Update MD051/link-fragments to use the same character classes as GitHub, encode unprintable characters from emojii.

This commit is contained in:
David Anson 2022-04-18 20:59:01 -07:00
parent db5d9f6dbb
commit 9a5e7e42ef
3 changed files with 34 additions and 7 deletions

View file

@ -18,10 +18,19 @@ const identifierRe = /(?:id|name)\s*=\s*['"]?([^'"\s>]+)/iu;
*/
function convertHeadingToHTMLFragment(inline) {
const inlineText = inline.children.map((token) => token.content).join("");
return "#" + inlineText
.toLowerCase()
.replace(/ /g, "-")
.replace(/[^-_a-z0-9]/g, "");
return "#" + encodeURIComponent(
inlineText
.toLowerCase()
// RegExp source with Ruby's \p{Word} expanded into its General Categories
// eslint-disable-next-line max-len
// https://github.com/gjtorikian/html-pipeline/blob/main/lib/html/pipeline/toc_filter.rb
// https://ruby-doc.org/core-3.0.2/Regexp.html
.replace(
/[^\p{Letter}\p{Mark}\p{Number}\p{Connector_Punctuation}\- ]/gu,
""
)
.replace(/ /gu, "-")
);
}
module.exports = {