New pycodestyle.max-line-length option (#8039)

## Summary

This PR introduces a new `pycodestyl.max-line-length` option that allows overriding the global `line-length` option for `E501` only.

This is useful when using the formatter and `E501` together, where the formatter uses a lower limit and `E501` is only used to catch extra-long lines. 

Closes #7644

## Considerations

~~Our fix infrastructure asserts in some places that the fix doesn't exceed the configured `line-width`. With this change, the question is whether it should use the `pycodestyle.max-line-width` or `line-width` option to make that decision.
I opted for the global `line-width` for now, considering that it should be the lower limit. However, this constraint isn't enforced and users not using the formatter may only specify `pycodestyle.max-line-width` because they're unaware of the global option (and it solves their need).~~


~~I'm interested to hear your thoughts on whether we should use `pycodestyle.max-line-width` or `line-width` to decide on whether to emit a fix or not.~~

Edit: The linter users `pycodestyle.max-line-width`. The `line-width` option has been removed from the `LinterSettings`

## Test Plan

Added integration test. Built the documentation and verified that the links are correct.

Author: MichaReiser

crates/ruff_cli/src/args.rs

@@ -13,6 +13,7 @@ use ruff_linter::settings::types::{
 };
 use ruff_linter::{RuleParser, RuleSelector, RuleSelectorParser};
 use ruff_workspace::configuration::{Configuration, RuleSelection};
+use ruff_workspace::options::PycodestyleOptions;
 use ruff_workspace::resolver::ConfigurationTransformer;
 
 #[derive(Debug, Parser)]
@@ -685,8 +686,12 @@ impl ConfigurationTransformer for CliOverrides {
         if let Some(force_exclude) = &self.force_exclude {
             config.force_exclude = Some(*force_exclude);
         }
-        if let Some(line_length) = &self.line_length {
-            config.line_length = Some(*line_length);
+        if let Some(line_length) = self.line_length {
+            config.line_length = Some(line_length);
+            config.lint.pycodestyle = Some(PycodestyleOptions {
+                max_line_length: Some(line_length),
+                ..config.lint.pycodestyle.unwrap_or_default()
+            });
         }
         if let Some(preview) = &self.preview {
             config.preview = Some(*preview);

crates/ruff_cli/tests/lint.rs

@@ -270,3 +270,41 @@ if __name__ == "__main__":
     "###);
     Ok(())
 }
+
+#[test]
+fn line_too_long_width_override() -> Result<()> {
+    let tempdir = TempDir::new()?;
+    let ruff_toml = tempdir.path().join("ruff.toml");
+    fs::write(
+        &ruff_toml,
+        r#"
+line-length = 80
+select = ["E501"]
+
+[pycodestyle]
+max-line-length = 100
+"#,
+    )?;
+
+    assert_cmd_snapshot!(Command::new(get_cargo_bin(BIN_NAME))
+        .args(STDIN_BASE_OPTIONS)
+        .arg("--config")
+        .arg(&ruff_toml)
+        .args(["--stdin-filename", "test.py"])
+        .arg("-")
+        .pass_stdin(r#"
+# longer than 80, but less than 100
+_ = "---------------------------------------------------------------------------亜亜亜亜亜亜"
+# longer than 100
+_ = "---------------------------------------------------------------------------亜亜亜亜亜亜亜亜亜亜亜亜亜亜"
+"#), @r###"
+    success: false
+    exit_code: 1
+    ----- stdout -----
+    test.py:5:91: E501 Line too long (109 > 100)
+    Found 1 error.
+
+    ----- stderr -----
+    "###);
+    Ok(())
+}

crates/ruff_linter/src/checkers/physical_lines.rs

@@ -95,6 +95,7 @@ mod tests {
 
     use crate::line_width::LineLength;
     use crate::registry::Rule;
+    use crate::rules::pycodestyle;
     use crate::settings::LinterSettings;
 
     use super::check_physical_lines;
@@ -114,7 +115,10 @@ mod tests {
                 &indexer,
                 &[],
                 &LinterSettings {
-                    line_length,
+                    pycodestyle: pycodestyle::settings::Settings {
+                        max_line_length: line_length,
+                        ..pycodestyle::settings::Settings::default()
+                    },
                     ..LinterSettings::for_rule(Rule::LineTooLong)
                 },
             )

