HigherOrderCO/Bend
1
1
Fork 0
mirror of https://github.com/HigherOrderCO/Bend.git synced 2024-11-04 01:20:56 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add upper unicode escape syntax

Browse Source
This commit is contained in:
imaqtkatt 2024-01-11 10:37:21 -03:00
parent 1fa587400d
commit 24d14bef86
2 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/term/parser/lexer.rs
View File

@ -36,7 +36,8 @@ pub enum Token {
#[regex(r#""([^"\\]|\\t|\\u|\\n|\\")*""#, |lex| normalized_string(lex).ok())]
Str(String),
#[regex(r#"'(.|\\t|\\u[0-9a-fA-F]{1,8}|\\n|\\')'"#, normalized_char)]
#[regex(r#"'\\U[0-9a-fA-F]{1,8}'"#, normalized_char, priority = 2)]
#[regex(r#"'(.|\\t|\\u[0-9a-fA-F]{1,4}|\\n|\\')'"#, normalized_char)]
Char(u64),
#[token("#")]
@ -144,7 +145,7 @@ fn normalized_string(lexer: &mut Lexer<Token>) -> Result<String, ParseIntError>
'\\' => match chars.next() {
Some('n') => s.push('\n'),
Some('t') => s.push('\t'),
Some('u') => {
Some('u') | Some('U') => {
let hex = chars.take(8).collect::<String>();
let hex_val = u32::from_str_radix(&hex, 16)?;
let char = char::from_u32(hex_val).unwrap_or(char::REPLACEMENT_CHARACTER);
@ -218,7 +219,7 @@ fn normalized_char(lexer: &mut Lexer<Token>) -> Option<u64> {
Some('n') => '\n',
Some('t') => '\t',
Some('\'') => '\'',
Some('u') => {
Some('u') | Some('U') => {
let hex = chars.take(8).collect::<String>();
let hex_val = u32::from_str_radix(&hex, 16).unwrap();
char::from_u32(hex_val).unwrap_or(char::REPLACEMENT_CHARACTER)

2
tests/golden_tests/run_file/world.hvm
View File

@ -1 +1 @@
main = (1, @#str s ('\u1F30E', s))
main = (1, @#str s ('\U1F30E', s))