def test_iterate(self):
subset = UnicodeSubset('a-d')
self.assertListEqual(list(iter(subset)),
[ord('a'), ord('b'),
ord('c'), ord('d')])
self.assertListEqual(list(subset.iter_characters()),
['a', 'b', 'c', 'd'])
def test_max_and_min(self):
s1 = UnicodeSubset([10, 51, (89, 151), 90])
s2 = UnicodeSubset([0, 2, (80, 201), 10000])
s3 = UnicodeSubset([1])
self.assertEqual((min(s1), max(s1)), (10, 150))
self.assertEqual((min(s2), max(s2)), (0, 10000))
self.assertEqual((min(s3), max(s3)), (1, 1))
def test_difference_update_method(self):
subset = UnicodeSubset('a-z')
subset.difference_update('a-c')
self.assertEqual(subset, UnicodeSubset('d-z'))
subset = UnicodeSubset('a-z')
subset.difference_update([(ord('a'), ord('c') + 1)])
self.assertEqual(subset, UnicodeSubset('d-z'))
def test_creation(self):
subset = UnicodeSubset([(0, 9), 11, 12, (14, 32), (33, sys.maxunicode + 1)])
self.assertEqual(subset, [(0, 9), 11, 12, (14, 32), (33, sys.maxunicode + 1)])
self.assertEqual(UnicodeSubset('0-9'), [(48, 58)])
self.assertEqual(UnicodeSubset('0-9:'), [(48, 59)])
subset = UnicodeSubset('a-z')
self.assertEqual(UnicodeSubset(subset), [(ord('a'), ord('z') + 1)])
def test_repr(self):
self.assertEqual(code_point_repr((ord('2'), ord('\\') + 1)), r'2-\\')
subset = UnicodeSubset('a-z')
self.assertEqual(repr(subset), "UnicodeSubset('a-z')")
self.assertEqual(str(subset), "a-z")
subset = UnicodeSubset((50, 90))
subset.codepoints.append(sys.maxunicode + 10) # Invalid subset
self.assertRaises(ValueError, repr, subset)
def test_reversed(self):
subset = UnicodeSubset('0-9ax')
self.assertEqual(
list(reversed(subset)),
[ord('x'),
ord('a'),
ord('9'), 56, 55, 54, 53, 52, 51, 50, 49, 48])
def test_in_operator(self):
subset = UnicodeSubset('0-9a-z')
self.assertIn('a', subset)
self.assertIn(ord('a'), subset)
self.assertIn(ord('z'), subset)
self.assertNotIn('/', subset)
self.assertNotIn('A', subset)
self.assertNotIn(ord('A'), subset)
self.assertNotIn(ord('}'), subset)
self.assertNotIn(float(ord('a')), subset)
self.assertNotIn('.', subset)
subset.update('.')
self.assertIn('.', subset)
self.assertNotIn('/', subset)
self.assertNotIn('-', subset)
def test_xor(self):
subset = UnicodeSubset('a-z')
subset ^= subset
self.assertEqual(subset, UnicodeSubset())
subset = UnicodeSubset('a-z')
subset ^= UnicodeSubset('a-c')
self.assertEqual(subset, UnicodeSubset('d-z'))
subset = UnicodeSubset('a-z')
subset ^= 'a-f'
self.assertEqual(subset, UnicodeSubset('g-z'))
with self.assertRaises(TypeError) as ctx:
subset = UnicodeSubset('a-z')
subset ^= False
self.assertIn('unsupported operand type', str(ctx.exception))
subset = UnicodeSubset('a-z')
subset ^= 'A-Za-f'
self.assertEqual(subset, UnicodeSubset('A-Zg-z'))
def test_subtraction(self):
subset = UnicodeSubset([0, 2, (80, 200), 10000])
self.assertEqual(subset - {2, 120, 121, (150, 260)}, [0, (80, 120), (122, 150), 10000])
subset = UnicodeSubset('a-z')
subset -= UnicodeSubset('a-c')
self.assertEqual(subset, UnicodeSubset('d-z'))
subset = UnicodeSubset('a-z')
subset -= 'a-c'
self.assertEqual(subset, UnicodeSubset('d-z'))
with self.assertRaises(TypeError) as ctx:
subset = UnicodeSubset('a-z')
subset -= False
self.assertIn('unsupported operand type', str(ctx.exception))
def test_union_and_intersection(self):
s1 = UnicodeSubset([50, (90, 200), 10])
s2 = UnicodeSubset([10, 51, (89, 150), 90])
self.assertEqual(s1 | s2, [10, (50, 52), (89, 200)])
self.assertEqual(s1 & s2, [10, (90, 150)])
subset = UnicodeSubset('a-z')
subset |= UnicodeSubset('A-Zfx')
self.assertEqual(subset, UnicodeSubset('A-Za-z'))
subset |= '0-9'
self.assertEqual(subset, UnicodeSubset('0-9A-Za-z'))
subset |= [ord('{'), ord('}')]
