Skip to content

Escape octet in string #1824

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
merged 4 commits into from
Mar 21, 2020
Merged

Escape octet in string #1824

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d6a8aeb
Remove expected failure from passing test
palaviv Mar 21, 2020
a2e85af
Escape octet in string
palaviv Mar 21, 2020
e436e42
Merge lex_byte into lex_string
palaviv Mar 21, 2020
0444c1a
Fix clippy warning
palaviv Mar 21, 2020
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
2 changes: 0 additions & 2 deletions Lib/test/test_bytes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -834,8 +834,6 @@ def test_xjust_int_error(self):
self.assertRaises(TypeError, self.type2test(b'abc').ljust, 7, 32)
self.assertRaises(TypeError, self.type2test(b'abc').rjust, 7, 32)

# TODO: RUSTPYTHON
@unittest.expectedFailure
def test_ord(self):
b = self.type2test(b'\0A\x7f\x80\xff')
self.assertEqual([ord(b[i:i+1]) for i in range(len(b))],
Expand Down
125 changes: 23 additions & 102 deletions parser/src/lexer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -462,6 +462,19 @@ where
}
}

fn parse_octet(&mut self, first: char) -> char {
let mut octet_content = String::new();
octet_content.push(first);
while octet_content.len() < 3 {
if let Some('0'..='7') = self.chr0 {
octet_content.push(self.next_char().unwrap())
} else {
break;
}
}
u8::from_str_radix(&octet_content, 8).unwrap() as char
}

fn lex_string(
&mut self,
is_bytes: bool,
Expand Down Expand Up @@ -521,8 +534,9 @@ where
}
Some('u') => string_content.push(self.unicode_literal(4)?),
Some('U') => string_content.push(self.unicode_literal(8)?),
Some('x') if !is_bytes => string_content.push(self.unicode_literal(2)?),
Some('x') => string_content.push(self.unicode_literal(2)?),
Some('v') => string_content.push('\x0b'),
Some(o @ '0'..='7') => string_content.push(self.parse_octet(o)),
Some(c) => {
string_content.push('\\');
string_content.push(c);
Expand Down Expand Up @@ -552,7 +566,7 @@ where
break;
}
} else {
if c == '\n' && !triple_quoted {
if (c == '\n' && !triple_quoted) || (is_bytes && !c.is_ascii()) {
return Err(LexicalError {
error: LexicalErrorType::StringError,
location: self.get_pos(),
Expand All @@ -572,21 +586,8 @@ where
let end_pos = self.get_pos();

let tok = if is_bytes {
if string_content.is_ascii() {
let value = if is_raw {
string_content.into_bytes()
} else {
lex_byte(string_content).map_err(|error| LexicalError {
error,
location: self.get_pos(),
})?
};
Tok::Bytes { value }
} else {
return Err(LexicalError {
error: LexicalErrorType::StringError,
location: self.get_pos(),
});
Tok::Bytes {
value: string_content.chars().map(|c| c as u8).collect(),
}
} else {
Tok::String {
Expand Down Expand Up @@ -1231,90 +1232,6 @@ where
}
}

#[derive(Debug)]
enum EscapeMode {
NORMAL,
HEX,
OCTET,
}

fn lex_byte(s: String) -> Result<Vec<u8>, LexicalErrorType> {
let mut res = vec![];
let mut escape: Option<EscapeMode> = None;
let mut escape_buffer = String::new();

let mut chars_iter = s.chars();
let mut next_char = chars_iter.next();

while let Some(c) = next_char {
match escape {
Some(EscapeMode::OCTET) => {
if let '0'..='7' = c {
escape_buffer.push(c);
next_char = chars_iter.next();
if escape_buffer.len() < 3 {
continue;
}
}
res.push(u8::from_str_radix(&escape_buffer, 8).unwrap());
escape = None;
escape_buffer.clear();
}
Some(EscapeMode::HEX) => {
if c.is_ascii_hexdigit() {
if escape_buffer.is_empty() {
escape_buffer.push(c);
} else {
escape_buffer.push(c);
res.push(u8::from_str_radix(&escape_buffer, 16).unwrap());
escape = None;
escape_buffer.clear();
}
next_char = chars_iter.next();
} else {
return Err(LexicalErrorType::StringError);
}
}
Some(EscapeMode::NORMAL) => {
match c {
'\\' => res.push(b'\\'),
'x' => {
escape = Some(EscapeMode::HEX);
next_char = chars_iter.next();
continue;
}
't' => res.push(b'\t'),
'n' => res.push(b'\n'),
'r' => res.push(b'\r'),
'0'..='7' => {
escape = Some(EscapeMode::OCTET);
continue;
}
x => {
res.push(b'\\');
res.push(x as u8);
}
}
escape = None;
next_char = chars_iter.next();
}
None => {
match c {
'\\' => escape = Some(EscapeMode::NORMAL),
x => res.push(x as u8),
}
next_char = chars_iter.next();
}
}
}
match escape {
Some(EscapeMode::OCTET) => res.push(u8::from_str_radix(&escape_buffer, 8).unwrap()),
Some(EscapeMode::HEX) => return Err(LexicalErrorType::StringError),
_ => (),
}
Ok(res)
}

#[cfg(test)]
mod tests {
use super::{make_tokenizer, NewlineHandler, Tok};
Expand Down Expand Up @@ -1642,7 +1559,7 @@ mod tests {

#[test]
fn test_string() {
let source = r#""double" 'single' 'can\'t' "\\\"" '\t\r\n' '\g' r'raw\''"#;
let source = r#""double" 'single' 'can\'t' "\\\"" '\t\r\n' '\g' r'raw\'' '\200\0a'"#;
let tokens = lex_source(source);
assert_eq!(
tokens,
Expand Down Expand Up @@ -1675,6 +1592,10 @@ mod tests {
value: String::from("raw\'"),
is_fstring: false,
},
Tok::String {
value: String::from("\u{80}\u{0}a"),
is_fstring: false,
},
Tok::Newline,
]
);
Expand Down