Separate StringNormalizer from StringPart (#9954)

## Summary

This PR is a small refactor to extract out the logic for normalizing
string in the formatter from the `StringPart` struct. It also separates
the quote selection into a separate method on the new
`StringNormalizer`. Both of these will help in the f-string formatting
to use `StringPart` and `choose_quotes` irrespective of normalization.

The reason for having separate quote selection and normalization step is
so that the f-string formatting can perform quote selection on its own.

Unlike string and byte literals, the f-string formatting would require
that the normalization happens only for the literal elements of it i.e.,
the "foo" and "bar" in `f"foo {x + y} bar"`. This will automatically be
handled by the already separate `normalize_string` function.

Another use-case in the f-string formatting is to extract out the
relevant information from the `StringPart` like quotes and prefix which
is to be passed as context while formatting each element of an f-string.

## Test Plan

Ensure that clippy is happy and all tests pass.
This commit is contained in:
Dhruv Manilawala 2024-02-13 18:14:56 +05:30 committed by GitHub
parent 6380c90031
commit 6f9c128d77
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 96 additions and 59 deletions

View file

@ -2,8 +2,7 @@ use ruff_python_ast::BytesLiteral;
use ruff_text_size::Ranged;
use crate::prelude::*;
use crate::preview::is_hex_codes_in_unicode_sequences_enabled;
use crate::string::{Quoting, StringPart};
use crate::string::{StringNormalizer, StringPart};
#[derive(Default)]
pub struct FormatBytesLiteral;
@ -12,14 +11,9 @@ impl FormatNodeRule<BytesLiteral> for FormatBytesLiteral {
fn fmt_fields(&self, item: &BytesLiteral, f: &mut PyFormatter) -> FormatResult<()> {
let locator = f.context().locator();
StringPart::from_source(item.range(), &locator)
.normalize(
Quoting::CanChange,
&locator,
f.options().quote_style(),
f.context().docstring(),
is_hex_codes_in_unicode_sequences_enabled(f.context()),
)
StringNormalizer::from_context(f.context())
.with_preferred_quote_style(f.options().quote_style())
.normalize(&StringPart::from_source(item.range(), &locator), &locator)
.fmt(f)
}
}

View file

@ -2,8 +2,7 @@ use ruff_python_ast::FString;
use ruff_text_size::Ranged;
use crate::prelude::*;
use crate::preview::is_hex_codes_in_unicode_sequences_enabled;
use crate::string::{Quoting, StringPart};
use crate::string::{Quoting, StringNormalizer, StringPart};
/// Formats an f-string which is part of a larger f-string expression.
///
@ -26,13 +25,12 @@ impl Format<PyFormatContext<'_>> for FormatFString<'_> {
fn fmt(&self, f: &mut PyFormatter) -> FormatResult<()> {
let locator = f.context().locator();
let result = StringPart::from_source(self.value.range(), &locator)
let result = StringNormalizer::from_context(f.context())
.with_quoting(self.quoting)
.with_preferred_quote_style(f.options().quote_style())
.normalize(
self.quoting,
&StringPart::from_source(self.value.range(), &locator),
&locator,
f.options().quote_style(),
f.context().docstring(),
is_hex_codes_in_unicode_sequences_enabled(f.context()),
)
.fmt(f);

View file

@ -2,8 +2,7 @@ use ruff_python_ast::StringLiteral;
use ruff_text_size::Ranged;
use crate::prelude::*;
use crate::preview::is_hex_codes_in_unicode_sequences_enabled;
use crate::string::{docstring, Quoting, StringPart};
use crate::string::{docstring, Quoting, StringNormalizer, StringPart};
use crate::QuoteStyle;
pub(crate) struct FormatStringLiteral<'a> {
@ -59,13 +58,13 @@ impl Format<PyFormatContext<'_>> for FormatStringLiteral<'_> {
quote_style
};
let normalized = StringPart::from_source(self.value.range(), &locator).normalize(
self.layout.quoting(),
&locator,
quote_style,
f.context().docstring(),
is_hex_codes_in_unicode_sequences_enabled(f.context()),
);
let normalized = StringNormalizer::from_context(f.context())
.with_quoting(self.layout.quoting())
.with_preferred_quote_style(quote_style)
.normalize(
&StringPart::from_source(self.value.range(), &locator),
&locator,
);
if self.layout.is_docstring() {
docstring::format(&normalized, f)