Skip to content
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.

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

Add support for backslash escape in wikilinks #471

Merged
merged 3 commits into from
Sep 28, 2024
Merged
Show file tree
Hide file tree
Changes from 2 commits
Commits
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
66 changes: 60 additions & 6 deletions src/parser/inlines.rs
Original file line number Diff line number Diff line change
Expand Up @@ -1730,7 +1730,7 @@ impl<'a, 'r, 'o, 'c, 'd, 'i> Subject<'a, 'r, 'o, 'c, 'd, 'i> {
let startpos = self.pos;
let component = self.wikilink_url_link_label()?;
let url_clean = strings::clean_url(component.url);
let (link_label, link_label_start_column, link_label_end_column) =
let (link_label, link_label_start_column, _link_label_end_column) =
match component.link_label {
Some((label, sc, ec)) => (entity::unescape_html(label), sc, ec),
None => (
Expand All @@ -1744,11 +1744,8 @@ impl<'a, 'r, 'o, 'c, 'd, 'i> Subject<'a, 'r, 'o, 'c, 'd, 'i> {
url: String::from_utf8(url_clean).unwrap(),
};
let inl = self.make_inline(NodeValue::WikiLink(nl), startpos - 1, self.pos - 1);
inl.append(self.make_inline(
NodeValue::Text(String::from_utf8(link_label).unwrap()),
link_label_start_column,
link_label_end_column,
));

self.label_backslash_escapes(inl, link_label, link_label_start_column);

Some(inl)
}
Expand Down Expand Up @@ -1844,6 +1841,63 @@ impl<'a, 'r, 'o, 'c, 'd, 'i> Subject<'a, 'r, 'o, 'c, 'd, 'i> {
true
}

// Given a label, handles backslash escaped characters. Appends the resulting
// nodes to the container
fn label_backslash_escapes(
&mut self,
container: &'a AstNode<'a>,
label: Vec<u8>,
start_column: usize,
) {
let mut startpos = 0;
let mut offset = 0;
let len = label.len();

while offset < len {
let c = label[offset];

if c == b'\\' && (offset + 1) < len && ispunct(label[offset + 1]) {
let preceding_text = self.make_inline(
NodeValue::Text(String::from_utf8(label[startpos..offset].to_owned()).unwrap()),
start_column + startpos,
start_column + offset - 1,
);

container.append(preceding_text);

let inline_text = self.make_inline(
NodeValue::Text(String::from_utf8(vec![label[offset + 1]]).unwrap()),
start_column + offset,
start_column + offset + 1,
);

if self.options.render.escaped_char_spans {
let span = self.make_inline(
NodeValue::Escaped,
start_column + offset,
start_column + offset + 1,
);

span.append(inline_text);
container.append(span);
} else {
container.append(inline_text);
}

offset += 2;
startpos = offset;
} else {
offset += 1;
}
}

container.append(self.make_inline(
Copy link
Owner

Choose a reason for hiding this comment

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

Let's check if startpos != offset here, otherwise we'll append an empty span when a wikilink title ends in an escaped character.

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Great point, thank you @kivikakk. Done.

NodeValue::Text(String::from_utf8(label[startpos..offset].to_owned()).unwrap()),
start_column + startpos,
start_column + offset - 1,
));
}

pub fn spnl(&mut self) {
self.skip_spaces();
if self.skip_line_end() {
Expand Down
24 changes: 23 additions & 1 deletion src/tests/fixtures/wikilinks_title_after_pipe.md
Original file line number Diff line number Diff line change
Expand Up @@ -44,4 +44,26 @@ HTML entities are recognized both in the name of page and in the link title.
[[Gesch&uuml;tztes Leerzeichen|&#xDC;ber &amp;nbsp;]]
.
<p><a href="Gesch%C3%BCtztes%20Leerzeichen" data-wikilink="true">Über &amp;nbsp;</a></p>
````````````````````````````````
````````````````````````````````

Escaping characters is supported

```````````````````````````````` example
[[https://example.org|foo\[\]bar]]
.
<p><a href="https://example.org" data-wikilink="true">foo[]bar</a></p>
````````````````````````````````

```````````````````````````````` example
[[Name \[of\] page]]
.
<p><a href="Name%20%5Bof%5D%20page" data-wikilink="true">Name [of] page</a></p>
````````````````````````````````

Emphasis or other inline markdown is not supported

```````````````````````````````` example
[[Name _of_ page]]
.
<p><a href="Name%20_of_%20page" data-wikilink="true">Name _of_ page</a></p>
````````````````````````````````
24 changes: 23 additions & 1 deletion src/tests/fixtures/wikilinks_title_before_pipe.md
Original file line number Diff line number Diff line change
Expand Up @@ -52,4 +52,26 @@ HTML entities are recognized both in the name of page and in the link title.
[[&#xDC;ber &amp;nbsp;|Gesch&uuml;tztes Leerzeichen]]
.
<p><a href="Gesch%C3%BCtztes%20Leerzeichen" data-wikilink="true">Über &amp;nbsp;</a></p>
````````````````````````````````
````````````````````````````````

Escaping characters is supported

```````````````````````````````` example
[[foo\[\]bar|https://example.org]]
.
<p><a href="https://example.org" data-wikilink="true">foo[]bar</a></p>
````````````````````````````````

```````````````````````````````` example
[[Name \[of\] page]]
.
<p><a href="Name%20%5Bof%5D%20page" data-wikilink="true">Name [of] page</a></p>
````````````````````````````````

Emphasis or other inline markdown is not supported

```````````````````````````````` example
[[Name _of_ page]]
.
<p><a href="Name%20_of_%20page" data-wikilink="true">Name _of_ page</a></p>
````````````````````````````````
26 changes: 26 additions & 0 deletions src/tests/wikilinks.rs
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,16 @@ fn wikilinks_sanitizes_the_href_attribute_case_2() {
);
}

#[test]
fn wikilinks_title_escape_chars() {
html_opts!(
[extension.wikilinks_title_before_pipe, render.escaped_char_spans],
concat!("[[Name \\[of\\] page|http://example.com]]",),
concat!("<p><a href=\"http://example.com\" data-wikilink=\"true\">Name <span data-escaped-char>[</span>of<span data-escaped-char>]</span> page</a></p>\n"),
no_roundtrip,
);
}

#[test]
fn wikilinks_supercedes_relaxed_autolinks() {
html_opts!(
Expand Down Expand Up @@ -228,4 +238,20 @@ fn sourcepos() {
])
])
);

assert_ast_match!(
[extension.wikilinks_title_before_pipe],
"This [[link\\[label|http://example.com]] that\n",
(document (1:1-1:44) [
(paragraph (1:1-1:44) [
(text (1:1-1:5) "This ")
(wikilink (1:6-1:39) [
(text (1:8-1:11) "link")
(text (1:12-1:13) "[")
(text (1:14-1:18) "label")
])
(text (1:40-1:44) " that")
])
])
);
}
Loading