Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[refurb] implement hardcoded-string-charset (FURB156) #13530

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 31 additions & 0 deletions crates/ruff_linter/resources/test/fixtures/refurb/FURB156.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
# Errors

_ = "0123456789"
_ = "01234567"
_ = "0123456789abcdefABCDEF"
_ = "abcdefghijklmnopqrstuvwxyz"
_ = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
_ = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
_ = r"""!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""
_ = " \t\n\r\v\f"

_ = "" in "1234567890"
_ = "" in "12345670"
_ = '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~ \t\n\r\x0b\x0c'
Copy link
Member

@MichaReiser MichaReiser Sep 27, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you add a test for a case where the string is parenthesized

Suggested change
_ = '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~ \t\n\r\x0b\x0c'
_ = (
'0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~ \t\n\r\x0b\x0c'
)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

066e700
I added the test and "took a look" on parenthesized_range, but its usage was really not intuitive for me in that special case. Could I somehow simplify "getting the parent" here?

_ = (
'0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'
"'()*+,-./:;<=>?@[\\]^_`{|}~ \t\n\r\x0b\x0c"
)
_ = id("0123"
"4567"
"89")
_ = "" in ("123"
"456"
"789"
"0")

# Ok

_ = "1234567890"
_ = "1234"
_ = "" in "1234"
8 changes: 7 additions & 1 deletion crates/ruff_linter/src/checkers/ast/analyze/expression.rs
Original file line number Diff line number Diff line change
Expand Up @@ -1355,6 +1355,9 @@ pub(crate) fn expression(expr: &Expr, checker: &mut Checker) {
if checker.enabled(Rule::SingleItemMembershipTest) {
refurb::rules::single_item_membership_test(checker, expr, left, ops, comparators);
}
if checker.enabled(Rule::HardcodedStringCharset) {
refurb::rules::hardcoded_string_charset_comparison(checker, compare);
}
}
Expr::NumberLiteral(number_literal @ ast::ExprNumberLiteral { .. }) => {
if checker.source_type.is_stub() && checker.enabled(Rule::NumericLiteralTooLong) {
Expand All @@ -1364,7 +1367,7 @@ pub(crate) fn expression(expr: &Expr, checker: &mut Checker) {
refurb::rules::math_constant(checker, number_literal);
}
}
Expr::StringLiteral(ast::ExprStringLiteral { value, range: _ }) => {
Expr::StringLiteral(string_like @ ast::ExprStringLiteral { value, range: _ }) => {
if checker.enabled(Rule::UnicodeKindPrefix) {
for string_part in value {
pyupgrade::rules::unicode_kind_prefix(checker, string_part);
Expand All @@ -1375,6 +1378,9 @@ pub(crate) fn expression(expr: &Expr, checker: &mut Checker) {
ruff::rules::missing_fstring_syntax(checker, string_literal);
}
}
if checker.enabled(Rule::HardcodedStringCharset) {
refurb::rules::hardcoded_string_charset_literal(checker, string_like);
}
}
Expr::If(
if_exp @ ast::ExprIf {
Expand Down
1 change: 1 addition & 0 deletions crates/ruff_linter/src/codes.rs
Original file line number Diff line number Diff line change
Expand Up @@ -1055,6 +1055,7 @@ pub fn code_to_rule(linter: Linter, code: &str) -> Option<(RuleGroup, Rule)> {
(Refurb, "148") => (RuleGroup::Preview, rules::refurb::rules::UnnecessaryEnumerate),
(Refurb, "152") => (RuleGroup::Preview, rules::refurb::rules::MathConstant),
(Refurb, "154") => (RuleGroup::Preview, rules::refurb::rules::RepeatedGlobal),
(Refurb, "156") => (RuleGroup::Preview, rules::refurb::rules::HardcodedStringCharset),
(Refurb, "157") => (RuleGroup::Preview, rules::refurb::rules::VerboseDecimalConstructor),
(Refurb, "161") => (RuleGroup::Stable, rules::refurb::rules::BitCount),
(Refurb, "163") => (RuleGroup::Stable, rules::refurb::rules::RedundantLogBase),
Expand Down
1 change: 1 addition & 0 deletions crates/ruff_linter/src/rules/refurb/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@ mod tests {
#[test_case(Rule::UnnecessaryEnumerate, Path::new("FURB148.py"))]
#[test_case(Rule::MathConstant, Path::new("FURB152.py"))]
#[test_case(Rule::RepeatedGlobal, Path::new("FURB154.py"))]
#[test_case(Rule::HardcodedStringCharset, Path::new("FURB156.py"))]
#[test_case(Rule::VerboseDecimalConstructor, Path::new("FURB157.py"))]
#[test_case(Rule::UnnecessaryFromFloat, Path::new("FURB164.py"))]
#[test_case(Rule::PrintEmptyString, Path::new("FURB105.py"))]
Expand Down
197 changes: 197 additions & 0 deletions crates/ruff_linter/src/rules/refurb/rules/hardcoded_string_charset.rs
Original file line number Diff line number Diff line change
@@ -0,0 +1,197 @@
use crate::checkers::ast::Checker;
use crate::importer::ImportRequest;
use ruff_diagnostics::{AlwaysFixableViolation, Diagnostic, Edit, Fix};
use ruff_macros::{derive_message_formats, violation};
use ruff_python_ast::parenthesize::parenthesized_range;
use ruff_python_ast::{CmpOp, Expr, ExprCall, ExprCompare, ExprStringLiteral};
use ruff_text_size::TextRange;

