Skip to content

Commit

Permalink
TST: Specify HTML file encoding on PY3 (#16526)
Browse files Browse the repository at this point in the history
(cherry picked from commit e60dc4c)
  • Loading branch information
neirbowj authored and TomAugspurger committed May 30, 2017
1 parent 3a0e92f commit eefbaf7
Showing 1 changed file with 9 additions and 6 deletions.
15 changes: 9 additions & 6 deletions pandas/tests/io/test_html.py
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
from pandas import (DataFrame, MultiIndex, read_csv, Timestamp, Index,
date_range, Series)
from pandas.compat import (map, zip, StringIO, string_types, BytesIO,
is_platform_windows)
is_platform_windows, PY3)
from pandas.io.common import URLError, urlopen, file_path_to_url
from pandas.io.html import read_html
from pandas._libs.parsers import ParserError
Expand Down Expand Up @@ -96,6 +96,9 @@ def read_html(self, *args, **kwargs):
class TestReadHtml(ReadHtmlMixin):
flavor = 'bs4'
spam_data = os.path.join(DATA_PATH, 'spam.html')
spam_data_kwargs = {}
if PY3:
spam_data_kwargs['encoding'] = 'UTF-8'
banklist_data = os.path.join(DATA_PATH, 'banklist.html')

@classmethod
Expand Down Expand Up @@ -247,18 +250,18 @@ def test_infer_types(self):
assert_framelist_equal(df1, df2)

def test_string_io(self):
with open(self.spam_data) as f:
with open(self.spam_data, **self.spam_data_kwargs) as f:
data1 = StringIO(f.read())

with open(self.spam_data) as f:
with open(self.spam_data, **self.spam_data_kwargs) as f:
data2 = StringIO(f.read())

df1 = self.read_html(data1, '.*Water.*')
df2 = self.read_html(data2, 'Unit')
assert_framelist_equal(df1, df2)

def test_string(self):
with open(self.spam_data) as f:
with open(self.spam_data, **self.spam_data_kwargs) as f:
data = f.read()

df1 = self.read_html(data, '.*Water.*')
Expand All @@ -267,10 +270,10 @@ def test_string(self):
assert_framelist_equal(df1, df2)

def test_file_like(self):
with open(self.spam_data) as f:
with open(self.spam_data, **self.spam_data_kwargs) as f:
df1 = self.read_html(f, '.*Water.*')

with open(self.spam_data) as f:
with open(self.spam_data, **self.spam_data_kwargs) as f:
df2 = self.read_html(f, 'Unit')

assert_framelist_equal(df1, df2)
Expand Down

0 comments on commit eefbaf7

Please sign in to comment.