[bugfix] html escape special characters in text instead of totally removing them (#719)

* remove minify dependency

* tidy up some tests

* remove pre + postformat funcs

* rework sanitization + formatting

* update tests

* add some more markdown tests
This commit is contained in:
tobi 2022-07-19 15:21:17 +02:00 committed by GitHub
commit c84384e660
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
51 changed files with 129 additions and 7419 deletions

View file

@ -19,7 +19,9 @@
package text
import (
"html"
"regexp"
"strings"
"github.com/microcosm-cc/bluemonday"
)
@ -59,7 +61,8 @@ func SanitizeHTML(in string) string {
// SanitizePlaintext runs text through basic sanitization. This removes
// any html elements that were in the string, and returns clean plaintext.
func SanitizePlaintext(in string) string {
content := preformat(in)
content := html.UnescapeString(in)
content = removeHTML(content)
return postformat(content)
content = html.UnescapeString(content)
return strings.TrimSpace(content)
}