/// ## What it does
/// Checks for uses of hardcoded charsets, which are defined in Python string module.
///
/// ## Why is this bad?
/// Usage of named charsets from the standard library is more readable and less error-prone.
///
/// ## Example
/// ```python
/// x = "0123456789"
/// y in "abcdefghijklmnopqrstuvwxyz"
/// ```
///
/// Use instead
/// ```python
/// import string
///
/// x = string.digits
/// y in string.ascii_lowercase
/// ```
///
/// ## References
/// - [Python documentation: String constants](https://docs.python.org/3/library/string.html#string-constants)
#[violation]
pub struct HardcodedStringCharset {
name: &'static str,
}

impl AlwaysFixableViolation for HardcodedStringCharset {
#[derive_message_formats]
fn message(&self) -> String {
format!("Use of hardcoded string charset")
}

fn fix_title(&self) -> String {
let HardcodedStringCharset { name } = self;
format!("Replace hardcoded charset with `string.{name}`")
}
}

struct NamedCharset {
name: &'static str,
bytes: &'static [u8],
ascii_char_set: AsciiCharSet,
}

/// Represents the set of ascii characters in form of a bitset.
#[derive(Copy, Clone, Eq, PartialEq)]
struct AsciiCharSet(u128);

impl AsciiCharSet {
/// Creates the set of ascii characters from `bytes`.
/// Returns None if there is non-ascii byte.
const fn from_bytes(bytes: &[u8]) -> Option<Self> {
// TODO: simplify implementation, when const-traits are supported
// https://github.com/rust-lang/rust-project-goals/issues/106
let mut bitset = 0;
let mut i = 0;
while i < bytes.len() {
if !bytes[i].is_ascii() {
return None;
}
bitset |= 1 << bytes[i];
MichaReiser marked this conversation as resolved.
Show resolved Hide resolved
i += 1;
}
Some(Self(bitset))
}
}

impl NamedCharset {
const fn new(name: &'static str, bytes: &'static [u8]) -> Self {
Self {
name,
bytes,
// SAFETY: The named charset is guaranteed to have only ascii bytes.
// TODO: replace with `.unwrap()`, when `Option::unwrap` will be stable in `const fn`
// https://github.com/rust-lang/rust/issues/67441
ascii_char_set: match AsciiCharSet::from_bytes(bytes) {
Some(ascii_char_set) => ascii_char_set,
None => unreachable!(),
},
}
}
}

