Skip to content

Use a &str for the input instead of a Vec<Char> in the tokenizer #89

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
valenting merged 1 commit into from
Jan 23, 2026
Merged

Use a &str for the input instead of a Vec<Char> in the tokenizer #89

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 1 addition & 6 deletions src/constructor_parser.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -231,12 +231,7 @@ impl<'a> ConstructorStringParser<'a> {
let token = &self.token_list[self.token_index];
let component_start_index = self.get_safe_token(self.component_start).index;

self
.input
.chars()
.skip(component_start_index)
.take(token.index - component_start_index)
.collect()
self.input[component_start_index..token.index].to_owned()
}

// Ref: https://wicg.github.io/urlpattern/#rewind-and-set-state
Expand Down
16 changes: 8 additions & 8 deletions src/tokenizer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,21 +41,22 @@ pub enum TokenizePolicy {
}

// Ref: https://wicg.github.io/urlpattern/#tokenizer
struct Tokenizer {
input: Vec<char>,
struct Tokenizer<'a> {
input: &'a str,
policy: TokenizePolicy,
token_list: Vec<Token>,
index: usize,
next_index: usize,
code_point: Option<char>, // TODO: get rid of Option
}

impl Tokenizer {
impl<'a> Tokenizer<'a> {
// Ref: https://wicg.github.io/urlpattern/#get-the-next-code-point
#[inline]
fn get_next_codepoint(&mut self) {
self.code_point = Some(self.input[self.next_index]);
self.next_index += 1;
let next_char = self.input[self.next_index..].chars().next().unwrap();
self.code_point = Some(next_char);
self.next_index += next_char.len_utf8();
}

// Ref: https://wicg.github.io/urlpattern/#add-a-token-with-default-position-and-length
Expand Down Expand Up @@ -85,7 +86,7 @@ impl Tokenizer {
value_len: usize,
) {
let range = value_pos..(value_pos + value_len);
let value = self.input[range].iter().collect::<String>();
let value = self.input[range].to_owned();
self.token_list.push(Token {
kind,
index: self.index,
Expand Down Expand Up @@ -127,7 +128,7 @@ pub fn tokenize(
policy: TokenizePolicy,
) -> Result<Vec<Token>, Error> {
let mut tokenizer = Tokenizer {
input: input.chars().collect::<Vec<char>>(),
input,
policy,
token_list: vec![],
index: 0,
Expand Down Expand Up @@ -318,7 +319,6 @@ pub fn tokenize(

tokenizer.add_token_with_default_pos_and_len(TokenType::Char);
}

tokenizer.add_token_with_default_len(
TokenType::End,
tokenizer.index,
Expand Down