bjoernager/rust
bjoernager/rust
1
Fork 0
Code Activity

libsyntax: Forbid escapes in the inclusive range \x80-\xff in

Browse source 
Unicode characters and strings.

Use `\u0080`-`\u00ff` instead. ASCII/byte literals are unaffected.

This PR introduces a new function, `escape_default`, into the ASCII
module. This was necessary for the pretty printer to continue to
function.

RFC #326.

Closes #18062.

[breaking-change]
This commit is contained in:
Patrick Walton 2014-10-27 09:13:51 -07:00
parent bb70ee56db
commit e8d6031c71
12 changed files with 4276 additions and 4191 deletions
Download patch file Download diff file Expand all files Collapse all files

23
src/libsyntax/parse/lexer/mod.rs
View file

@ -720,7 +720,11 @@ impl<'a> StringReader<'a> {
/// Scan over `n_digits` hex digits, stopping at `delim`, reporting an
/// error if too many or too few digits are encountered.
fn scan_hex_digits(&mut self, n_digits: uint, delim: char) -> bool {
fn scan_hex_digits(&mut self,
n_digits: uint,
delim: char,
below_0x7f_only: bool)
-> bool {
debug!("scanning {} digits until {}", n_digits, delim);
let start_bpos = self.last_pos;
let mut accum_int = 0;
@ -745,6 +749,13 @@ impl<'a> StringReader<'a> {
self.bump();
}
if below_0x7f_only && accum_int >= 0x80 {
self.err_span_(start_bpos,
self.last_pos,
"this form of character escape may only be used \
with characters in the range [\\x00-\\x7f]");
}
match char::from_u32(accum_int) {
Some(_) => true,
None => {
@ -773,9 +784,13 @@ impl<'a> StringReader<'a> {
Some(e) => {
return match e {
'n' | 'r' | 't' | '\\' | '\'' | '"' | '0' => true,
'x' => self.scan_hex_digits(2u, delim),
'u' if !ascii_only => self.scan_hex_digits(4u, delim),
'U' if !ascii_only => self.scan_hex_digits(8u, delim),
'x' => self.scan_hex_digits(2u, delim, !ascii_only),
'u' if !ascii_only => {
self.scan_hex_digits(4u, delim, false)
}
'U' if !ascii_only => {
self.scan_hex_digits(8u, delim, false)
}
'\n' if delim == '"' => {
self.consume_whitespace();
true