Reorganize to split util

1 files changed, 29 insertions, 0 deletions

diff --git a/src/util/encode.rs b/src/util/encode.rs
new file mode 100644
index 0000000..f79c8ea
--- /dev/null
+++ b/src/util/encode.rs
@@ -0,0 +1,29 @@
+//! Utilities to encode HTML.
+
+/// Encode dangerous html characters.
+///
+/// This ensures that certain characters which have special meaning in HTML are
+/// dealt with.
+/// Technically, we can skip `>` and `"` in many cases, but CM includes them.
+///
+/// This behavior is not explained in prose in `CommonMark` but can be inferred
+/// from the input/output test cases.
+///
+/// ## Examples
+///
+/// ```rust ignore
+/// use micromark::util::encode;
+///
+/// assert_eq!(encode("I <3 🦀"), "I &lt;3 🦀");
+/// ```
+///
+/// ## References
+///
+/// *   [`micromark-util-encode` in `micromark`](https://github.com/micromark/micromark/tree/main/packages/micromark-util-encode)
+pub fn encode(value: &str) -> String {
+    value
+        .replace('&', "&amp;")
+        .replace('"', "&quot;")
+        .replace('<', "&lt;")
+        .replace('>', "&gt;")
+}