in list(doc['Resources']): # w/o list(), will iterate over new terms
if not t.term_is('root.datafile'):
continue
if t.as_dict().get('url'):
add_resource(doc, t.as_dict()['url'], m.cache)
else:
warn("Entry '{}' on row {} is missing a url; skipping".format(t.join, t.row))
write_doc(doc, m.mt_file)
if m.args.schemas:
update_name(m.mt_file, fail_on_missing=False, report_unchanged=False)
process_schemas(m.mt_file, cache=m.cache, clean=m.args.clean)
if m.args.datapackage:
update_name(m.mt_file, fail_on_missing=False, report_unchanged=False)
from metatab.datapackage import convert_to_datapackage
doc = MetatabDoc(m.mt_file)
u = Url(m.mt_file)
if u.proto == 'file':
dpj_file = join(dirname(abspath(u.parts.path)), 'datapackage.json')
else:
dpj_file = join(getcwd(), 'datapackage.json')
try:
with open(dpj_file, 'w') as f:
f.write(json.dumps(convert_to_datapackage(doc), indent=4))
except ConversionError as e:
err(e)
if m.mtfile_url.scheme == 'file' and m.args.update:
update_name(m.mt_file, fail_on_missing=True, force=m.args.force)
def _write_dpj(self):
with open(join(self.package_path.path, 'datapackage.json'),
'w',
encoding="utf-8") as f:
f.write(json.dumps(convert_to_datapackage(self._doc), indent=4))
def _write_dpj(self):
with open(join(self.package_dir, 'datapackage.json'), 'w') as f:
f.write(json.dumps(convert_to_datapackage(self._doc), indent=4))
def _write_dpj(self):
self.write_to_s3(
'datapackage.json',
json.dumps(convert_to_datapackage(self._doc), indent=4))