def test_unique_constraint_violation():
schema = deepcopy(SCHEMA_CSV)
schema['fields'][0]['constraints'] = {'unique': True}
source = [
['id', 'age', 'name'],
[1, 39, 'Paul'],
[1, 36, 'Jane'],
]
table = Table(source, schema=schema)
with pytest.raises(exceptions.TableSchemaException) as excinfo:
table.read()
assert 'duplicates' in str(excinfo.value)
def test_unique_primary_key_violation():
schema = deepcopy(SCHEMA_CSV)
schema['primaryKey'] = 'id'
source = [
['id', 'age', 'name'],
[1, 39, 'Paul'],
[1, 36, 'Jane'],
]
table = Table(source, schema=schema)
with pytest.raises(exceptions.TableSchemaException) as excinfo:
table.read()
assert 'duplicates' in str(excinfo.value)
def test_read_invalid_col_value_handled():
# Test a schema-invalid column value in one row, handled
source = [
['key', 'value'],
['one', 'not_an_int'],
['two', 2],
]
table = Table(source, schema=SCHEMA_MIN)
errors = []
def handler(exc, row_number, row_data, error_data):
errors.append((exc, row_number, row_data, error_data))
actual = table.read(exc_handler=handler)
expect = [
['one', 'not_an_int'],
['two', 2],
]
assert actual == expect
assert isinstance(actual[0][1], FailedCast)
assert len(errors) == 1
expect_row_data = OrderedDict([('key', 'one'), ('value', 'not_an_int')])
expect_error_data = OrderedDict([('value', 'not_an_int')])
_check_error(errors[0],
expect_exc_class=exceptions.CastError,
expect_exc_str='There are 1 cast errors',
expect_row_number=2,
expect_row_data=expect_row_data,
expect_error_data=expect_error_data)
def test_read_single_field_foreign_key_invalid_handled():
relations = deepcopy(FK_RELATIONS)
relations['people'][2]['firstname'] = 'Max'
table = Table(FK_SOURCE, schema=FK_SCHEMA)
errors = []
def handler(exc, row_number, row_data, error_data):
errors.append((exc, row_number, row_data, error_data))
expect = [
['1', {
'firstname': 'Alex',
'surname': 'Martin'
}, 'Martin'],
['2', {
'firstname': 'John',
'surname': 'Dockins'
}, 'Dockins'],
['3', {}, 'White'],
]
actual = table.read(relations=relations, exc_handler=handler)
assert actual == expect
assert len(errors) == 1
exc, row_number, row_data, error_data = errors[0]
assert row_number == 4
expect_keyed_row_data = OrderedDict(zip(FK_SOURCE[0], FK_SOURCE[3]))
assert row_data == expect_keyed_row_data
assert error_data == OrderedDict([('name', 'Walter')])
assert isinstance(exc, exceptions.UnresolvedFKError)
assert 'Foreign key' in str(exc)
def test_read_with_headers_field_names_mismatch_handled():
source = [
['id', 'bad', 'name'],
[1, 39, 'Paul'],
[2, 42, 'Peter'],
]
table = Table(source, schema=SCHEMA_CSV)
errors = []
def handler(exc, row_number, row_data, error_data):
errors.append((exc, row_number, row_data, error_data))
expect = []
actual = table.read(exc_handler=handler)
assert actual == expect
assert len(errors) == 2
for i, error in enumerate(errors):
expect_keyed_row_data = OrderedDict(zip(source[0], source[i + 1]))
exc, row_number, row_data, error_data = error
assert isinstance(exc, exceptions.CastError)
assert row_number == i + 2 # actual row number including header line
assert row_data == expect_keyed_row_data
assert error_data == expect_keyed_row_data
assert 'match schema field names' in str(exc)
def test_read_unique_primary_key_violation_handled():
schema = deepcopy(SCHEMA_CSV)
schema['primaryKey'] = 'id'
source = [
['id', 'age', 'name'],
[1, 39, 'Paul'],
[1, 36, 'Jane'],
]
table = Table(source, schema=schema)
errors = []
def handler(exc, row_number, row_data, error_data):
errors.append((exc, row_number, row_data, error_data))
