Split Constant to individual literal nodes (#8064)

## Summary

This PR splits the `Constant` enum as individual literal nodes. It
introduces the following new nodes for each variant:
* `ExprStringLiteral`
* `ExprBytesLiteral`
* `ExprNumberLiteral`
* `ExprBooleanLiteral`
* `ExprNoneLiteral`
* `ExprEllipsisLiteral`

The main motivation behind this refactor is to introduce the new AST
node for implicit string concatenation in the coming PR. The elements of
that node will be either a string literal, bytes literal or a f-string
which can be implemented using an enum. This means that a string or
bytes literal cannot be represented by `Constant::Str` /
`Constant::Bytes` which creates an inconsistency.

This PR avoids that inconsistency by splitting the constant nodes into
it's own literal nodes, literal being the more appropriate naming
convention from a static analysis tool perspective.

This also makes working with literals in the linter and formatter much
more ergonomic like, for example, if one would want to check if this is
a string literal, it can be done easily using
`Expr::is_string_literal_expr` or matching against `Expr::StringLiteral`
as oppose to matching against the `ExprConstant` and enum `Constant`. A
few AST helper methods can be simplified as well which will be done in a
follow-up PR.

This introduces a new `Expr::is_literal_expr` method which is the same
as `Expr::is_constant_expr`. There are also intermediary changes related
to implicit string concatenation which are quiet less. This is done so
as to avoid having a huge PR which this already is.

## Test Plan

1. Verify and update all of the existing snapshots (parser, visitor)
2. Verify that the ecosystem check output remains **unchanged** for both
the linter and formatter

### Formatter ecosystem check

#### `main`

| project | similarity index | total files | changed files |

|----------------|------------------:|------------------:|------------------:|
| cpython | 0.75803 | 1799 | 1647 |
| django | 0.99983 | 2772 | 34 |
| home-assistant | 0.99953 | 10596 | 186 |
| poetry | 0.99891 | 317 | 17 |
| transformers | 0.99966 | 2657 | 330 |
| twine | 1.00000 | 33 | 0 |
| typeshed | 0.99978 | 3669 | 20 |
| warehouse | 0.99977 | 654 | 13 |
| zulip | 0.99970 | 1459 | 22 |

#### `dhruv/constant-to-literal`

| project | similarity index | total files | changed files |

|----------------|------------------:|------------------:|------------------:|
| cpython | 0.75803 | 1799 | 1647 |
| django | 0.99983 | 2772 | 34 |
| home-assistant | 0.99953 | 10596 | 186 |
| poetry | 0.99891 | 317 | 17 |
| transformers | 0.99966 | 2657 | 330 |
| twine | 1.00000 | 33 | 0 |
| typeshed | 0.99978 | 3669 | 20 |
| warehouse | 0.99977 | 654 | 13 |
| zulip | 0.99970 | 1459 | 22 |
This commit is contained in:
Dhruv Manilawala 2023-10-30 12:13:23 +05:30 committed by GitHub
parent 78bbf6d403
commit 230c9ce236
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
268 changed files with 6663 additions and 6741 deletions

View file

@ -344,45 +344,21 @@ impl From<&ast::Singleton> for ComparableSingleton {
}
#[derive(Debug, PartialEq, Eq, Hash)]
pub enum ComparableConstant<'a> {
None,
Bool(&'a bool),
Str { value: &'a str, unicode: bool },
Bytes(&'a [u8]),
pub enum ComparableNumber<'a> {
Int(&'a ast::Int),
Float(u64),
Complex { real: u64, imag: u64 },
Ellipsis,
}
impl<'a> From<&'a ast::Constant> for ComparableConstant<'a> {
fn from(constant: &'a ast::Constant) -> Self {
match constant {
ast::Constant::None => Self::None,
ast::Constant::Bool(value) => Self::Bool(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: _,
unicode,
}) => Self::Str {
value,
unicode: *unicode,
},
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 {
impl<'a> From<&'a ast::Number> for ComparableNumber<'a> {
fn from(number: &'a ast::Number) -> Self {
match number {
ast::Number::Int(value) => Self::Int(value),
ast::Number::Float(value) => Self::Float(value.to_bits()),
ast::Number::Complex { real, imag } => Self::Complex {
real: real.to_bits(),
imag: imag.to_bits(),
},
ast::Constant::Ellipsis => Self::Ellipsis,
}
}
}
@ -669,8 +645,24 @@ pub struct ExprFString<'a> {
}
#[derive(Debug, PartialEq, Eq, Hash)]
pub struct ExprConstant<'a> {
value: ComparableConstant<'a>,
pub struct ExprStringLiteral<'a> {
value: &'a str,
unicode: &'a bool,
}
#[derive(Debug, PartialEq, Eq, Hash)]
pub struct ExprBytesLiteral<'a> {
value: &'a [u8],
}
#[derive(Debug, PartialEq, Eq, Hash)]
pub struct ExprNumberLiteral<'a> {
value: ComparableNumber<'a>,
}
#[derive(Debug, PartialEq, Eq, Hash)]
pub struct ExprBoolLiteral<'a> {
value: &'a bool,
}
#[derive(Debug, PartialEq, Eq, Hash)]
@ -739,7 +731,12 @@ pub enum ComparableExpr<'a> {
Call(ExprCall<'a>),
FormattedValue(ExprFormattedValue<'a>),
FString(ExprFString<'a>),
Constant(ExprConstant<'a>),
StringLiteral(ExprStringLiteral<'a>),
BytesLiteral(ExprBytesLiteral<'a>),
NumberLiteral(ExprNumberLiteral<'a>),
BoolLiteral(ExprBoolLiteral<'a>),
NoneLiteral,
EllispsisLiteral,
Attribute(ExprAttribute<'a>),
Subscript(ExprSubscript<'a>),
Starred(ExprStarred<'a>),
@ -913,11 +910,31 @@ impl<'a> From<&'a ast::Expr> for ComparableExpr<'a> {
}) => Self::FString(ExprFString {
values: values.iter().map(Into::into).collect(),
}),
ast::Expr::Constant(ast::ExprConstant { value, range: _ }) => {
Self::Constant(ExprConstant {
ast::Expr::StringLiteral(ast::ExprStringLiteral {
value,
// Compare strings based on resolved value, not representation (i.e., ignore whether
// the string was implicitly concatenated).
implicit_concatenated: _,
unicode,
range: _,
}) => Self::StringLiteral(ExprStringLiteral { value, unicode }),
ast::Expr::BytesLiteral(ast::ExprBytesLiteral {
value,
// Compare bytes based on resolved value, not representation (i.e., ignore whether
// the bytes was implicitly concatenated).
implicit_concatenated: _,
range: _,
}) => Self::BytesLiteral(ExprBytesLiteral { value }),
ast::Expr::NumberLiteral(ast::ExprNumberLiteral { value, range: _ }) => {
Self::NumberLiteral(ExprNumberLiteral {
value: value.into(),
})
}
ast::Expr::BooleanLiteral(ast::ExprBooleanLiteral { value, range: _ }) => {
Self::BoolLiteral(ExprBoolLiteral { value })
}
ast::Expr::NoneLiteral(_) => Self::NoneLiteral,
ast::Expr::EllipsisLiteral(_) => Self::EllispsisLiteral,
ast::Expr::Attribute(ast::ExprAttribute {
value,
attr,