Fix for escaping backslashes in interpolated strings (fixes #6737) (#7119)

Co-authored-by: Gavin Foley <gavinmfoley@gmail.com>
This commit is contained in:
Gavin Foley 2022-12-14 08:54:13 -05:00 committed by GitHub
parent 0db4d89838
commit 98b9839e3d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 288 additions and 68 deletions

View File

@ -1639,42 +1639,52 @@ pub fn parse_string_interpolation(
let mut token_start = start;
let mut delimiter_stack = vec![];
let mut consecutive_backslashes: usize = 0;
let mut b = start;
while b != end {
if contents[b - start] == b'('
&& (if double_quote && (b - start) > 0 {
contents[b - start - 1] != b'\\'
let current_byte = contents[b - start];
if mode == InterpolationMode::String {
let preceding_consecutive_backslashes = consecutive_backslashes;
let is_backslash = current_byte == b'\\';
consecutive_backslashes = if is_backslash {
preceding_consecutive_backslashes + 1
} else {
true
})
&& mode == InterpolationMode::String
{
mode = InterpolationMode::Expression;
if token_start < b {
let span = Span::new(token_start, b);
let str_contents = working_set.get_span_contents(span);
0
};
let str_contents = if double_quote {
let (str_contents, err) = unescape_string(str_contents, span);
error = error.or(err);
if current_byte == b'(' && (!double_quote || preceding_consecutive_backslashes % 2 == 0)
{
mode = InterpolationMode::Expression;
if token_start < b {
let span = Span::new(token_start, b);
let str_contents = working_set.get_span_contents(span);
str_contents
} else {
str_contents.to_vec()
};
let str_contents = if double_quote {
let (str_contents, err) = unescape_string(str_contents, span);
error = error.or(err);
output.push(Expression {
expr: Expr::String(String::from_utf8_lossy(&str_contents).to_string()),
span,
ty: Type::String,
custom_completion: None,
});
token_start = b;
str_contents
} else {
str_contents.to_vec()
};
output.push(Expression {
expr: Expr::String(String::from_utf8_lossy(&str_contents).to_string()),
span,
ty: Type::String,
custom_completion: None,
});
token_start = b;
}
}
}
if mode == InterpolationMode::Expression {
let byte = contents[b - start];
let byte = current_byte;
if let Some(b'\'') = delimiter_stack.last() {
if byte == b'\'' {
delimiter_stack.pop();