expect = [
[1, 39, 'Paul'],
[1, 36, 'Jane'],
]
actual = table.read(exc_handler=handler)
assert actual == expect
assert len(errors) == 1
exc, row_number, row_data, error_data = errors[0]
assert isinstance(exc, exceptions.UniqueKeyError)
assert row_number == 3 # actual row number including header line
assert row_data == OrderedDict([('id', 1), ('age', 36), ('name', 'Jane')])
assert error_data == OrderedDict([('id', 1)])
assert 'duplicates' in str(exc)
def test_read_missing_cols_handled():
source = [
['key', 'value'],
[
'one',
],
['two', 2],
]
table = Table(source, schema=SCHEMA_MIN)
errors = []
def handler(exc, row_number, row_data, error_data):
errors.append((exc, row_number, row_data, error_data))
actual = table.read(exc_handler=handler)
expect = [
['one', None],
['two', 2],
]
assert actual == expect
expect_row_data = OrderedDict([('key', 'one'), ('value', None)])
_check_error(errors[0],
expect_exc_class=exceptions.CastError,
expect_exc_str='Row length',
expect_row_number=2,
expect_row_data=expect_row_data,
expect_error_data=expect_row_data)
def test_read_invalid_extra_cols_handled():
# Test a schema-invalid extra column in one row
source = [
['key', 'value'],
['one', 1, 'unexpected'],
['two', 2],
]
table = Table(source, schema=SCHEMA_MIN)
errors = []
def handler(exc, row_number, row_data, error_data):
errors.append((exc, row_number, row_data, error_data))
actual = table.read(exc_handler=handler)
expect = [
['one', 1],
['two', 2],
]
assert actual == expect
assert len(errors) == 1
expect_row_data = OrderedDict([('key', 'one'), ('value', 1),
('tableschema-cast-error-extra-col-3',
'unexpected')])
_check_error(errors[0],
expect_exc_class=exceptions.CastError,
expect_exc_str='Row length',
expect_row_number=2,
expect_row_data=expect_row_data,
expect_error_data=expect_row_data)
def test_schema_infer_missing_values():
table = Table('data/data_infer_missing_values.csv')
table.infer(missing_values=['-'])
schema = deepcopy(SCHEMA_CSV)
schema['missingValues'] = ['-']
assert table.schema.descriptor == schema
assert table.read() == [[1, 39, 'Paul'], [None, 25, 'Test'],
[2, 23, 'Jimmy'], [None, 25, 'Test'],
[3, 36, 'Jane'], [None, 25, 'Test'],
[4, 28, 'Judy']]
def test_multiple_foreign_keys_same_field():
schema = deepcopy(FK_SCHEMA)
relations = deepcopy(FK_RELATIONS)
relations['gender'] = [{
'firstname': 'Alex',
'gender': 'male/female'
}, {
'firstname': 'John',
'gender': 'male'
}, {
'firstname': 'Walter',
'gender': 'male'
}, {
'firstname': 'Alice',
'gender': 'female'
}]
# the main ressource now has tow foreignKeys using the same 'name' field
schema['foreignKeys'].append({
'fields': 'name',
'reference': {
'resource': 'gender',
'fields': 'firstname'
},
})
table = Table(FK_SOURCE, schema=schema)
keyed_rows = table.read(keyed=True, relations=relations)
assert keyed_rows == [
{
'id': '1',
'name': {
'firstname': 'Alex',
'surname': 'Martin',
'gender': 'male/female'
},
'surname': 'Martin'
},
{
'id': '2',
'name': {
'firstname': 'John',
'surname': 'Dockins',
'gender': 'male'
},
'surname': 'Dockins'
},
{
'id': '3',
'name': {
'firstname': 'Walter',
'surname': 'White',
'gender': 'male'
},
'surname': 'White'
},
]
def test_read_storage(import_module):
# Mocks
import_module.return_value = Mock(Storage=Mock(return_value=Mock(
describe=Mock(return_value=SCHEMA_MIN),
iter=Mock(return_value=DATA_MIN[1:]),
)))
# Tests
table = Table('table', backend='storage')
expect = [['one', 1], ['two', 2]]
actual = table.read()
assert actual == expect
