Skip to content

TST: Use unicode literals in string test #10405

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 23, 2015
+9 −32
Merged

TST: Use unicode literals in string test #10405

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
41 changes: 9 additions & 32 deletions pandas/tests/test_strings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -747,20 +747,18 @@ def test_isnumeric(self):
# 0x2605: ★ not number
# 0x1378: ፸ ETHIOPIC NUMBER SEVENTY
# 0xFF13: ３ Em 3
values = ['A', '3', unichr(0x00bc), unichr(0x2605),
unichr(0x1378), unichr(0xFF13), 'four']
values = ['A', '3', u'¼', u'★', u'፸', u'３', 'four']
s = Series(values)
numeric_e = [False, True, True, False, True, True, False]
decimal_e = [False, True, False, False, False, True, False]
tm.assert_series_equal(s.str.isnumeric(), Series(numeric_e))
tm.assert_series_equal(s.str.isdecimal(), Series(decimal_e))
unicodes = [u('A'), u('3'), unichr(0x00bc), unichr(0x2605),
unichr(0x1378), unichr(0xFF13), u('four')]

unicodes = [u'A', u'3', u'¼', u'★', u'፸', u'３', u'four']
self.assertEqual(s.str.isnumeric().tolist(), [v.isnumeric() for v in unicodes])
self.assertEqual(s.str.isdecimal().tolist(), [v.isdecimal() for v in unicodes])

values = ['A', np.nan, unichr(0x00bc), unichr(0x2605),
np.nan, unichr(0xFF13), 'four']
values = ['A', np.nan, u'¼', u'★', np.nan, u'３', 'four']
s = Series(values)
numeric_e = [False, np.nan, True, False, np.nan, True, False]
decimal_e = [False, np.nan, False, False, np.nan, True, False]
Expand Down Expand Up @@ -1950,33 +1948,16 @@ def test_encode_decode_errors(self):
tm.assert_series_equal(result, exp)

def test_normalize(self):
def unistr(codes):
# build unicode string from unichr
# we cannot use six.u() here because it escapes unicode
return ''.join([unichr(c) for c in codes])

values = ['ABC', # ASCII
unistr([0xFF21, 0xFF22, 0xFF23]), # ＡＢＣ
unistr([0xFF11, 0xFF12, 0xFF13]), # １２３
np.nan,
unistr([0xFF71, 0xFF72, 0xFF74])] # ｱｲｴ
values = ['ABC', u'ＡＢＣ', u'１２３', np.nan, u'ｱｲｴ']
s = Series(values, index=['a', 'b', 'c', 'd', 'e'])

normed = [compat.u_safe('ABC'),
compat.u_safe('ABC'),
compat.u_safe('123'),
np.nan,
unistr([0x30A2, 0x30A4, 0x30A8])] # アイエ
normed = [u'ABC', u'ABC', u'123', np.nan, u'アイエ']
expected = Series(normed, index=['a', 'b', 'c', 'd', 'e'])

result = s.str.normalize('NFKC')
tm.assert_series_equal(result, expected)

expected = Series([compat.u_safe('ABC'),
unistr([0xFF21, 0xFF22, 0xFF23]), # ＡＢＣ
unistr([0xFF11, 0xFF12, 0xFF13]), # １２３
np.nan,
unistr([0xFF71, 0xFF72, 0xFF74])], # ｱｲｴ
expected = Series([u'ABC', u'ＡＢＣ', u'１２３', np.nan, u'ｱｲｴ'],
index=['a', 'b', 'c', 'd', 'e'])

result = s.str.normalize('NFC')
Expand All @@ -1985,12 +1966,8 @@ def unistr(codes):
with tm.assertRaisesRegexp(ValueError, "invalid normalization form"):
s.str.normalize('xxx')

s = Index([unistr([0xFF21, 0xFF22, 0xFF23]), # ＡＢＣ
unistr([0xFF11, 0xFF12, 0xFF13]), # １２３
unistr([0xFF71, 0xFF72, 0xFF74])]) # ｱｲｴ
expected = Index([compat.u_safe('ABC'),
compat.u_safe('123'),
unistr([0x30A2, 0x30A4, 0x30A8])])
s = Index([u'ＡＢＣ', u'１２３', u'ｱｲｴ'])
expected = Index([u'ABC', u'123', u'アイエ'])
result = s.str.normalize('NFKC')
tm.assert_index_equal(result, expected)

Expand Down