Skip to content

Forward pyexpat lexical events #8264

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
doma17 wants to merge 1 commit into
base: main
Choose a base branch
from
+38 −2
Open

Forward pyexpat lexical events #8264

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
1 change: 0 additions & 1 deletion Lib/test/test_pyexpat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -560,7 +560,6 @@ def test6(self):
["<a>", "1", "<b>", "</b>", "2", "<c>", "</c>", "345", "</a>"],
"buffered text not properly split")

@unittest.expectedFailure # TODO: RUSTPYTHON
def test7(self):
self.setHandlers(["CommentHandler", "EndElementHandler",
"StartElementHandler"])
Expand Down
18 changes: 17 additions & 1 deletion crates/stdlib/src/pyexpat.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -305,8 +305,9 @@ mod _pyexpat {

fn create_config(&self) -> xml::ParserConfig {
xml::ParserConfig::new()
.cdata_to_characters(true)
.cdata_to_characters(false)
.coalesce_characters(false)
.ignore_comments(false)
.whitespace_to_characters(true)
}

Expand Down Expand Up @@ -376,6 +377,21 @@ mod _pyexpat {
let str = PyStr::from(chars).into_ref(&vm.ctx);
invoke_handler(vm, &self.character_data, (str,));
}
Ok(XmlEvent::ProcessingInstruction { name, data }) => {

@ShaharNaveh ShaharNaveh Jul 12, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I can't comment on things outside the diff. can you please make the match to be:

- match e {
+ match e? {

then we could do:

- Ok(XmlEvent::Foo { .. })
+ XmlEvent::Foo { ..}

let name = PyStr::from(name).into_ref(&vm.ctx);
let data = PyStr::from(data.unwrap_or_default()).into_ref(&vm.ctx);
invoke_handler(vm, &self.processing_instruction, (name, data));
}
Ok(XmlEvent::Comment(comment)) => {
let comment = PyStr::from(comment).into_ref(&vm.ctx);
invoke_handler(vm, &self.comment, (comment,));
}
Ok(XmlEvent::CData(chars)) => {
invoke_handler(vm, &self.start_cdata_section, ());
let str = PyStr::from(chars).into_ref(&vm.ctx);
invoke_handler(vm, &self.character_data, (str,));
invoke_handler(vm, &self.end_cdata_section, ());
}
Err(e) => return Err(e),
_ => {}
}
Expand Down
21 changes: 21 additions & 0 deletions extra_tests/snippets/stdlib_xml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,3 +45,24 @@ def endElement(self, name):
("end", "child"),
("end", "main"),
]

events = []
parser = expat.ParserCreate()
parser.ProcessingInstructionHandler = lambda target, data: events.append(
("processing-instruction", target, data)
)
parser.CommentHandler = lambda data: events.append(("comment", data))
parser.StartCdataSectionHandler = lambda: events.append(("start-cdata",))
parser.CharacterDataHandler = lambda data: events.append(("characters", data))
parser.EndCdataSectionHandler = lambda: events.append(("end-cdata",))
parser.Parse(
"<?target data?><?empty?><root><!--comment--><![CDATA[text]]></root>", True
)
assert events == [
("processing-instruction", "target", "data"),
("processing-instruction", "empty", ""),
("comment", "comment"),
("start-cdata",),
("characters", "text"),
("end-cdata",),
]
Loading