def test_composite_primary_key_fails_unique_issue_194():
source = [
['id1', 'id2'],
['a', '1'],
['a', '1'],
]
schema = {
'fields': [
{
'name': 'id1'
},
{
'name': 'id2'
},
],
'primaryKey': ['id1', 'id2']
}
table = Table(source, schema=schema)
with pytest.raises(exceptions.CastError) as excinfo:
table.read()
assert 'duplicates' in str(excinfo.value)
def task5(inputcsv,outputjson): ! pip install tableschema from tableschema import Table table = Table(inputcsv) table.read(keyed=True) table.infer() table.schema.descriptor table.schema.descriptor["missingValues"] = "N/A" table.schema.commit() table.schema.valid table.schema.errors table.schema.descriptor["missingValues"] = "N/A" table.schema.commit() table.schema.valid table.schema.errors table.read(keyed=True) table.schema.save(outputjson)
def test_read_storage_passed_as_instance():
# Mocks
storage = Mock(
describe=Mock(return_value=SCHEMA_MIN),
iter=Mock(return_value=DATA_MIN[1:]),
spec=Storage,
)
# Tests
table = Table('table', storage=storage)
table.infer()
expect = [['one', 1], ['two', 2]]
actual = table.read()
assert actual == expect
def test_table_sql(name, resource):
# Storage
engine = create_engine('sqlite:///')
storage = Storage.connect('sql', engine=engine)
# Save
table = Table(resource['data'], schema=resource['schema'])
table.save('table', storage=storage)
# Load
table = Table('table', schema=resource['schema'], storage=storage)
assert table.read() == cast(resource)['data']
def test_processors():
# Processor
def skip_under_30(erows):
for row_number, headers, row in erows:
krow = dict(zip(headers, row))
if krow['age'] >= 30:
yield (row_number, headers, row)
# Create table
table = Table('data/data_infer.csv', post_cast=[skip_under_30])
table.infer()
expect = [[1, 39, 'Paul'], [3, 36, 'Jane']]
actual = table.read()
assert actual == expect
def test_read_invalid_col_value():
# Test a schema-invalid column value in one row
source = [
['key', 'value'],
['one', 'not_an_int'],
['two', 2],
]
table = Table(source, schema=SCHEMA_MIN)
with pytest.raises(exceptions.CastError) as excinfo:
actual = table.read()
assert 'There are 1 cast errors' in str(excinfo.value)
error = excinfo.value.errors[0]
assert isinstance(error, exceptions.CastError)
assert ('Field "value" can\'t cast value "not_an_int" for type "integer"'
in str(error))
def test_read_invalid_col_value_no_cast():
# Test a schema-invalid column value in one row, without value-casting
source = [
['key', 'value'],
['one', 'not_an_int'],
['two', 2],
]
expect = [
['one', 'not_an_int'],
['two', 2],
]
table = Table(source, schema=SCHEMA_MIN)
actual = table.read(cast=False)
# no actual casting, no cast errors
assert actual == expect
def test_single_field_foreign_key():
table = Table(FK_SOURCE, schema=FK_SCHEMA)
rows = table.read(relations=FK_RELATIONS)
assert rows == [
['1', {
'firstname': 'Alex',
'surname': 'Martin'
}, 'Martin'],
['2', {
'firstname': 'John',
'surname': 'Dockins'
}, 'Dockins'],
['3', {
'firstname': 'Walter',
'surname': 'White'
}, 'White'],
]
def test_composite_primary_key_issue_194():
source = [
['id1', 'id2'],
['a', '1'],
['a', '2'],
]
schema = {
'fields': [
{
'name': 'id1'
},
{
'name': 'id2'
},
],
'primaryKey': ['id1', 'id2']
}
table = Table(source, schema=schema)
assert table.read() == source[1:]
def test_processors():
# Processor
def skip_under_30(erows):
for number, headers, row in erows:
krow = dict(zip(headers, row))
if krow['age'] >= 30:
yield (number, headers, row)
# Create table
table = Table('data/data_infer.csv', post_cast=[skip_under_30])