self.assertEqual(subset, UnicodeSubset('0-9A-Za-z{}'))
subset = UnicodeSubset('a-z')
subset &= UnicodeSubset('A-Zfx')
self.assertEqual(subset, UnicodeSubset('fx'))
subset &= 'xyz'
self.assertEqual(subset, UnicodeSubset('x'))
with self.assertRaises(TypeError) as ctx:
subset = UnicodeSubset('a-z')
subset |= False
self.assertIn('unsupported operand type', str(ctx.exception))
with self.assertRaises(TypeError) as ctx:
subset = UnicodeSubset('a-z')
subset &= False
self.assertIn('unsupported operand type', str(ctx.exception))
def test_equality(self):
self.assertFalse(UnicodeSubset() == 0.0)
self.assertEqual(UnicodeSubset('a-z'), UnicodeSubset('a-kl-z'))
def test_complement(self):
subset = UnicodeSubset((50, 90, 10, 90))
self.assertEqual(list(subset.complement()), [(0, 10), (11, 50),
(51, 90),
(91, sys.maxunicode + 1)])
subset.add(11)
self.assertEqual(list(subset.complement()), [(0, 10), (12, 50),
(51, 90),
(91, sys.maxunicode + 1)])
subset.add((0, 10))
self.assertEqual(list(subset.complement()), [(12, 50), (51, 90),
(91, sys.maxunicode + 1)])
s1 = UnicodeSubset(
chain(UNICODE_CATEGORIES['L'].codepoints,
UNICODE_CATEGORIES['M'].codepoints,
UNICODE_CATEGORIES['N'].codepoints,
UNICODE_CATEGORIES['S'].codepoints))
s2 = UnicodeSubset(
chain(UNICODE_CATEGORIES['C'].codepoints,
UNICODE_CATEGORIES['P'].codepoints,
UNICODE_CATEGORIES['Z'].codepoints))
self.assertEqual(s1.codepoints,
UnicodeSubset(s2.complement()).codepoints)
subset = UnicodeSubset((50, 90))
subset.codepoints.append(70) # Invalid subset (unordered)
with self.assertRaises(ValueError) as ctx:
list(subset.complement())
self.assertEqual(
str(ctx.exception),
"unordered code points found in UnicodeSubset('2ZF')")
subset = UnicodeSubset((sys.maxunicode - 1, ))
self.assertEqual(list(subset.complement()),
[(0, sys.maxunicode - 1), sys.maxunicode])
def test_update_method(self):
subset = UnicodeSubset()
subset.update('\\\\')
self.assertListEqual(subset.codepoints, [ord('\\')])
subset.update('\\$')
self.assertListEqual(subset.codepoints, [ord('$'), ord('\\')])
subset.clear()
subset.update('!--')
self.assertListEqual(subset.codepoints, [(ord('!'), ord('-') + 1)])
subset.clear()
subset.update('!---')
self.assertListEqual(subset.codepoints, [(ord('!'), ord('-') + 1)])
subset.clear()
subset.update('!--a')
self.assertListEqual(
subset.codepoints,
[(ord('!'), ord('-') + 1), ord('a')])
with self.assertRaises(RegexError):
subset.update('[[')
def test_modify(self):
subset = UnicodeSubset()
for cp in [50, 90, 10, 90]:
subset.add(cp)
self.assertEqual(subset, [10, 50, 90])
self.assertRaises(ValueError, subset.add, -1)
self.assertRaises(ValueError, subset.add, sys.maxunicode + 1)
subset.add((100, 20001))
subset.discard((100, 19001))
self.assertEqual(subset, [10, 50, 90, (19001, 20001)])
subset.add(0)
subset.discard(1)
self.assertEqual(subset, [0, 10, 50, 90, (19001, 20001)])
subset.discard(0)
self.assertEqual(subset, [10, 50, 90, (19001, 20001)])
subset.discard((10, 100))
self.assertEqual(subset, [(19001, 20001)])
subset.add(20)
subset.add(19)
subset.add(30)
subset.add([30, 33])
subset.add(30000)
subset.add(30001)
self.assertEqual(subset, [(19, 21), (30, 33), (19001, 20001),
(30000, 30002)])
subset.add(22)
subset.add(21)
subset.add(22)
self.assertEqual(subset, [(19, 22), 22, (30, 33), (19001, 20001),
(30000, 30002)])
subset.discard((90, 50000))
self.assertEqual(subset, [(19, 22), 22, (30, 33)])
subset.discard(21)
subset.discard(19)
self.assertEqual(subset, [20, 22, (30, 33)])
subset.discard((0, 200))
self.assertEqual(subset, [])
with self.assertRaises(ValueError):
subset.discard(None)
with self.assertRaises(ValueError):
subset.discard((10, 11, 12))