crates/ruff_linter/src/rules/flake8_simplify/rules/ast_with.rs

@@ -139,7 +139,7 @@ pub(crate) fn multiple_with_statements(
                             content,
                             with_stmt.into(),
                             checker.locator(),
-                            checker.settings.line_length,
+                            checker.settings.pycodestyle.max_line_length,
                             checker.settings.tab_size,
                         )
                     }) {

crates/ruff_linter/src/rules/flake8_simplify/rules/collapsible_if.rs

@@ -128,7 +128,7 @@ pub(crate) fn nested_if_statements(
                         content,
                         (&nested_if).into(),
                         checker.locator(),
-                        checker.settings.line_length,
+                        checker.settings.pycodestyle.max_line_length,
                         checker.settings.tab_size,
                     )
                 }) {

crates/ruff_linter/src/rules/flake8_simplify/rules/if_else_block_instead_of_dict_get.rs

@@ -195,7 +195,7 @@ pub(crate) fn if_else_block_instead_of_dict_get(checker: &mut Checker, stmt_if:
         &contents,
         stmt_if.into(),
         checker.locator(),
-        checker.settings.line_length,
+        checker.settings.pycodestyle.max_line_length,
         checker.settings.tab_size,
     ) {
         return;

crates/ruff_linter/src/rules/flake8_simplify/rules/if_else_block_instead_of_if_exp.rs

@@ -130,7 +130,7 @@ pub(crate) fn if_else_block_instead_of_if_exp(checker: &mut Checker, stmt_if: &a
         &contents,
         stmt_if.into(),
         checker.locator(),
-        checker.settings.line_length,
+        checker.settings.pycodestyle.max_line_length,
         checker.settings.tab_size,
     ) {
         return;

crates/ruff_linter/src/rules/flake8_simplify/rules/reimplemented_builtin.rs

@@ -101,7 +101,7 @@ pub(crate) fn convert_for_loop_to_any_all(checker: &mut Checker, stmt: &Stmt) {
                 &contents,
                 stmt.into(),
                 checker.locator(),
-                checker.settings.line_length,
+                checker.settings.pycodestyle.max_line_length,
                 checker.settings.tab_size,
             ) {
                 return;
@@ -188,7 +188,7 @@ pub(crate) fn convert_for_loop_to_any_all(checker: &mut Checker, stmt: &Stmt) {
                         .slice(TextRange::new(line_start, stmt.start())),
                 )
                 .add_str(&contents)
-                > checker.settings.line_length
+                > checker.settings.pycodestyle.max_line_length
             {
                 return;
             }

crates/ruff_linter/src/rules/isort/rules/organize_imports.rs

@@ -120,7 +120,7 @@ pub(crate) fn organize_imports(
         block,
         comments,
         locator,
-        settings.line_length,
+        settings.pycodestyle.max_line_length,
         LineWidthBuilder::new(settings.tab_size).add_str(indentation),
         stylist,
         &settings.src,

crates/ruff_linter/src/rules/pycodestyle/mod.rs

@@ -16,6 +16,7 @@ mod tests {
 
     use crate::line_width::LineLength;
     use crate::registry::Rule;
+    use crate::rules::pycodestyle;
     use crate::settings::types::PreviewMode;
     use crate::test::test_path;
     use crate::{assert_messages, settings};
@@ -229,7 +230,10 @@ mod tests {
             Path::new("pycodestyle/E501_2.py"),
             &settings::LinterSettings {
                 tab_size: NonZeroU8::new(tab_size).unwrap().into(),
-                line_length: LineLength::try_from(6).unwrap(),
+                pycodestyle: pycodestyle::settings::Settings {
+                    max_line_length: LineLength::try_from(6).unwrap(),
+                    ..pycodestyle::settings::Settings::default()
+                },
                 ..settings::LinterSettings::for_rule(Rule::LineTooLong)
             },
         )?;

crates/ruff_linter/src/rules/pycodestyle/rules/line_too_long.rs

@@ -47,6 +47,7 @@ use crate::settings::LinterSettings;
 ///
 /// ## Options
 /// - `line-length`
+/// - `pycodestyle.max-line-length`
 /// - `task-tags`
 /// - `pycodestyle.ignore-overlong-task-comments`
 ///
@@ -68,7 +69,7 @@ pub(crate) fn line_too_long(
     indexer: &Indexer,
     settings: &LinterSettings,
 ) -> Option<Diagnostic> {
-    let limit = settings.line_length;
+    let limit = settings.pycodestyle.max_line_length;
 