# Test stream
table.stream.open()
expect = [['1', '39', 'Paul'], ['2', '23', 'Jimmy'], ['3', '36', 'Jane'],
['4', '28', 'Judy']]
actual = table.stream.read()
assert actual == expect
# Test table
expect = [[1, 39, 'Paul'], [3, 36, 'Jane']]
actual = table.read()
assert actual == expect
def test_multi_field_foreign_key():
schema = deepcopy(FK_SCHEMA)
schema['foreignKeys'][0]['fields'] = ['name', 'surname']
schema['foreignKeys'][0]['reference']['fields'] = ['firstname', 'surname']
table = Table(FK_SOURCE, schema=schema)
keyed_rows = table.read(keyed=True, relations=FK_RELATIONS)
assert keyed_rows == [
{
'id': '1',
'name': {
'firstname': 'Alex',
'surname': 'Martin'
},
'surname': {
'firstname': 'Alex',
'surname': 'Martin'
},
},
{
'id': '2',
'name': {
'firstname': 'John',
'surname': 'Dockins'
},
'surname': {
'firstname': 'John',
'surname': 'Dockins'
},
},
{
'id': '3',
'name': {
'firstname': 'Walter',
'surname': 'White'
},
'surname': {
'firstname': 'Walter',
'surname': 'White'
},
},
]
def test_read_invalid_col_value_handled_no_cast():
# Test a schema-invalid column value in one row, without value-casting
source = [
['key', 'value'],
['one', 'not_an_int'],
['two', 2],
]
expect = [
['one', 'not_an_int'],
['two', 2],
]
table = Table(source, schema=SCHEMA_MIN)
errors = []
def handler(exc, row_number, row_data, error_data):
errors.append((exc, row_number, row_data, error_data))
actual = table.read(cast=False, exc_handler=handler)
# no actual casting, no cast errors
assert len(errors) == 0
assert actual == expect
def test_table_bigquery(name, resource):
# Storage
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = '.credentials.json'
credentials = GoogleCredentials.get_application_default()
service = build('bigquery', 'v2', credentials=credentials)
project = json.load(io.open('.credentials.json', encoding='utf-8'))['project_id']
dataset = 'resource'
prefix = '%s_' % uuid.uuid4().hex
storage = Storage.connect('bigquery',
service=service, project=project, dataset=dataset, prefix=prefix)
# Save
table = Table(resource['data'], schema=resource['schema'])
table.save('table', storage=storage)
# Load
table = Table('table', schema=resource['schema'], storage=storage)
assert table.read() == cast(resource)['data']
# Clean
storage.delete()
def test_multi_fk_single_field_foreign_keys():
table = Table(MULTI_FK_SOURCE, schema=MULTI_FK_SCHEMA)
actual = table.read(relations=MULTI_FK_RELATIONS)
expect = [
[
'1',
{
'firstname': 'Alex',
'middlename': 'F.'
},
{
'surname': 'Martin',
'title': 'Mrs'
},
],
[
'2',
{
'firstname': 'John',
'middlename': 'G.'
},
{
'surname': 'Dockins',
'title': 'Mr'
},
],
[
'3',
{
'firstname': 'Walter',
'middlename': 'H.'
},
{
'surname': 'White',
'title': 'Mr'
},
],
]
assert actual == expect
output_row['mean_top_70m_mm'] = input_row['mean_top_70m_mm']
output_row['mean_alignment_70m_mm'] = input_row[
'mean_alignment_70m_mm']
output_row['twist_5m_mm'] = input_row['twist_5m_mm']
output_row['gradient_deg'] = input_row['gradient_deg']
# unvalidated extension point for non-standard geometry items
output_row['extended_items_geometry'] = json.dumps(
{'curvature_mm': input_row['x_curvature_mm']})
output_row['aws_signal_strength_V'] = input_row[
'aws_signal_strength_V']
output_row['creating_adapter_version'] = ADAPTER_VERSION
output_row['data_row_uid'] = uuid.uuid4()
wr.writerow(output_row)
if args.schema is not None:
# validate the output file against the schema
# print(args.schema.name)
tbl = Table(out_file.name, schema=args.schema.name)
