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

@ -1,7 +1,7 @@
use ruff_formatter::{write, FormatOwnedWithRule, FormatRefWithRule, FormatRuleWithOptions};
use ruff_python_ast::helpers::is_compound_statement;
use ruff_python_ast::AnyNodeRef;
use ruff_python_ast::{self as ast, Constant, Expr, ExprConstant, PySourceType, Stmt, Suite};
use ruff_python_ast::{self as ast, Expr, PySourceType, Stmt, Suite};
use ruff_python_trivia::{lines_after, lines_after_ignoring_end_of_line_trivia, lines_before};
use ruff_text_size::{Ranged, TextRange};
@ -9,7 +9,6 @@ use crate::comments::{
leading_comments, trailing_comments, Comments, LeadingDanglingTrailingComments,
};
use crate::context::{NodeLevel, WithNodeLevel};
use crate::expression::expr_constant::ExprConstantLayout;
use crate::expression::string::StringLayout;
use crate::prelude::*;
use crate::statement::stmt_expr::FormatStmtExpr;
@ -501,13 +500,7 @@ pub(crate) fn contains_only_an_ellipsis(body: &[Stmt], comments: &Comments) -> b
let [node] = body else {
return false;
};
matches!(
value.as_ref(),
Expr::Constant(ast::ExprConstant {
value: Constant::Ellipsis,
..
})
) && !comments.has_leading(node)
value.is_ellipsis_literal_expr() && !comments.has_leading(node)
}
_ => false,
}
@ -559,15 +552,11 @@ impl<'a> DocstringStmt<'a> {
return None;
};
if let Expr::Constant(ExprConstant { value, .. }) = value.as_ref() {
return match value {
Constant::Str(value) if !value.implicit_concatenated => Some(DocstringStmt(stmt)),
Constant::Bytes(value) if !value.implicit_concatenated => Some(DocstringStmt(stmt)),
_ => None,
};
match value.as_ref() {
Expr::StringLiteral(value) if !value.implicit_concatenated => Some(DocstringStmt(stmt)),
Expr::BytesLiteral(value) if !value.implicit_concatenated => Some(DocstringStmt(stmt)),
_ => None,
}
None
}
}
@ -579,13 +568,13 @@ impl Format<PyFormatContext<'_>> for DocstringStmt<'_> {
if FormatStmtExpr.is_suppressed(node_comments.trailing, f.context()) {
suppressed_node(self.0).fmt(f)
} else {
// SAFETY: Safe because `DocStringStmt` guarantees that it only ever wraps a `ExprStmt` containing a `ConstantExpr`.
let constant = self
// SAFETY: Safe because `DocStringStmt` guarantees that it only ever wraps a `ExprStmt` containing a `ExprStringLiteral`.
let string_literal = self
.0
.as_expr_stmt()
.unwrap()
.value
.as_constant_expr()
.as_string_literal_expr()
.unwrap();
// We format the expression, but the statement carries the comments
@ -593,9 +582,9 @@ impl Format<PyFormatContext<'_>> for DocstringStmt<'_> {
f,
[
leading_comments(node_comments.leading),
constant
string_literal
.format()
.with_options(ExprConstantLayout::String(StringLayout::DocString)),
.with_options(StringLayout::DocString),
trailing_comments(node_comments.trailing),
]
)