def testCalculateSlices(self):
"""Test of _CalculateSlices with powersets."""
column1 = data_source.DataSourceColumn(
'col1', rollup=True, concept_extension='entity:entity')
column2 = data_source.DataSourceColumn('col2', rollup=False)
column3 = data_source.DataSourceColumn('col3',
rollup=True,
parent_ref='col5')
column4 = data_source.DataSourceColumn('col4',
rollup=True,
parent_ref='col3')
column5 = data_source.DataSourceColumn('col5', rollup=True)
column_bundle = data_source.DataSourceColumnBundle(
columns=[column1, column2, column3, column4, column5])
slice_column_sets = data_source_to_dspl._CalculateSlices(column_bundle)
# Convert columns to id strings
slice_column_ids = []
for slice_column_set in slice_column_sets:
slice_column_ids.append([c.column_id for c in slice_column_set])
# Sort the actual and expected results so that the test is not order
# dependent
self.assertEqual(
sorted([sorted(s) for s in slice_column_ids]),
sorted([
sorted(s)
for s in [['col1', 'col2', 'col3'], ['col1', 'col2', 'col4'],
['col1', 'col2', 'col5'], ['col1', 'col2'],
['col2', 'col3'], ['col2', 'col4'], ['col2', 'col5'],
['col2']]
]))
def GetColumnBundle(self):
column1 = data_source.DataSourceColumn(
'col1',
data_type='string',
slice_role='dimension',
concept_extension='entity:entity',
rollup=True)
column2 = data_source.DataSourceColumn(
'col2',
data_type='string',
concept_extension='geo:location',
slice_role='dimension',
parent_ref='col6')
column3 = data_source.DataSourceColumn('col3',
data_type='date',
concept_ref='time:year',
data_format='yyyy',
slice_role='dimension')
column4 = data_source.DataSourceColumn('col4',
data_type='float',
slice_role='metric')
column5 = data_source.DataSourceColumn('col5',
data_type='integer',
slice_role='metric')
column6 = data_source.DataSourceColumn('col6',
data_type='string',
slice_role='dimension',
rollup=True)
return data_source.DataSourceColumnBundle(
columns=[column1, column2, column3, column4, column5, column6])
def _HeaderToColumn(header_string):
"""Parse the header string for a column.
Args:
header_string: The complete string for the column header
Returns:
A DataColumn object populated based on the header data
Raises:
DataSourceError: If there are any errors in parsing, e.g. if an unrecognized
key is found.
"""
# The column id must be at least one character long, and cannot contain the
# characters '[', ']', ';', or whitespace
parameters_match = re.match('^([^\]\[;\s]+)(?:\[(.*)\]){0,1}$',
header_string.strip().replace('"', ''))
if not parameters_match:
raise data_source.DataSourceError(
'Formatting error for header string: %s' % header_string)
column_id = parameters_match.group(1)
column = data_source.DataSourceColumn(column_id, internal_parameters={})
if parameters_match.group(2):
# Parse the column parameters
key_value_pairs = parameters_match.group(2).split(';')
for key_value_pair in key_value_pairs:
try:
[key, value] = key_value_pair.split('=')
except ValueError:
raise data_source.DataSourceError(
'Formatting error for header string: %s' % header_string)
# Map the key to the appropriate field of the DataSourceColumn object
if key == 'type':
if value not in ['date', 'float', 'integer', 'string']:
raise data_source.DataSourceError(
'Unknown data type for column %s: %s' %
(column.column_id, value))
column.data_type = value
elif key == 'format':
column.data_format = value
elif key == 'concept':
column.concept_ref = value
elif key == 'extends':
column.concept_extension = value
elif key == 'parent':
column.parent_ref = value
elif key == 'slice_role':
role_value = value.lower()
if role_value not in ['dimension', 'metric']:
raise data_source.DataSourceError(
'Unrecognized slice_roll in column %s: %s' %
(column.column_id, value))
else:
column.slice_role = role_value
elif key == 'rollup':
if value.lower() == 'true':
column.rollup = True
elif value.lower() == 'false':
column.rollup = False
else:
raise data_source.DataSourceError(
'Unrecognized boolean value in column %s: %s' %
(column.column_id, value))
elif key == 'total_val':
column.total_val = value
elif key == 'dropif':
column.internal_parameters['dropif_val'] = value
elif key == 'zeroif':
column.internal_parameters['zeroif_val'] = value
elif key == 'aggregation':
if string.lower(value) not in [
'sum', 'max', 'min', 'avg', 'count'
]:
raise data_source.DataSourceError(
'Unknown aggregation for column %s: %s' %
(column.column_id, value))
column.internal_parameters['aggregation'] = value
else:
raise data_source.DataSourceError(
'Unknown parameter for column %s: %s' %
(column.column_id, key))
return column
def testAddColumn(self):
self.column_bundle.AddColumn(
data_source.DataSourceColumn(column_id='col4'))
self.assertEqual(
self.column_bundle.GetColumnByID('col4').column_id, 'col4')
def setUp(self):
self.column_bundle = data_source.DataSourceColumnBundle([
data_source.DataSourceColumn(column_id='col1'),
data_source.DataSourceColumn(column_id='col2'),
data_source.DataSourceColumn(column_id='col3')
])