def get_case(field_type, values):
""" Determines the case of a list or dictionary of values.
Args:
- type: if not == 'string', will return 'n/a'
- values: could be either dictionary or list. If it's a list, then
it will only examine the keys.
Returns:
- one of: 'mixed','lower','upper','unknown'
Misc notes:
- "unknown values" are ignored
- empty values list/dict results in 'unknown' result
To do:
- add consistency factor
Test coverage:
- complete, via test harness
"""
freq = collections.defaultdict(int)
case = None
if field_type != 'string':
return 'n/a'
# count occurances of each case field_type in values:
for key in values:
if typer.is_unknown(key):
freq['unk'] += 1
elif typer.is_integer(key): # will be ignoring these
freq['number'] += 1
elif typer.is_float(key): # will be ignoring these
freq['number'] += 1
elif key.islower():
freq['lower'] += 1
elif key.isupper():
freq['upper'] += 1
else:
freq['mixed'] += 1
# evaluate frequency distribution:
if 'mixed' in freq:
case = 'mixed'
elif ('lower' in freq and 'upper' not in freq):
case = 'lower'
elif ('lower' not in freq and 'upper' in freq):
case = 'upper'
elif ('lower' in freq and 'upper' in freq):
case = 'mixed'
else:
case = 'unknown'
return case
def get_case(field_type, values):
""" Determines the case of a list or dictionary of values.
Args:
- type: if not == 'string', will return 'n/a'
- values: could be either dictionary or list. If it's a list, then
it will only examine the keys.
Returns:
- one of: 'mixed','lower','upper','unknown'
Misc notes:
- "unknown values" are ignored
- empty values list/dict results in 'unknown' result
To do:
- add consistency factor
Test coverage:
- complete, via test harness
"""
freq = collections.defaultdict(int)
case = None
if field_type != 'string':
return 'n/a'
# count occurances of each case field_type in values:
for key in values:
if typer.is_unknown(key):
freq['unk'] += 1
elif typer.is_integer(key): # will be ignoring these
freq['number'] += 1
elif typer.is_float(key): # will be ignoring these
freq['number'] += 1
elif key.islower():
freq['lower'] += 1
elif key.isupper():
freq['upper'] += 1
else:
freq['mixed'] += 1
# evaluate frequency distribution:
if 'mixed' in freq:
case = 'mixed'
def test_type_a01_is_integer(self):
self.assertTrue(mod.is_integer('3'))
self.assertTrue(mod.is_integer('-3'))
self.assertTrue(mod.is_integer(3))
self.assertTrue(mod.is_integer(-3))
self.assertFalse(mod.is_integer('b'))
self.assertFalse(mod.is_integer(''))
self.assertFalse(mod.is_integer(' '))
self.assertFalse(mod.is_integer('$3'))
self.assertFalse(mod.is_integer('4,333.22'))
self.assertFalse(mod.is_integer('33.22'))
self.assertFalse(mod.is_integer(3.3))
self.assertFalse(mod.is_integer(None))
def test_type_a01_is_integer(self):
self.assertTrue(mod.is_integer('3'))
self.assertTrue(mod.is_integer('-3'))
self.assertTrue(mod.is_integer(3))
self.assertTrue(mod.is_integer(-3))
self.assertFalse(mod.is_integer('b'))
self.assertFalse(mod.is_integer(''))
self.assertFalse(mod.is_integer(' '))
self.assertFalse(mod.is_integer('$3'))
self.assertFalse(mod.is_integer('4,333.22'))
self.assertFalse(mod.is_integer('33.22'))
self.assertFalse(mod.is_integer(3.3))
self.assertFalse(mod.is_integer(None))
def test_is_integer_basics(self):
assert mod.is_integer('3')
assert mod.is_integer('-3')
assert mod.is_integer(3)
assert mod.is_integer(-3)
assert mod.is_integer('b') is False
assert mod.is_integer('') is False
assert mod.is_integer(' ') is False
assert mod.is_integer('$3') is False
assert mod.is_integer('4,333.22') is False
assert mod.is_integer('33.22') is False
assert mod.is_integer(3.3) is False
assert mod.is_integer(None) is False
def test_is_integer_basics(self):
assert mod.is_integer("3")
assert mod.is_integer("-3")
assert mod.is_integer(3)
assert mod.is_integer(-3)
assert mod.is_integer("b") is False
assert mod.is_integer("") is False
assert mod.is_integer(" ") is False
assert mod.is_integer("$3") is False
assert mod.is_integer("4,333.22") is False
assert mod.is_integer("33.22") is False
assert mod.is_integer(3.3) is False
assert mod.is_integer(None) is False
