Skip to content

Added support for unicode characters #22

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.

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
merged 1 commit into from
Jun 28, 2019
Merged
Changes from all commits
Commits
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
38 changes: 35 additions & 3 deletions src/common.rs
Original file line number Diff line number Diff line change
Expand Up @@ -148,19 +148,37 @@ fn unquote_string(s: &str) -> Result<String, Error<Token, Token>> {
let mut res = String::with_capacity(s.len());
debug_assert!(s.starts_with('"') && s.ends_with('"'));
let mut chars = s[1..s.len()-1].chars();
let mut temp_code_point = String::with_capacity(4);
while let Some(c) = chars.next() {
match c {
'\\' => {
match chars.next().expect("slash cant be and the end") {
match chars.next().expect("slash cant be at the end") {
c@'"' | c@'\\' | c@'/' => res.push(c),
'b' => res.push('\u{0010}'),
'f' => res.push('\u{000C}'),
'n' => res.push('\n'),
'r' => res.push('\r'),
't' => res.push('\t'),
'u' => {
unimplemented!();
}
temp_code_point.clear();
for _ in 0..4 {
match chars.next() {
Some(inner_c) => temp_code_point.push(inner_c),
None => return Err(Error::unexpected_message(
format_args!("\\u must have 4 characters after it, only found '{}'", temp_code_point)
)),
}
}

// convert our hex string into a u32, then convert that into a char
match u32::from_str_radix(&temp_code_point, 16).map(std::char::from_u32) {
Ok(Some(unicode_char)) => res.push(unicode_char),
_ => {
return Err(Error::unexpected_message(
format_args!("{} is not a valid unicode code point", temp_code_point)))
}
}
},
c => {
return Err(Error::unexpected_message(
format_args!("bad escaped char {:?}", c)));
Expand Down Expand Up @@ -263,6 +281,7 @@ pub fn parse_type<'a>(input: &mut TokenStream<'a>)
#[cfg(test)]
mod tests {
use super::Number;
use super::unquote_string;

#[test]
fn number_from_i32_and_to_i64_conversion() {
Expand All @@ -271,4 +290,17 @@ mod tests {
assert_eq!(Number::from(i32::min_value()).as_i64(), Some(i32::min_value() as i64));
assert_eq!(Number::from(i32::max_value()).as_i64(), Some(i32::max_value() as i64));
}

#[test]
fn unquote_unicode_string() {
// basic tests
assert_eq!(unquote_string(r#""\u0009""#).expect(""), "\u{0009}");
assert_eq!(unquote_string(r#""\u000A""#).expect(""), "\u{000A}");
assert_eq!(unquote_string(r#""\u000D""#).expect(""), "\u{000D}");
assert_eq!(unquote_string(r#""\u0020""#).expect(""), "\u{0020}");
assert_eq!(unquote_string(r#""\uFFFF""#).expect(""), "\u{FFFF}");

// a more complex string
assert_eq!(unquote_string(r#""\u0009 hello \u000A there""#).expect(""), "\u{0009} hello \u{000A} there");
}
}