Stabilize support for Jupyter Notebooks (#12878)

dhruvmanila · AlexWaygood · MichaReiser · commit 73160dc8b684 · 2024-08-14T18:15:45.000+02:00
Co-authored-by: Alex Waygood <alex.waygood@gmail.com> Closes: #12456 Closes: astral-sh/ruff-vscode#546
diff --git a/crates/ruff/src/commands/check.rs b/crates/ruff/src/commands/check.rs
@@ -268,8 +268,7 @@ mod test {
 
         // Run
         let diagnostics = check(
-            // Notebooks are not included by default
-            &[tempdir.path().to_path_buf(), notebook],
+            &[tempdir.path().to_path_buf()],
             &pyproject_config,
             &ConfigArguments::default(),
             flags::Cache::Disabled,
diff --git a/crates/ruff/tests/lint.rs b/crates/ruff/tests/lint.rs
@@ -1806,7 +1806,7 @@ select = ["UP006"]
 }
 
 #[test]
-fn checks_notebooks_in_preview_mode() -> anyhow::Result<()> {
+fn checks_notebooks_in_stable() -> anyhow::Result<()> {
     let tempdir = TempDir::new()?;
     std::fs::write(
         tempdir.path().join("main.ipynb"),
@@ -1853,7 +1853,6 @@ fn checks_notebooks_in_preview_mode() -> anyhow::Result<()> {
         .args(STDIN_BASE_OPTIONS)
         .arg("--select")
         .arg("F401")
-        .arg("--preview")
         .current_dir(&tempdir)
         , @r###"
     success: false
@@ -1867,64 +1866,3 @@ fn checks_notebooks_in_preview_mode() -> anyhow::Result<()> {
     "###);
     Ok(())
 }
-
-#[test]
-fn ignores_notebooks_in_stable() -> anyhow::Result<()> {
-    let tempdir = TempDir::new()?;
-    std::fs::write(
-        tempdir.path().join("main.ipynb"),
-        r#"
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "ad6f36d9-4b7d-4562-8d00-f15a0f1fbb6d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import random"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.0"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
-"#,
-    )?;
-
-    assert_cmd_snapshot!(Command::new(get_cargo_bin(BIN_NAME))
-        .args(STDIN_BASE_OPTIONS)
-        .arg("--select")
-        .arg("F401")
-        .current_dir(&tempdir)
-        , @r###"
-    success: true
-    exit_code: 0
-    ----- stdout -----
-    All checks passed!
-
-    ----- stderr -----
-    warning: No Python files found under the given path(s)
-    "###);
-    Ok(())
-}
diff --git a/crates/ruff/tests/snapshots/show_settings__display_default_settings.snap b/crates/ruff/tests/snapshots/show_settings__display_default_settings.snap
@@ -60,6 +60,7 @@ file_resolver.force_exclude = false
 file_resolver.include = [
 	"*.py",
 	"*.pyi",
+	"*.ipynb",
 	"**/pyproject.toml",
 ]
 file_resolver.extend_include = []
diff --git a/crates/ruff_linter/src/rules/flake8_bugbear/rules/useless_comparison.rs b/crates/ruff_linter/src/rules/flake8_bugbear/rules/useless_comparison.rs
@@ -25,6 +25,11 @@ use super::super::helpers::at_last_top_level_expression_in_cell;
 /// assert foo == bar, "`foo` and `bar` should be equal."
 /// ```
 ///
+/// ## Notebook behavior
+/// For Jupyter Notebooks, this rule is not applied to the last top-level expression in a cell.
+/// This is because it's common to have a notebook cell that ends with an expression,
+/// which will result in the `repr` of the evaluated expression being printed as the cell's output.
+///
 /// ## References
 /// - [Python documentation: `assert` statement](https://docs.python.org/3/reference/simple_stmts.html#the-assert-statement)
 #[violation]
@@ -43,9 +48,6 @@ impl Violation for UselessComparison {
 /// B015
 pub(crate) fn useless_comparison(checker: &mut Checker, expr: &Expr) {
     if expr.is_compare_expr() {
-        // For Jupyter Notebooks, ignore the last top-level expression for each cell.
-        // This is because it's common to have a cell that ends with an expression
-        // to display it's value.
         if checker.source_type.is_ipynb()
             && at_last_top_level_expression_in_cell(
                 checker.semantic(),
diff --git a/crates/ruff_linter/src/rules/flake8_bugbear/rules/useless_expression.rs b/crates/ruff_linter/src/rules/flake8_bugbear/rules/useless_expression.rs
@@ -26,6 +26,11 @@ use super::super::helpers::at_last_top_level_expression_in_cell;
 /// foo = 1 + 1
 /// ```
 ///
+/// ## Notebook behavior
+/// For Jupyter Notebooks, this rule is not applied to the last top-level expression in a cell.
+/// This is because it's common to have a notebook cell that ends with an expression,
+/// which will result in the `repr` of the evaluated expression being printed as the cell's output.
+///
 /// ## Known problems
 /// This rule ignores expression types that are commonly used for their side
 /// effects, such as function calls.
@@ -81,9 +86,6 @@ pub(crate) fn useless_expression(checker: &mut Checker, value: &Expr) {
         return;
     }
 
