[xermicus]

Closes #708

[elle-j]

We should probably unify the escape decoding logic and just have it owned by the yul crate's String (most of what's in the current String::unescape).

E.g. the loop logic from String::unescape could be shared and probably replace all of:

• crates/yul/src/parser/statement/expression/literal.rs:

revive/crates/yul/src/parser/statement/expression/literal.rs

Lines 141 to 195 in 304cad8

	let mut hex_string = String::with_capacity(BYTE_LENGTH_WORD * 2);
	let mut index = 0;
	loop {
	if index >= string.len() {
	break;
	}
	if string[index..].starts_with('\\') {
	index += 1;
	if string[index..].starts_with('x') {
	hex_string.push_str(&string[index + 1..index + 3]);
	index += 3;
	} else if string[index..].starts_with('u') {
	let codepoint_str = &string[index + 1..index + 5];
	let codepoint =
	u32::from_str_radix(codepoint_str, BASE_HEXADECIMAL).map_err(
	|error| {
	anyhow::anyhow!(
	"Invalid codepoint `{}`: {}",
	codepoint_str,
	error
	)
	},
	)?;
	let unicode_char = char::from_u32(codepoint).ok_or_else(|| {
	anyhow::anyhow!("Invalid codepoint {}", codepoint)
	})?;
	for byte in unicode_char.to_string().bytes() {
	hex_string.push_str(format!("{byte:02x}").as_str());
	}
	index += 5;
	} else if string[index..].starts_with('t') {
	hex_string.push_str("09");
	index += 1;
	} else if string[index..].starts_with('n') {
	hex_string.push_str("0a");
	index += 1;
	} else if string[index..].starts_with('r') {
	hex_string.push_str("0d");
	index += 1;
	} else if string[index..].starts_with('\n') {
	index += 1;
	} else {
	hex_string
	.push_str(format!("{:02x}", string.as_bytes()[index]).as_str());
	index += 1;
	}
	} else {
	hex_string
	.push_str(format!("{:02x}", string.as_bytes()[index]).as_str());
	index += 1;
	}
	}
	hex_string

• crates/newyork/src/from_yul.rs:

revive/crates/newyork/src/from_yul.rs

Lines 1438 to 1497 in 304cad8

	let mut hex = std::string::String::with_capacity(64);
	let mut index = 0;
	let bytes = string.as_bytes();
	while index < bytes.len() {
	if bytes[index] == b'\\' {
	index += 1;
	if index >= bytes.len() {
	break;
	}
	match bytes[index] {
	b'x' => {
	if index + 2 < bytes.len() {
	hex.push(bytes[index + 1] as char);
	hex.push(bytes[index + 2] as char);
	}
	index += 3;
	}
	b'u' => {
	if index + 4 < bytes.len() {
	let code_point_string = &string[index + 1..index + 5];
	if let Ok(codepoint) =
	u32::from_str_radix(code_point_string, 16)
	{
	if let Some(character) = char::from_u32(codepoint) {
	let mut buffer = [0u8; 4];
	let encoded = character.encode_utf8(&mut buffer);
	for byte in encoded.bytes() {
	hex.push_str(&format!("{byte:02x}"));
	}
	}
	}
	}
	index += 5;
	}
	b't' => {
	hex.push_str("09");
	index += 1;
	}
	b'n' => {
	hex.push_str("0a");
	index += 1;
	}
	b'r' => {
	hex.push_str("0d");
	index += 1;
	}
	b'\n' => {
	index += 1;
	}
	other => {
	hex.push_str(&format!("{other:02x}"));
	index += 1;
	}
	}
	} else {
	hex.push_str(&format!("{:02x}", bytes[index]));
	index += 1;
	}
	}
	hex

[xermicus]

will be addressed in #724