def test_max_length(self):
rows = [
Row(['a'], ['test']),
Row(['gobble'], ['test']),
Row(['w'], ['test']),
]
column = Column(0, 'test', Text(), rows)
self.assertEqual(column.aggregate(MaxLength()), 6)
def test_max_length(self):
rows = [
Row(['a'], ['test']),
Row(['gobble'], ['test']),
Row(['w'], ['test']),
]
column = Column(0, 'test', Text(), rows)
self.assertEqual(column.aggregate(MaxLength()), 6)
def test_max(self):
rows = [
Row([datetime.datetime(1994, 3, 3, 6, 31)], ['test']),
Row([datetime.datetime(1994, 3, 3, 6, 30, 30)], ['test']),
Row([datetime.datetime(1994, 3, 3, 6, 30)], ['test']),
]
column = Column(0, 'test', DateTime(), rows)
self.assertIsInstance(Max().get_aggregate_data_type(column), DateTime)
self.assertEqual(column.aggregate(Max()), datetime.datetime(1994, 3, 3, 6, 31))
def test_all(self):
rows = [
Row([True], ['test']),
Row([True], ['test']),
Row([None], ['test']),
]
column = Column(0, 'test', Boolean(), rows)
self.assertEqual(column.aggregate(All()), False)
rows = [
Row([True], ['test']),
Row([True], ['test']),
Row([True], ['test']),
]
column = Column(0, 'test', Boolean(), rows)
self.assertEqual(column.aggregate(All()), True)
def test_all(self):
rows = [
Row([True], ['test']),
Row([True], ['test']),
Row([None], ['test']),
]
column = Column(0, 'test', Boolean(), rows)
self.assertEqual(column.aggregate(All()), False)
rows = [
Row([True], ['test']),
Row([True], ['test']),
Row([True], ['test']),
]
column = Column(0, 'test', Boolean(), rows)
self.assertEqual(column.aggregate(All()), True)
def __init__(self,
rows,
column_names=None,
column_types=None,
row_names=None,
_is_fork=False):
# Validate column names
if column_names:
final_column_names = []
for i, column_name in enumerate(column_names):
if column_name is None:
final_column_names.append(utils.letter_name(i))
elif isinstance(column_name, six.string_types):
final_column_names.append(column_name)
else:
raise ValueError('Column names must be strings or None.')
if len(set(final_column_names)) != len(final_column_names):
raise ValueError('Duplicate column names are not allowed.')
self._column_names = tuple(final_column_names)
else:
self._column_names = tuple(
utils.letter_name(i) for i in range(len(rows[0])))
len_column_names = len(self._column_names)
# Validate column_types
if column_types is None:
column_types = TypeTester()
elif isinstance(column_types, TypeTester):
pass
else:
for column_type in column_types:
if not isinstance(column_type, DataType):
raise ValueError(
'Column types must be instances of DataType.')
if isinstance(column_types, TypeTester):
self._column_types = column_types.run(rows, self._column_names)
else:
self._column_types = tuple(column_types)
if len_column_names != len(self._column_types):
raise ValueError(
'column_names and column_types must be the same length.')
if not _is_fork:
new_rows = []
cast_funcs = [c.cast for c in self._column_types]
for i, row in enumerate(rows):
len_row = len(row)
if len_row > len_column_names:
raise ValueError(
'Row %i has %i values, but Table only has %i columns.'
% (i, len_row, len_column_names))
elif len(row) < len_column_names:
row = chain(row,
[None] * (len(self.column_names) - len_row))
new_rows.append(
Row(tuple(cast_funcs[i](d) for i, d in enumerate(row)),
self._column_names))
else:
new_rows = rows
if row_names:
computed_row_names = []
if isinstance(row_names, six.string_types):
for row in new_rows:
name = row[row_names]
computed_row_names.append(name)
elif hasattr(row_names, '__call__'):
for row in new_rows:
name = row_names(row)
computed_row_names.append(name)
elif isinstance(row_names, Sequence):
computed_row_names = row_names
else:
raise ValueError(
'row_names must be a column name, function or sequence')
self._row_names = tuple(computed_row_names)
else:
self._row_names = None
self._rows = MappedSequence(new_rows, self._row_names)
# Build columns
new_columns = []
for i, (name, data_type) in enumerate(
zip(self._column_names, self._column_types)):
column = Column(i,
name,
data_type,
self._rows,
row_names=self._row_names)
new_columns.append(column)
self._columns = MappedSequence(new_columns, self._column_names)
def __init__(self, rows, column_info, row_names=None, _is_fork=False):
column_info = list(column_info)
if isinstance(column_info[0], Column):
self._column_names = tuple(c.name for c in column_info)
self._column_types = tuple(c.data_type for c in column_info)
else:
column_names, self._column_types = zip(*column_info)
self._column_names = []
# Validation
for i, column_name in enumerate(column_names):
if not column_name:
self._column_names.append(letter_name(i))
else:
if not isinstance(column_name, six.string_types):
raise ValueError('Column names must be strings.')
