Skip to content

Use ASCII case folding for HTML element and attribute names #200

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
ac1982 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Use ASCII case folding for HTML element and attribute names #200

Show file tree
Hide file tree
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
4 changes: 2 additions & 2 deletions cssselect/xpath.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -420,7 +420,7 @@ def xpath_attrib(self, selector: Attrib) -> XPathExpr:
getattr(self, f"xpath_attrib_{operator}"),
)
if self.lower_case_attribute_names:
name = selector.attrib.lower()
name = ascii_lower(selector.attrib)
else:
name = selector.attrib
if selector.namespace == "*":
Expand Down Expand Up @@ -470,7 +470,7 @@ def xpath_element(self, selector: Element) -> XPathExpr:
else:
safe = bool(is_safe_name(element))
if self.lower_case_element_names:
element = element.lower()
element = ascii_lower(element)
if selector.namespace == "*":
# Namespace wildcard, e.g. "*|div": any namespace,
# including none. XPath 1.0 has no "*:name" name test
Expand Down
26 changes: 26 additions & 0 deletions tests/test_cssselect.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1361,6 +1361,32 @@ def argument_types(css: str) -> list[str]:
css = f"::pseudo_element({argument_string})"
assert argument_types(css) == argument_list

def test_html_non_ascii_element_names(self) -> None:
document = html.fromstring(
'<div><x-Ä id="upper"></x-Ä><x-ä id="lower"></x-ä></div>'
)
translator = HTMLTranslator()
for selector in ("x-Ä", "X-Ä", "*|X-Ä"):
elements = typing.cast(
"list[etree._Element]",
document.xpath(translator.css_to_xpath(selector)),
)
assert [element.get("id") for element in elements] == ["upper"]
assert len(document.xpath(translator.css_to_xpath("X-ä"))) == 1

def test_html_non_ascii_attribute_names(self) -> None:
document = html.fromstring(
'<div><p id="upper" DATA-Ä="yes"></p><p id="lower" data-ä="yes"></p></div>'
)
translator = HTMLTranslator()
for selector in ("[DATA-Ä]", '[DATA-Ä="yes"]', "[*|DATA-Ä]"):
elements = typing.cast(
"list[etree._Element]",
document.xpath(translator.css_to_xpath(selector)),
)
assert [element.get("id") for element in elements] == ["upper"]
assert len(document.xpath(translator.css_to_xpath('[DATA-ä="yes"]'))) == 1

def test_select(self) -> None:
document = etree.fromstring(HTML_IDS)
sort_key = {el: count for count, el in enumerate(document.iter())}.__getitem__
Expand Down