Refactor to work on `char`s

Previously, a custom char implementation was used.
This was easier to work with, as sometimes “virtual” characters are injected,
or characters are ignored.

This replaces that with working on actual `char`s.
In the hope of in the future working on `u8`s, even.

This simplifies the state machine somewhat, as only `\n` is fed, regardless of
whether it was a CRLF, CR, or LF.
It also feeds `' '` instead of virtual spaces.

The BOM, if present, is now available as a `ByteOrderMark` event.

1 files changed, 9 insertions, 3 deletions

diff --git a/src/util/encode.rs b/src/util/encode.rs
index 965ea5c..91c5462 100644
--- a/src/util/encode.rs
+++ b/src/util/encode.rs
@@ -20,7 +20,8 @@
 /// ## References
 ///
 /// *   [`micromark-util-encode` in `micromark`](https://github.com/micromark/micromark/tree/main/packages/micromark-util-encode)
-pub fn encode<S: Into<String>>(value: S) -> String {
+pub fn encode<S: Into<String>>(value: S, encode_html: bool) -> String {
+    let check = if encode_html { check_all } else { check_nil };
     let mut value = value.into();
 
     // It’ll grow a bit bigger for each dangerous character.
@@ -31,6 +32,7 @@ pub fn encode<S: Into<String>>(value: S) -> String {
         let dangerous = value.pop().unwrap();
         result.push_str(&value);
         result.push_str(match dangerous {
+            '\0' => "�",
             '&' => "&amp;",
             '"' => "&quot;",
             '<' => "&lt;",
@@ -45,6 +47,10 @@ pub fn encode<S: Into<String>>(value: S) -> String {
     result
 }
 
-fn check(char: char) -> bool {
-    matches!(char, '&' | '"' | '<' | '>')
+fn check_all(char: char) -> bool {
+    matches!(char, '\0' | '&' | '"' | '<' | '>')
+}
+
+fn check_nil(char: char) -> bool {
+    matches!(char, '\0')
 }