self._column_names.append(column_name)
len_column_names = len(self._column_names)
if len(set(self._column_names)) != len_column_names:
raise ValueError('Duplicate column names are not allowed.')
self._column_names = tuple(self._column_names)
for column_type in self._column_types:
if not isinstance(column_type, DataType):
raise ValueError('Column types must be instances of DataType.')
if not _is_fork:
new_rows = []
cast_funcs = [c.cast for c in self._column_types]
for i, row in enumerate(rows):
len_row = len(row)
if len_row > len_column_names:
raise ValueError('Row %i has %i values, but Table only has %i columns.' % (i, len_row, len_column_names))
elif len(row) < len_column_names:
row = chain(row, [None] * (len(self.column_names) - len_row))
new_rows.append(Row(tuple(cast_funcs[i](d) for i, d in enumerate(row)), self._column_names))
else:
new_rows = rows
if row_names:
computed_row_names = []
if isinstance(row_names, six.string_types):
for row in new_rows:
name = row[row_names]
computed_row_names.append(name)
elif hasattr(row_names, '__call__'):
for row in new_rows:
name = row_names(row)
computed_row_names.append(name)
elif isinstance(row_names, Sequence):
computed_row_names = row_names
else:
raise ValueError('row_names must be a column name, function or sequence')
self._row_names = tuple(computed_row_names)
else:
self._row_names = None
self._rows = MappedSequence(new_rows, self._row_names)
# Build columns
new_columns = []
for i, (name, data_type) in enumerate(zip(self._column_names, self._column_types)):
column = Column(i, name, data_type, self._rows, row_names=self._row_names)
new_columns.append(column)
self._columns = MappedSequence(new_columns, self._column_names)
def __init__(self,
rows,
column_names=None,
column_types=None,
row_names=None,
_is_fork=False):
if isinstance(rows, six.string_types):
raise ValueError(
'When created directly, the first argument to Table must be a sequence of rows. Did you want agate.Table.from_csv?'
)
# Validate column names
if column_names:
final_column_names = []
for i, column_name in enumerate(column_names):
if column_name is None:
new_column_name = utils.letter_name(i)
warnings.warn(
'Column name not specified. "%s" will be used as name.'
% new_column_name, RuntimeWarning)
elif isinstance(column_name, six.string_types):
new_column_name = column_name
else:
raise ValueError('Column names must be strings or None.')
final_column_name = new_column_name
duplicates = 0
while final_column_name in final_column_names:
final_column_name = new_column_name + '_' + str(
duplicates + 2)
duplicates += 1
if duplicates > 0:
warn_duplicate_column(new_column_name, final_column_name)
final_column_names.append(final_column_name)
self._column_names = tuple(final_column_names)
elif rows:
self._column_names = tuple(
utils.letter_name(i) for i in range(len(rows[0])))
warnings.warn(
'Column names not specified. "%s" will be used as names.' %
str(self._column_names),
RuntimeWarning,
stacklevel=2)
else:
self._column_names = []
len_column_names = len(self._column_names)
# Validate column_types
if column_types is None:
column_types = TypeTester()
elif isinstance(column_types, dict):
for v in six.itervalues(column_types):
if not isinstance(v, DataType):
raise ValueError(
'Column types must be instances of DataType.')
column_types = TypeTester(force=column_types)
elif not isinstance(column_types, TypeTester):
for column_type in column_types:
if not isinstance(column_type, DataType):
raise ValueError(
'Column types must be instances of DataType.')
if isinstance(column_types, TypeTester):
self._column_types = column_types.run(rows, self._column_names)
else:
self._column_types = tuple(column_types)
if len_column_names != len(self._column_types):
raise ValueError(
'column_names and column_types must be the same length.')
if not _is_fork:
new_rows = []
cast_funcs = [c.cast for c in self._column_types]
for i, row in enumerate(rows):
len_row = len(row)
if len_row > len_column_names:
raise ValueError(
'Row %i has %i values, but Table only has %i columns.'