-    // For Jupyter Notebooks, ignore the last top-level expression for each cell.
-    // This is because it's common to have a cell that ends with an expression
-    // to display it's value.
     if checker.source_type.is_ipynb()
         && at_last_top_level_expression_in_cell(
             checker.semantic(),
diff --git a/crates/ruff_linter/src/rules/pycodestyle/rules/module_import_not_at_top_of_file.rs b/crates/ruff_linter/src/rules/pycodestyle/rules/module_import_not_at_top_of_file.rs
@@ -6,8 +6,7 @@ use ruff_text_size::Ranged;
 use crate::checkers::ast::Checker;
 
 /// ## What it does
-/// Checks for imports that are not at the top of the file. For Jupyter notebooks, this
-/// checks for imports that are not at the top of the cell.
+/// Checks for imports that are not at the top of the file.
 ///
 /// ## Why is this bad?
 /// According to [PEP 8], "imports are always put at the top of the file, just after any
@@ -36,6 +35,9 @@ use crate::checkers::ast::Checker;
 /// a = 1
 /// ```
 ///
+/// ## Notebook behavior
+/// For Jupyter notebooks, this rule checks for imports that are not at the top of a *cell*.
+///
 /// [PEP 8]: https://peps.python.org/pep-0008/#imports
 #[violation]
 pub struct ModuleImportNotAtTopOfFile {
diff --git a/crates/ruff_linter/src/rules/pydocstyle/rules/not_missing.rs b/crates/ruff_linter/src/rules/pydocstyle/rules/not_missing.rs
@@ -53,6 +53,9 @@ use crate::registry::Rule;
 /// def calculate_speed(distance: float, time: float) -> float: ...
 /// ```
 ///
+/// ## Notebook behavior
+/// This rule is ignored for Jupyter Notebooks.
+///
 /// ## References
 /// - [PEP 257 – Docstring Conventions](https://peps.python.org/pep-0257/)
 /// - [PEP 287 – reStructuredText Docstring Format](https://peps.python.org/pep-0287/)
diff --git a/crates/ruff_workspace/src/configuration.rs b/crates/ruff_workspace/src/configuration.rs
@@ -230,15 +230,9 @@ impl Configuration {
                 extend_exclude: FilePatternSet::try_from_iter(self.extend_exclude)?,
                 extend_include: FilePatternSet::try_from_iter(self.extend_include)?,
                 force_exclude: self.force_exclude.unwrap_or(false),
-                include: FilePatternSet::try_from_iter(self.include.unwrap_or_else(|| {
-                    let mut include = INCLUDE.to_vec();
-
-                    if global_preview.is_enabled() {
-                        include.push(FilePattern::Builtin("*.ipynb"));
-                    }
-
-                    include
-                }))?,
+                include: FilePatternSet::try_from_iter(
+                    self.include.unwrap_or_else(|| INCLUDE.to_vec()),
+                )?,
                 respect_gitignore: self.respect_gitignore.unwrap_or(true),
                 project_root: project_root.to_path_buf(),
             },
diff --git a/crates/ruff_workspace/src/options.rs b/crates/ruff_workspace/src/options.rs
@@ -241,13 +241,11 @@ pub struct Options {
     /// included here not for configuration but because we lint whether e.g. the
     /// `[project]` matches the schema.
     ///
-    /// If [preview](https://docs.astral.sh/ruff/preview/) is enabled, the default
-    /// includes notebook files (`.ipynb` extension). You can exclude them by adding
-    /// `*.ipynb` to [`extend-exclude`](#extend-exclude).
+    /// Notebook files (`.ipynb` extension) are included by default on Ruff 0.6.0+.
     ///
     /// For more information on the glob syntax, refer to the [`globset` documentation](https://docs.rs/globset/latest/globset/#syntax).
     #[option(
-        default = r#"["*.py", "*.pyi", "**/pyproject.toml"]"#,
+        default = r#"["*.py", "*.pyi", "*.ipynb", "**/pyproject.toml"]"#,
         value_type = "list[str]",
         example = r#"
             include = ["*.py"]
diff --git a/crates/ruff_workspace/src/settings.rs b/crates/ruff_workspace/src/settings.rs
@@ -137,6 +137,7 @@ pub(crate) static EXCLUDE: &[FilePattern] = &[
 pub(crate) static INCLUDE: &[FilePattern] = &[
     FilePattern::Builtin("*.py"),
     FilePattern::Builtin("*.pyi"),
+    FilePattern::Builtin("*.ipynb"),
     FilePattern::Builtin("**/pyproject.toml"),
 ];
 
