break!: emit chars instead of strings

The HTML spec specifies that the tokenizer emits character tokens.
That html5gum always emitted strings instead was probably just done
to make the token consumption more convenient. When it comes to tree
construction character tokens are however actually more convenient
than string tokens since the spec defines that specific character
tokens should be ignored in specific states (and character tokens
let us avoid string manipulation for these conditions).

This should also make the DefaultEmitter more performant for cases
where you don't actually need the strings at all (or only a few)
since it avoids string allocations. Though I haven't benchmarked it.

1 files changed, 7 insertions, 6 deletions

diff --git a/src/tokenizer/machine/utils.rs b/src/tokenizer/machine/utils.rs
index d96e50b..ea4d697 100644
--- a/src/tokenizer/machine/utils.rs
+++ b/src/tokenizer/machine/utils.rs
@@ -16,7 +16,7 @@ where
     /// Emits the given character as a character token.
     #[inline]
     pub(super) fn emit_char(&mut self, c: char) {
-        self.emitter.emit_string(ctostr!(c));
+        self.emitter.emit_char(c);
     }
 
     /// Emits every byte of the given byte slice as a character token.
@@ -25,10 +25,9 @@ where
     /// since [`str::chars`] isn't `const`.)
     #[inline]
     pub(super) fn emit_chars(&mut self, s: &[u8]) {
-        self.emitter.emit_string(
-            // this unsafe block is only temporary and will be removed in the next commit
-            unsafe { std::str::from_utf8_unchecked(s) },
-        );
+        for c in s {
+            self.emit_char(*c as char);
+        }
     }
 
     #[inline]
@@ -204,7 +203,9 @@ where
     }
 
     pub(super) fn flush_buffer_characters(&mut self) {
-        self.emitter.emit_string(&self.temporary_buffer);
+        for c in self.temporary_buffer.chars() {
+            self.emitter.emit_char(c);
+        }
         self.temporary_buffer.clear();
     }
 }