% (i, len_row, len_column_names))
elif len(row) < len_column_names:
row = chain(row,
[None] * (len(self.column_names) - len_row))
new_rows.append(
Row(tuple(cast_funcs[i](d) for i, d in enumerate(row)),
self._column_names))
else:
new_rows = rows
if row_names:
computed_row_names = []
if isinstance(row_names, six.string_types):
for row in new_rows:
name = row[row_names]
computed_row_names.append(name)
elif hasattr(row_names, '__call__'):
for row in new_rows:
name = row_names(row)
computed_row_names.append(name)
elif utils.issequence(row_names):
computed_row_names = row_names
else:
raise ValueError(
'row_names must be a column name, function or sequence')
self._row_names = tuple(computed_row_names)
else:
self._row_names = None
self._rows = MappedSequence(new_rows, self._row_names)
# Build columns
new_columns = []
for i, (name, data_type) in enumerate(
zip(self._column_names, self._column_types)):
column = Column(i,
name,
data_type,
self._rows,
row_names=self._row_names)
new_columns.append(column)
self._columns = MappedSequence(new_columns, self._column_names)
def test_max_length_invalid(self):
column = Column(0, 'test', Number(), ([1], [2], [3]))
with self.assertRaises(DataTypeError):
column.aggregate(MaxLength())
def __init__(self,
rows,
column_names=None,
column_types=None,
row_names=None,
_is_fork=False):
if isinstance(rows, six.string_types):
raise ValueError(
'When created directly, the first argument to Table must be a sequence of rows. '
'Did you want agate.Table.from_csv?')
# Validate column names
if column_names:
self._column_names = utils.deduplicate(column_names,
column_names=True)
elif rows:
self._column_names = tuple(
utils.letter_name(i) for i in range(len(rows[0])))
warnings.warn(
'Column names not specified. "%s" will be used as names.' %
str(self._column_names),
RuntimeWarning,
stacklevel=2)
else:
self._column_names = tuple()
len_column_names = len(self._column_names)
# Validate column_types
if column_types is None:
column_types = TypeTester()
elif isinstance(column_types, dict):
for v in column_types.values():
if not isinstance(v, DataType):
raise ValueError(
'Column types must be instances of DataType.')
column_types = TypeTester(force=column_types)
elif not isinstance(column_types, TypeTester):
for column_type in column_types:
if not isinstance(column_type, DataType):
raise ValueError(
'Column types must be instances of DataType.')
if isinstance(column_types, TypeTester):
self._column_types = column_types.run(rows, self._column_names)
else:
self._column_types = tuple(column_types)
if len_column_names != len(self._column_types):
raise ValueError(
'column_names and column_types must be the same length.')
if not _is_fork:
new_rows = []
cast_funcs = [c.cast for c in self._column_types]
for i, row in enumerate(rows):
len_row = len(row)
if len_row > len_column_names:
raise ValueError(
'Row %i has %i values, but Table only has %i columns.'
% (i, len_row, len_column_names))
elif len(row) < len_column_names:
row = chain(row, [None] * (len_column_names - len_row))
row_values = []
for j, d in enumerate(row):
try:
row_values.append(cast_funcs[j](d))
except CastError as e:
raise CastError(
str(e) + ' Error at row %s column %s.' %
(i, self._column_names[j]))
new_rows.append(Row(row_values, self._column_names))
else:
new_rows = rows
if row_names:
computed_row_names = []
if isinstance(row_names, six.string_types):
for row in new_rows:
name = row[row_names]
computed_row_names.append(name)
elif hasattr(row_names, '__call__'):
for row in new_rows:
name = row_names(row)
computed_row_names.append(name)
elif utils.issequence(row_names):
computed_row_names = row_names
else:
raise ValueError(
'row_names must be a column name, function or sequence')
for row_name in computed_row_names:
if type(row_name) is int:
raise ValueError(
'Row names cannot be of type int. Use Decimal for numbered row names.'
)
self._row_names = tuple(computed_row_names)
else:
self._row_names = None
self._rows = MappedSequence(new_rows, self._row_names)
# Build columns
new_columns = []
for i in range(len_column_names):
name = self._column_names[i]
data_type = self._column_types[i]
column = Column(i,
name,
data_type,
self._rows,
row_names=self._row_names)
new_columns.append(column)
self._columns = MappedSequence(new_columns, self._column_names)
def test_max_length_invalid(self):
column = Column(0, 'test', Number(), ([1], [2], [3]))
with self.assertRaises(DataTypeError):
column.aggregate(MaxLength())
