Add an implicit concatenation flag to string and bytes constants (#6512)

## Summary

Per the discussion in
https://github.com/astral-sh/ruff/discussions/6183, this PR adds an
`implicit_concatenated` flag to the string and bytes constant variants.
It's not actually _used_ anywhere as of this PR, but it is covered by
the tests.

Specifically, we now use a struct for the string and bytes cases, along
with the `Expr::FString` node. That struct holds the value, plus the
flag:

```rust
#[derive(Clone, Debug, PartialEq, is_macro::Is)]
pub enum Constant {
    Str(StringConstant),
    Bytes(BytesConstant),
    ...
}

#[derive(Clone, Debug, PartialEq, Eq)]
pub struct StringConstant {
    /// The string value as resolved by the parser (i.e., without quotes, or escape sequences, or
    /// implicit concatenations).
    pub value: String,
    /// Whether the string contains multiple string tokens that were implicitly concatenated.
    pub implicit_concatenated: bool,
}

impl Deref for StringConstant {
    type Target = str;
    fn deref(&self) -> &Self::Target {
        self.value.as_str()
    }
}

#[derive(Clone, Debug, PartialEq, Eq)]
pub struct BytesConstant {
    /// The bytes value as resolved by the parser (i.e., without quotes, or escape sequences, or
    /// implicit concatenations).
    pub value: Vec<u8>,
    /// Whether the string contains multiple string tokens that were implicitly concatenated.
    pub implicit_concatenated: bool,
}

impl Deref for BytesConstant {
    type Target = [u8];
    fn deref(&self) -> &Self::Target {
        self.value.as_slice()
    }
}
```

## Test Plan

`cargo test`
This commit is contained in:
Charlie Marsh 2023-08-14 09:46:54 -04:00 committed by GitHub
parent fc0c9507d0
commit f16e780e0a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
88 changed files with 1252 additions and 761 deletions

View file

@ -24,7 +24,7 @@ where
fn add_to_names<'a>(elts: &'a [Expr], names: &mut Vec<&'a str>, flags: &mut DunderAllFlags) {
for elt in elts {
if let Expr::Constant(ast::ExprConstant {
value: Constant::Str(value),
value: Constant::Str(ast::StringConstant { value, .. }),
..
}) = elt
{

View file

@ -326,8 +326,18 @@ impl<'a> From<&'a ast::Constant> for ComparableConstant<'a> {
match constant {
ast::Constant::None => Self::None,
ast::Constant::Bool(value) => Self::Bool(value),
ast::Constant::Str(value) => Self::Str(value),
ast::Constant::Bytes(value) => Self::Bytes(value),
ast::Constant::Str(ast::StringConstant {
value,
// Compare strings based on resolved value, not representation (i.e., ignore whether
// the string was implicitly concatenated).
implicit_concatenated: _,
}) => Self::Str(value),
ast::Constant::Bytes(ast::BytesConstant {
value,
// Compare bytes based on resolved value, not representation (i.e., ignore whether
// the bytes were implicitly concatenated).
implicit_concatenated: _,
}) => Self::Bytes(value),
ast::Constant::Int(value) => Self::Int(value),
ast::Constant::Float(value) => Self::Float(value.to_bits()),
ast::Constant::Complex { real, imag } => Self::Complex {
@ -865,11 +875,13 @@ impl<'a> From<&'a ast::Expr> for ComparableExpr<'a> {
debug_text: debug_text.as_ref(),
format_spec: format_spec.as_ref().map(Into::into),
}),
ast::Expr::FString(ast::ExprFString { values, range: _ }) => {
Self::FString(ExprFString {
values: values.iter().map(Into::into).collect(),
})
}
ast::Expr::FString(ast::ExprFString {
values,
implicit_concatenated: _,
range: _,
}) => Self::FString(ExprFString {
values: values.iter().map(Into::into).collect(),
}),
ast::Expr::Constant(ast::ExprConstant {
value,
kind,

View file

@ -123,10 +123,8 @@ where
return true;
}
match expr {
Expr::BoolOp(ast::ExprBoolOp {
values, range: _, ..
})
| Expr::FString(ast::ExprFString { values, range: _ }) => {
Expr::BoolOp(ast::ExprBoolOp { values, .. })
| Expr::FString(ast::ExprFString { values, .. }) => {
values.iter().any(|expr| any_over_expr(expr, func))
}
Expr::NamedExpr(ast::ExprNamedExpr {
@ -1087,25 +1085,26 @@ impl Truthiness {
Expr::Constant(ast::ExprConstant { value, .. }) => match value {
Constant::Bool(value) => Some(*value),
Constant::None => Some(false),
Constant::Str(string) => Some(!string.is_empty()),
Constant::Str(ast::StringConstant { value, .. }) => Some(!value.is_empty()),
Constant::Bytes(bytes) => Some(!bytes.is_empty()),
Constant::Int(int) => Some(!int.is_zero()),
Constant::Float(float) => Some(*float != 0.0),
Constant::Complex { real, imag } => Some(*real != 0.0 || *imag != 0.0),
Constant::Ellipsis => Some(true),
},
Expr::FString(ast::ExprFString { values, range: _ }) => {
Expr::FString(ast::ExprFString { values, .. }) => {
if values.is_empty() {
Some(false)
} else if values.iter().any(|value| {
let Expr::Constant(ast::ExprConstant {
value: Constant::Str(string),
if let Expr::Constant(ast::ExprConstant {
value: Constant::Str(ast::StringConstant { value, .. }),
..
}) = &value
else {
return false;
};
!string.is_empty()
{
!value.is_empty()
} else {
false
}
}) {
Some(true)
} else {

