Skip to content

Ensure input files are read as UTF-8 #45

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

Open
refack wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Ensure input files are read as UTF-8 #45

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
fe93434
Ensure HTML is parsed as UTF-8
refack Apr 25, 2025
3c821db
Ensure text files are opened as UTF-8
refack Sep 23, 2025
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
2 changes: 1 addition & 1 deletion commands/preprocess.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -386,7 +386,7 @@ def remove_unused_external(html):


def preprocess_html_file(root, fn, rename_map):
parser = etree.HTMLParser()
parser = etree.HTMLParser(encoding='utf-8')
html = etree.parse(fn, parser)
output = io.StringIO()

Expand Down
4 changes: 2 additions & 2 deletions commands/preprocess_cssless.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,9 +29,9 @@


def preprocess_html_merge_cssless(src_path, dst_path):
with open(src_path, 'r') as a_file:
with open(src_path, 'r', encoding='utf-8') as a_file:
content = a_file.read()
parser = etree.HTMLParser()
parser = etree.HTMLParser(encoding='utf-8')
stripped = content.strip()
root = etree.fromstring(stripped, parser)

Expand Down
4 changes: 2 additions & 2 deletions gadgets/replace_tests_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,14 +46,14 @@ def main():

for path in paths:
print('Processing {0}'.format(path))
with open(path, 'r') as file:
with open(path, 'r', encoding='utf-8') as file:
text = file.read()

# TODO user proper XML parser, not this hack
text = re.sub('<link rel="selenium.base" href="(.*)" />',
'<link rel="selenium.base" href="' + args.url + '" />', text)

with open(path, 'w') as file:
with open(path, 'w', encoding='utf-8') as file:
file.write(text)

if __name__ == '__main__':
Expand Down
4 changes: 2 additions & 2 deletions gadgets/sync_tests_mwiki.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@ def sync_single_page(page, direction, dest_root):
if direction == SYNC_DIRECTION_UPLOAD:
if not os.path.exists(dest_path):
return
with open(dest_path, 'r') as file:
with open(dest_path, 'r', encoding='utf-8') as file:
new_text = file.read()
if fix_whitespace(text) != fix_whitespace(new_text):
page.put(new_text, 'sync with git')
Expand All @@ -82,7 +82,7 @@ def sync_single_page(page, direction, dest_root):
if not os.path.exists(dest_dir):
os.makedirs(dest_dir)

with open(dest_path, 'w') as file:
with open(dest_path, 'w', encoding='utf-8') as file:
file.write(fix_whitespace(text))
print('Downloaded {0}'.format(dest_path))

Expand Down
2 changes: 1 addition & 1 deletion index2ddg.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -582,7 +582,7 @@ def main():
# i+=1

root = e.parse(os.path.join(args.reference, fn),
parser=html.HTMLParser())
parser=html.HTMLParser(encoding='utf-8'))

for ident in idents:

Expand Down
2 changes: 1 addition & 1 deletion tests/test_preprocess.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -258,7 +258,7 @@ def setUp(self):
self.testdata = os.path.join(os.path.dirname(__file__),
'preprocess_data')
infile = os.path.join(self.testdata, "fabs.html")
self.parser = etree.HTMLParser()
self.parser = etree.HTMLParser(encoding='utf-8')
self.html = etree.parse(infile, self.parser)

# Check whether the HTML matches the contents of the specified test data
Expand Down
10 changes: 5 additions & 5 deletions tests/test_preprocess_cssless.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,10 +43,10 @@ def test_preprocess_html_merge_cssless(self):

preprocess_html_merge_cssless(src_path, dst_path)

with open(dst_path, 'r') as a_file:
with open(dst_path, 'r', encoding='utf-8') as a_file:
test = a_file.read()

with open(expected_path, 'r') as a_file:
with open(expected_path, 'r', encoding='utf-8') as a_file:
expected = a_file.read()

self.assertEqual(test, expected)
Expand All @@ -63,10 +63,10 @@ def test_preprocess_html_merge_cssless2(self):

preprocess_html_merge_cssless(src_path, dst_path)

with open(dst_path, 'r') as a_file:
with open(dst_path, 'r', encoding='utf-8') as a_file:
test = a_file.read()

with open(expected_path, 'r') as a_file:
with open(expected_path, 'r', encoding='utf-8') as a_file:
expected = a_file.read()

self.assertEqual(test, expected)
Expand All @@ -83,7 +83,7 @@ def assert_converts_html(self, input, expected_output, function):
expected_output = \
'<html><body>{0}</body></html>'.format(expected_output)

parser = etree.HTMLParser()
parser = etree.HTMLParser(encoding='utf-8')
root = etree.fromstring(input, parser)

root = function(root)
Expand Down