     Overlong::try_from_line(
         line,

crates/ruff_linter/src/rules/pycodestyle/settings.rs

@@ -6,6 +6,7 @@ use crate::line_width::LineLength;
 
 #[derive(Debug, Default, CacheKey)]
 pub struct Settings {
+    pub max_line_length: LineLength,
     pub max_doc_length: Option<LineLength>,
     pub ignore_overlong_task_comments: bool,
 }

crates/ruff_linter/src/rules/pyupgrade/rules/f_strings.rs

@@ -399,7 +399,7 @@ pub(crate) fn f_strings(
         &contents,
         template.into(),
         checker.locator(),
-        checker.settings.line_length,
+        checker.settings.pycodestyle.max_line_length,
         checker.settings.tab_size,
     ) {
         return;

crates/ruff_linter/src/settings/mod.rs

@@ -26,7 +26,7 @@ use crate::rules::{
 use crate::settings::types::{FilePatternSet, PerFileIgnore, PythonVersion};
 use crate::{codes, RuleSelector};
 
-use super::line_width::{LineLength, TabSize};
+use super::line_width::TabSize;
 
 use self::rule_table::RuleTable;
 use self::types::PreviewMode;
@@ -56,7 +56,6 @@ pub struct LinterSettings {
     pub dummy_variable_rgx: Regex,
     pub external: FxHashSet<String>,
     pub ignore_init_module_imports: bool,
-    pub line_length: LineLength,
     pub logger_objects: Vec<String>,
     pub namespace_packages: Vec<PathBuf>,
     pub src: Vec<PathBuf>,
@@ -147,7 +146,6 @@ impl LinterSettings {
 
             external: HashSet::default(),
             ignore_init_module_imports: false,
-            line_length: LineLength::default(),
             logger_objects: vec![],
             namespace_packages: vec![],
 

crates/ruff_workspace/src/configuration.rs

@@ -21,6 +21,7 @@ use ruff_linter::line_width::{LineLength, TabSize};
 use ruff_linter::registry::RuleNamespace;
 use ruff_linter::registry::{Rule, RuleSet, INCOMPATIBLE_CODES};
 use ruff_linter::rule_selector::{PreviewOptions, Specificity};
+use ruff_linter::rules::pycodestyle;
 use ruff_linter::settings::rule_table::RuleTable;
 use ruff_linter::settings::types::{
     FilePattern, FilePatternSet, PerFileIgnore, PreviewMode, PythonVersion, SerializationFormat,
@@ -183,6 +184,8 @@ impl Configuration {
         let lint = self.lint;
         let lint_preview = lint.preview.unwrap_or(global_preview);
 
+        let line_length = self.line_length.unwrap_or_default();
+
         Ok(Settings {
             cache_dir: self
                 .cache_dir
@@ -225,7 +228,6 @@ impl Configuration {
                     .unwrap_or_else(|| DUMMY_VARIABLE_RGX.clone()),
                 external: FxHashSet::from_iter(lint.external.unwrap_or_default()),
                 ignore_init_module_imports: lint.ignore_init_module_imports.unwrap_or_default(),
-                line_length: self.line_length.unwrap_or_default(),
                 tab_size: self.tab_size.unwrap_or_default(),
                 namespace_packages: self.namespace_packages.unwrap_or_default(),
                 per_file_ignores: resolve_per_file_ignores(
@@ -346,10 +348,14 @@ impl Configuration {
                     .map(Pep8NamingOptions::try_into_settings)
                     .transpose()?
                     .unwrap_or_default(),
-                pycodestyle: lint
-                    .pycodestyle
-                    .map(PycodestyleOptions::into_settings)
-                    .unwrap_or_default(),
+                pycodestyle: if let Some(pycodestyle) = lint.pycodestyle {
+                    pycodestyle.into_settings(line_length)
+                } else {
+                    pycodestyle::settings::Settings {
+                        max_line_length: line_length,
+                        ..pycodestyle::settings::Settings::default()
+                    }
+                },
                 pydocstyle: lint
                     .pydocstyle
                     .map(PydocstyleOptions::into_settings)