View File

@ -210,48 +210,6 @@ pub fn parse_binary_with_multi_byte_char() {
}
}
#[test]
pub fn parse_string() {
let engine_state = EngineState::new();
let mut working_set = StateWorkingSet::new(&engine_state);
let (block, err) = parse(&mut working_set, None, b"\"hello nushell\"", true, &[]);
assert!(err.is_none());
assert!(block.len() == 1);
let expressions = &block[0];
assert!(expressions.len() == 1);
if let PipelineElement::Expression(_, expr) = &expressions[0] {
assert_eq!(expr.expr, Expr::String("hello nushell".to_string()))
} else {
panic!("Not an expression")
}
}
#[test]
pub fn parse_escaped_string() {
let engine_state = EngineState::new();
let mut working_set = StateWorkingSet::new(&engine_state);
let (block, err) = parse(
&mut working_set,
None,
b"\"hello \\u006e\\u0075\\u0073hell\"",
true,
&[],
);
assert!(err.is_none());
assert!(block.len() == 1);
let expressions = &block[0];
assert!(expressions.len() == 1);
if let PipelineElement::Expression(_, expr) = &expressions[0] {
assert_eq!(expr.expr, Expr::String("hello nushell".to_string()))
} else {
panic!("Not an expression")
}
}
#[test]
pub fn parse_call() {
let engine_state = EngineState::new();
@ -410,6 +368,258 @@ fn test_nothing_comparisson_neq() {
))
}
mod string {
use super::*;
#[test]
pub fn parse_string() {
let engine_state = EngineState::new();
let mut working_set = StateWorkingSet::new(&engine_state);
let (block, err) = parse(&mut working_set, None, b"\"hello nushell\"", true, &[]);
assert!(err.is_none());
assert!(block.len() == 1);
let expressions = &block[0];
assert!(expressions.len() == 1);
if let PipelineElement::Expression(_, expr) = &expressions[0] {
assert_eq!(expr.expr, Expr::String("hello nushell".to_string()))
} else {
panic!("Not an expression")
}
}
#[test]
pub fn parse_escaped_string() {
let engine_state = EngineState::new();
let mut working_set = StateWorkingSet::new(&engine_state);
let (block, err) = parse(
&mut working_set,
None,
b"\"hello \\u006e\\u0075\\u0073hell\"",
true,
&[],
);
assert!(err.is_none());
assert!(block.len() == 1);
let expressions = &block[0];
assert!(expressions.len() == 1);
if let PipelineElement::Expression(_, expr) = &expressions[0] {
assert_eq!(expr.expr, Expr::String("hello nushell".to_string()))
} else {
panic!("Not an expression")
}
}
mod interpolation {
use nu_protocol::Span;
use super::*;
#[test]
pub fn parse_string_interpolation() {
let engine_state = EngineState::new();
let mut working_set = StateWorkingSet::new(&engine_state);
let (block, err) = parse(&mut working_set, None, b"$\"hello (39 + 3)\"", true, &[]);
assert!(err.is_none());
assert!(block.len() == 1);
let expressions = &block[0];
assert!(expressions.len() == 1);
if let PipelineElement::Expression(_, expr) = &expressions[0] {
let subexprs: Vec<&Expr>;
match expr {
Expression {
expr: Expr::StringInterpolation(expressions),
..
} => {
subexprs = expressions.iter().map(|e| &e.expr).collect();
}
_ => panic!("Expected an `Expr::StringInterpolation`"),
}
assert_eq!(subexprs.len(), 2);
assert_eq!(subexprs[0], &Expr::String("hello ".to_string()));
assert!(matches!(subexprs[1], &Expr::FullCellPath(..)));
} else {
panic!("Not an expression")
}
}
#[test]
pub fn parse_string_interpolation_escaped_parenthesis() {
let engine_state = EngineState::new();
let mut working_set = StateWorkingSet::new(&engine_state);
let (block, err) = parse(&mut working_set, None, b"$\"hello \\(39 + 3)\"", true, &[]);
assert!(err.is_none());
assert!(block.len() == 1);
let expressions = &block[0];
assert!(expressions.len() == 1);
if let PipelineElement::Expression(_, expr) = &expressions[0] {
let subexprs: Vec<&Expr>;
match expr {
Expression {
expr: Expr::StringInterpolation(expressions),
..
} => {
subexprs = expressions.iter().map(|e| &e.expr).collect();
}
_ => panic!("Expected an `Expr::StringInterpolation`"),
}
assert_eq!(subexprs.len(), 1);
assert_eq!(subexprs[0], &Expr::String("hello (39 + 3)".to_string()));
} else {
panic!("Not an expression")
}
}
#[test]
pub fn parse_string_interpolation_escaped_backslash_before_parenthesis() {
let engine_state = EngineState::new();
let mut working_set = StateWorkingSet::new(&engine_state);
let (block, err) = parse(
&mut working_set,
None,
b"$\"hello \\\\(39 + 3)\"",
true,
&[],
);
assert!(err.is_none());
assert!(block.len() == 1);
let expressions = &block[0];
assert!(expressions.len() == 1);
if let PipelineElement::Expression(_, expr) = &expressions[0] {
let subexprs: Vec<&Expr>;
match expr {
Expression {
expr: Expr::StringInterpolation(expressions),
..
} => {
subexprs = expressions.iter().map(|e| &e.expr).collect();
}
_ => panic!("Expected an `Expr::StringInterpolation`"),
}
assert_eq!(subexprs.len(), 2);
assert_eq!(subexprs[0], &Expr::String("hello \\".to_string()));
assert!(matches!(subexprs[1], &Expr::FullCellPath(..)));
} else {
panic!("Not an expression")
}
}
#[test]
pub fn parse_string_interpolation_backslash_count_reset_by_expression() {
let engine_state = EngineState::new();
let mut working_set = StateWorkingSet::new(&engine_state);
let (block, err) = parse(
&mut working_set,
None,
b"$\"\\(1 + 3)\\(7 - 5)\"",
true,
&[],
);
assert!(err.is_none());
assert!(block.len() == 1);
let expressions = &block[0];
assert!(expressions.len() == 1);
if let PipelineElement::Expression(_, expr) = &expressions[0] {
let subexprs: Vec<&Expr>;
match expr {
Expression {
expr: Expr::StringInterpolation(expressions),
..
} => {
subexprs = expressions.iter().map(|e| &e.expr).collect();
}
_ => panic!("Expected an `Expr::StringInterpolation`"),
}
assert_eq!(subexprs.len(), 1);
assert_eq!(subexprs[0], &Expr::String("(1 + 3)(7 - 5)".to_string()));
} else {
panic!("Not an expression")
}
}
#[test]
pub fn parse_nested_expressions() {
let engine_state = EngineState::new();
let mut working_set = StateWorkingSet::new(&engine_state);
working_set.add_variable(
"foo".to_string().into_bytes(),
Span::new(0, 0),
nu_protocol::Type::CellPath,
false,
);
let (_block, err) = parse(
&mut working_set,
None,
br#"
$"(($foo))"
"#,
true,
&[],
);
assert!(err.is_none());
}
#[test]
pub fn parse_path_expression() {
let engine_state = EngineState::new();
let mut working_set = StateWorkingSet::new(&engine_state);
working_set.add_variable(
"foo".to_string().into_bytes(),
Span::new(0, 0),
nu_protocol::Type::CellPath,
false,
);
let (_block, err) = parse(
&mut working_set,
None,
br#"
$"Hello ($foo.bar)"
"#,
true,
&[],
);
assert!(err.is_none());
}
}
}
mod range {
use super::*;
use nu_protocol::ast::{RangeInclusion, RangeOperator};