const KNOWN_NAMED_CHARSETS: [NamedCharset; 9] = [
NamedCharset::new(
"ascii_letters",
b"abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ",
),
NamedCharset::new("ascii_lowercase", b"abcdefghijklmnopqrstuvwxyz"),
NamedCharset::new("ascii_uppercase", b"ABCDEFGHIJKLMNOPQRSTUVWXYZ"),
NamedCharset::new("digits", b"0123456789"),
NamedCharset::new("hexdigits", b"0123456789abcdefABCDEF"),
NamedCharset::new("octdigits", b"01234567"),
NamedCharset::new("punctuation", b"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"),
NamedCharset::new(
"printable",
b"0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!\"\
#$%&'()*+,-./:;<=>?@[\\]^_`{|}~ \t\n\r\x0b\x0c",
),
NamedCharset::new("whitespace", b" \t\n\r\x0b\x0c"),
];

fn check_charset_as_set(bytes: &[u8]) -> Option<&NamedCharset> {
let ascii_char_set = AsciiCharSet::from_bytes(bytes)?;

KNOWN_NAMED_CHARSETS
.iter()
.find(|&charset| charset.ascii_char_set == ascii_char_set)
}

fn check_charset_exact(bytes: &[u8]) -> Option<&NamedCharset> {
KNOWN_NAMED_CHARSETS
.iter()
.find(|&charset| charset.bytes == bytes)
}

fn push_diagnostic(checker: &mut Checker, range: TextRange, charset: &NamedCharset) {
let name = charset.name;
let mut diagnostic = Diagnostic::new(HardcodedStringCharset { name }, range);
diagnostic.try_set_fix(|| {
let (edit, binding) = checker.importer().get_or_import_symbol(
&ImportRequest::import("string", name),
range.start(),
checker.semantic(),
)?;
Ok(Fix::safe_edits(
Edit::range_replacement(binding, range),
[edit],
))
});
checker.diagnostics.push(diagnostic);
}

/// FURB156
pub(crate) fn hardcoded_string_charset_comparison(checker: &mut Checker, compare: &ExprCompare) {
let (
[CmpOp::In | CmpOp::NotIn],
[Expr::StringLiteral(string_literal @ ExprStringLiteral { value, .. })],
) = (compare.ops.as_ref(), compare.comparators.as_ref())
else {
return;
};

let bytes = value.to_str().as_bytes();

let Some(charset) = check_charset_as_set(bytes) else {
return;
};

// In this case the diagnostic will be emitted via string_literal check.
if charset.bytes == bytes {
return;
}

let range = parenthesized_range(
string_literal.into(),
compare.into(),
checker.comment_ranges(),
checker.locator().contents(),
)
.unwrap_or(string_literal.range);

push_diagnostic(checker, range, charset);
}

/// FURB156
pub(crate) fn hardcoded_string_charset_literal(checker: &mut Checker, expr: &ExprStringLiteral) {
if let Some(charset) = check_charset_exact(expr.value.to_str().as_bytes()) {
let range = parenthesized_range(
expr.into(),
checker.semantic().current_expression_parent().map_or_else(
|| checker.semantic().current_statement().into(),
|parent| {
if let Expr::Call(ExprCall { arguments, .. }) = parent {
arguments.into()
} else {
parent.into()
}
},
),
checker.comment_ranges(),
checker.locator().contents(),
)
.unwrap_or(expr.range);

push_diagnostic(checker, range, charset);
}
}
2 changes: 2 additions & 0 deletions crates/ruff_linter/src/rules/refurb/rules/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@ pub(crate) use check_and_remove_from_set::*;
pub(crate) use delete_full_slice::*;
pub(crate) use for_loop_set_mutations::*;
pub(crate) use fstring_number_format::*;
pub(crate) use hardcoded_string_charset::*;
pub(crate) use hashlib_digest_hex::*;
pub(crate) use if_exp_instead_of_or_operator::*;
pub(crate) use if_expr_min_max::*;
Expand Down Expand Up @@ -36,6 +37,7 @@ mod check_and_remove_from_set;
mod delete_full_slice;
mod for_loop_set_mutations;
mod fstring_number_format;
mod hardcoded_string_charset;
mod hashlib_digest_hex;
mod if_exp_instead_of_or_operator;
mod if_expr_min_max;
Expand Down
Loading
Loading