crates/ruff_workspace/src/options.rs

@@ -60,7 +60,7 @@ pub struct Options {
     /// this base configuration file, then merge in any properties defined
     /// in the current configuration file.
     #[option(
-        default = r#"None"#,
+        default = r#"null"#,
         value_type = "str",
         example = r#"
             # Extend the `pyproject.toml` file in the parent directory.
@@ -132,7 +132,7 @@ pub struct Options {
     /// results across many environments, e.g., with a `pyproject.toml`
     /// file).
     #[option(
-        default = "None",
+        default = "null",
         value_type = "str",
         example = r#"
             required-version = "0.0.193"
@@ -362,6 +362,8 @@ pub struct Options {
     /// Note: While the formatter will attempt to format lines such that they remain
     /// within the `line-length`, it isn't a hard upper bound, and formatted lines may
     /// exceed the `line-length`.
+    ///
+    /// See [`pycodestyle.max-line-length`](#pycodestyle-max-line-length) to configure different lengths for `E501` and the formatter.
     #[option(
         default = "88",
         value_type = "int",
@@ -1043,7 +1045,7 @@ pub struct Flake8CopyrightOptions {
 
     /// Author to enforce within the copyright notice. If provided, the
     /// author must be present immediately following the copyright notice.
-    #[option(default = "None", value_type = "str", example = r#"author = "Ruff""#)]
+    #[option(default = "null", value_type = "str", example = r#"author = "Ruff""#)]
     pub author: Option<String>,
 
     /// A minimum file size (in bytes) required for a copyright notice to
@@ -2247,6 +2249,32 @@ impl Pep8NamingOptions {
 #[serde(deny_unknown_fields, rename_all = "kebab-case")]
 #[cfg_attr(feature = "schemars", derive(schemars::JsonSchema))]
 pub struct PycodestyleOptions {
+    /// The maximum line length to allow for [`line-too-long`](https://docs.astral.sh/ruff/rules/line-too-long/) violations. By default,
+    /// this is set to the value of the [`line-length`](#line-length) option.
+    ///
+    /// Use this option when you want to detect extra-long lines that the formatter can't automatically split by setting
+    /// `pycodestyle.line-length` to a value larger than [`line-length`](#line-length).
+    ///
+    /// ```toml
+    /// line-length = 88 # The formatter wraps lines at a length of 88
+    ///
+    /// [pycodestyle]
+    /// max-line-length = 100 # E501 reports lines that exceed the length of 100.
+    /// ```
+    ///
+    /// The length is determined by the number of characters per line, except for lines containing East Asian characters or emojis.
+    /// For these lines, the [unicode width](https://unicode.org/reports/tr11/) of each character is added up to determine the length.
+    ///
+    /// See the [`line-too-long`](https://docs.astral.sh/ruff/rules/line-too-long/) rule for more information.
+    #[option(
+        default = "null",
+        value_type = "int",
+        example = r#"
+            max-line-length = 100
+        "#
+    )]
+    pub max_line_length: Option<LineLength>,
+
     /// The maximum line length to allow for [`doc-line-too-long`](https://docs.astral.sh/ruff/rules/doc-line-too-long/) violations within
     /// documentation (`W505`), including standalone comments. By default,
     /// this is set to null which disables reporting violations.
@@ -2256,7 +2284,7 @@ pub struct PycodestyleOptions {
     ///
     /// See the [`doc-line-too-long`](https://docs.astral.sh/ruff/rules/doc-line-too-long/) rule for more information.
     #[option(
-        default = "None",
+        default = "null",
         value_type = "int",
         example = r#"
             max-doc-length = 88
@@ -2278,9 +2306,10 @@ pub struct PycodestyleOptions {
 }
 
 impl PycodestyleOptions {
-    pub fn into_settings(self) -> pycodestyle::settings::Settings {
+    pub fn into_settings(self, global_line_length: LineLength) -> pycodestyle::settings::Settings {
         pycodestyle::settings::Settings {
             max_doc_length: self.max_doc_length,
+            max_line_length: self.max_line_length.unwrap_or(global_line_length),
             ignore_overlong_task_comments: self.ignore_overlong_task_comments.unwrap_or_default(),
         }
     }
@@ -2321,7 +2350,7 @@ pub struct PydocstyleOptions {
     /// enabling _additional_ rules on top of a convention is currently
     /// unsupported.
     #[option(
-        default = r#"None"#,
+        default = r#"null"#,
         value_type = r#""google" | "numpy" | "pep257""#,
         example = r#"
             # Use Google-style docstrings.