pub fn tokenize<'a>(input: &'a str) -> Vec<Token<'a>>Expand description
Tokenize an HTML string into a sequence of tokens.
Convenience wrapper that runs both pipeline stages:
- SIMD structural indexing
- State-machine token extraction
ยงExample
use fhp_tokenizer::tokenize;
use fhp_tokenizer::token::Token;
let tokens = tokenize("<p>Hello & world</p>");
// Should contain OpenTag, Text, CloseTag
assert!(tokens.iter().any(|t| matches!(t, Token::OpenTag { .. })));
assert!(tokens.iter().any(|t| matches!(t, Token::Text { .. })));
assert!(tokens.iter().any(|t| matches!(t, Token::CloseTag { .. })));