# print('checking...')
try:
tbl.read(limit=2000)
print('OK')
except exceptions.TableSchemaException as exception:
for error in exception.errors:
print(error)
OUT_FILE = 'test_minimal_xircm_ugms.csv'
ADAPTER_VERSION = 'Vivacity-UGMS-Sample-v0.0.1'
UGMS_UNIT_ID = 'ugms-00001'
UGMS_UNIT_UID = 'e4c27259-ed1c-4e6e-be7c-2b06966b0689'
# create a minimal csv file output
with open(OUT_FILE, 'w') as f:
wr = csv.writer(f, quoting=csv.QUOTE_MINIMAL)
f.write(
'file_timestamp_utc,file_name,timestamp_recorded_utc,ugms_unit_id,creating_adapter_version\n'
)
data_row = [
'2019-02-18T07:45:23Z', OUT_FILE,
datetime.now().strftime('%Y-%m-%dT%H:%M:%SZ'), UGMS_UNIT_ID,
UGMS_UNIT_UID, ADAPTER_VERSION
]
wr.writerow(data_row)
# validate it against the schema
tbl = Table(OUT_FILE, schema=SCHEMA)
try:
tbl.read()
print('OK')
except exceptions.CastError as exception:
for error in exception.errors:
print(error)
except:
pass
def data(self):
source = self.storage.read(self.index_name)
t = Table(source, ignore_blank_headers=True)
return (t.infer(), t.headers, t.read(keyed=False, limit=1000))
# Data from WEB, schema from MEMORY
SOURCE = 'https://raw.githubusercontent.com/frictionlessdata/tableschema-py/master/data/data_infer.csv'
SCHEMA = {
'fields': [{
'name': 'id',
'type': 'integer'
}, {
'name': 'age',
'type': 'integer'
}, {
'name': 'name',
'type': 'string'
}]
}
# Open from WEB save to SQL database
table = Table(SOURCE, schema=SCHEMA)
table.save('articles', backend='sql', engine=db)
# Open from SQL save to DRIVE
table = Table('articles', backend='sql', engine=db)
table.schema.save('tmp/articles.json')
table.save('tmp/articles.csv')
# Open from DRIVE print to CONSOLE
table = Table('tmp/articles.csv', schema='tmp/articles.json')
print(table.read(keyed=True))
# Will print
# [{'id': 1, 'age': 39, 'name': 'Paul'}, {'id': 2, 'age': 23, 'name': 'Jimmy'}, {'id': 3, 'age': 36, 'name': 'Jane'}, {'id': 4, 'age': 28, 'name': 'Judy'}]
# Define a DataSet Schema
dsr = DataSetRequest()
dsr.name = # PUT YOUR DATASET NAME LOGIC HERE
dsr.description = # DATASET DESCRIPTION
dsr.schema = Schema(jeff)
# Create a DataSet with the given Schema
dataset = datasets.create(dsr)
domo.logger.info("Created DataSet " + dataset['id'])
# Get a DataSets's metadata
retrieved_dataset = datasets.get(dataset['id'])
domo.logger.info("Retrieved DataSet " + retrieved_dataset['id'])
# List DataSets
dataset_list = list(datasets.list(sort=Sorting.NAME))
domo.logger.info("Retrieved a list containing {} DataSet(s)".format(
len(dataset_list)))
csv_file_path = allFiles
datasets.data_import_from_file(dataset['id'], csv_file_path)
domo.logger.info("Uploaded data from a file to DataSet {}".format(
dataset['id']))
for eachCSV in os.listdir(inputdir):
allFiles = str(os.path.abspath(eachCSV))
table = Table(allFiles)
table.infer()
jeff = table.schema.descriptor
table.read(keyed=True)
directoryUpload()
def test_read_integrity_hash_error():
table = Table('data/data.csv')
with pytest.raises(exceptions.IntegrityError) as excinfo:
table.read(integrity={'hash': HASH + 'a'})
assert HASH in str(excinfo.value)
def test_read_integrity_hash():
table = Table('data/data.csv')
table.read(integrity={'hash': HASH})
assert True