View file

@ -2676,7 +2676,11 @@ impl AstNode for ast::ExprFString {
where
V: PreorderVisitor<'a> + ?Sized,
{
let ast::ExprFString { values, range: _ } = self;
let ast::ExprFString {
values,
implicit_concatenated: _,
range: _,
} = self;
for expr in values {
visitor.visit_expr(expr);

View file

@ -881,6 +881,8 @@ pub struct DebugText {
pub struct ExprFString {
pub range: TextRange,
pub values: Vec<Expr>,
/// Whether the f-string contains multiple string tokens that were implicitly concatenated.
pub implicit_concatenated: bool,
}
impl From<ExprFString> for Expr {
@ -2463,8 +2465,8 @@ impl std::cmp::PartialEq<usize> for Int {
pub enum Constant {
None,
Bool(bool),
Str(String),
Bytes(Vec<u8>),
Str(StringConstant),
Bytes(BytesConstant),
Int(BigInt),
Float(f64),
Complex { real: f64, imag: f64 },
@ -2472,38 +2474,68 @@ pub enum Constant {
}
impl Constant {
pub fn is_true(self) -> bool {
self.bool().is_some_and(|b| b)
}
pub fn is_false(self) -> bool {
self.bool().is_some_and(|b| !b)
}
pub fn complex(self) -> Option<(f64, f64)> {
/// Returns `true` if the constant is a string or bytes constant that contains multiple,
/// implicitly concatenated string tokens.
pub fn is_implicit_concatenated(&self) -> bool {
match self {
Constant::Complex { real, imag } => Some((real, imag)),
_ => None,
Constant::Str(value) => value.implicit_concatenated,
Constant::Bytes(value) => value.implicit_concatenated,
_ => false,
}
}
}
impl From<String> for Constant {
fn from(s: String) -> Constant {
Self::Str(s)
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct StringConstant {
/// The string value as resolved by the parser (i.e., without quotes, or escape sequences, or
/// implicit concatenations).
pub value: String,
/// Whether the string contains multiple string tokens that were implicitly concatenated.
pub implicit_concatenated: bool,
}
impl Deref for StringConstant {
type Target = str;
fn deref(&self) -> &Self::Target {
self.value.as_str()
}
}
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct BytesConstant {
/// The bytes value as resolved by the parser (i.e., without quotes, or escape sequences, or
/// implicit concatenations).
pub value: Vec<u8>,
/// Whether the string contains multiple string tokens that were implicitly concatenated.
pub implicit_concatenated: bool,
}
impl Deref for BytesConstant {
type Target = [u8];
fn deref(&self) -> &Self::Target {
self.value.as_slice()
}
}
impl From<Vec<u8>> for Constant {
fn from(b: Vec<u8>) -> Constant {
Self::Bytes(b)
fn from(value: Vec<u8>) -> Constant {
Self::Bytes(BytesConstant {
value,
implicit_concatenated: false,
})
}
}
impl From<String> for Constant {
fn from(value: String) -> Constant {
Self::Str(StringConstant {
value,
implicit_concatenated: false,
})
}
}
impl From<bool> for Constant {
fn from(b: bool) -> Constant {
Self::Bool(b)
}
}
impl From<BigInt> for Constant {
fn from(i: BigInt) -> Constant {
Self::Int(i)
fn from(value: bool) -> Constant {
Self::Bool(value)
}
}
@ -3056,7 +3088,7 @@ mod size_assertions {
assert_eq_size!(StmtClassDef, [u8; 104]);
assert_eq_size!(StmtTry, [u8; 104]);
assert_eq_size!(Expr, [u8; 80]);
assert_eq_size!(Constant, [u8; 32]);
assert_eq_size!(Constant, [u8; 40]);
assert_eq_size!(Pattern, [u8; 96]);
assert_eq_size!(Mod, [u8; 32]);
}

View file

@ -140,7 +140,7 @@ pub fn relocate_expr(expr: &mut Expr, location: TextRange) {
relocate_expr(expr, location);
}
}
Expr::FString(nodes::ExprFString { values, range }) => {
Expr::FString(nodes::ExprFString { values, range, .. }) => {
*range = location;
for expr in values {
relocate_expr(expr, location);

View file

@ -476,7 +476,7 @@ pub fn walk_expr<'a, V: Visitor<'a> + ?Sized>(visitor: &mut V, expr: &'a Expr) {
visitor.visit_format_spec(expr);
}
}
Expr::FString(ast::ExprFString { values, range: _ }) => {
Expr::FString(ast::ExprFString { values, .. }) => {
for expr in values {
visitor.visit_expr(expr);
}