diff --git a/docs/configuration.md b/docs/configuration.md
@@ -339,23 +339,9 @@ For example, `ruff check /path/to/excluded/file.py` will always lint `file.py`.
 
 ### Default inclusions
 
-By default, Ruff will discover files matching `*.py`, `*.ipy`, or `pyproject.toml`.
+By default, Ruff will discover files matching `*.py`, `*.pyi`, `*.ipynb`, or `pyproject.toml`.
 
 To lint or format files with additional file extensions, use the [`extend-include`](settings.md#extend-include) setting.
-
-=== "pyproject.toml"
-
-    ```toml
-    [tool.ruff]
-    extend-include = ["*.ipynb"]
-    ```
-
-=== "ruff.toml"
-
-    ```toml
-    extend-include = ["*.ipynb"]
-    ```
-
 You can also change the default selection using the [`include`](settings.md#include) setting.
 
 
@@ -378,78 +364,82 @@ You can also change the default selection using the [`include`](settings.md#incl
 
 ## Jupyter Notebook discovery
 
-Ruff has built-in support for [Jupyter Notebooks](https://jupyter.org/).
-
-!!! info
-    Notebooks are linted and formatted by default when using [preview mode](preview.md).
-    You can opt-out of notebook linting and formatting by adding `*.ipynb` to [`extend-exclude`](settings.md#extend-exclude).
+Ruff has built-in support for linting and formatting [Jupyter Notebooks](https://jupyter.org/),
+which are linted and formatted by default on version `0.6.0` and higher.
 
-To opt in to linting and formatting Jupyter Notebook (`.ipynb`) files, add the `*.ipynb` pattern to
-your [`extend-include`](settings.md#extend-include) setting, like so:
+If you'd prefer to either only lint or only format Jupyter Notebook files, you can use the
+section-specific `exclude` option to do so. For example, the following would only lint Jupyter
+Notebook files and not format them:
 
 === "pyproject.toml"
 
     ```toml
-    [tool.ruff]
-    extend-include = ["*.ipynb"]
+    [tool.ruff.format]
+    exclude = ["*.ipynb"]
     ```
 
 === "ruff.toml"
 
     ```toml
-    extend-include = ["*.ipynb"]
+    [format]
+    exclude = ["*.ipynb"]
     ```
 
-This will prompt Ruff to discover Jupyter Notebook (`.ipynb`) files in any specified
-directories, then lint and format them accordingly.
-
-If you'd prefer to either only lint or only format Jupyter Notebook files, you can use the
-section specific `exclude` option to do so. For example, the following would only lint Jupyter
-Notebook files and not format them:
+And, conversely, the following would only format Jupyter Notebook files and not lint them:
 
 === "pyproject.toml"
 
     ```toml
-    [tool.ruff]
-    extend-include = ["*.ipynb"]
-
-    [tool.ruff.format]
+    [tool.ruff.lint]
     exclude = ["*.ipynb"]
     ```
 
 === "ruff.toml"
 
     ```toml
-    extend-include = ["*.ipynb"]
-
-    [format]
+    [lint]
     exclude = ["*.ipynb"]
     ```
 
-And, conversely, the following would only format Jupyter Notebook files and not lint them:
+You can completely disable Jupyter Notebook support by updating the
+[`extend-exclude`](settings.md#extend-exclude) setting:
 
 === "pyproject.toml"
 
     ```toml
     [tool.ruff]
-    extend-include = ["*.ipynb"]
-
-    [tool.ruff.lint]
-    exclude = ["*.ipynb"]
+    extend-exclude = ["*.ipynb"]
     ```
 
 === "ruff.toml"
 
     ```toml
-    extend-include = ["*.ipynb"]
+    extend-exclude = ["*.ipynb"]
+    ```
 
-    [lint]
-    exclude = ["*.ipynb"]
+If you'd like to ignore certain rules specifically for Jupyter Notebook files, you can do so by
+using the [`per-file-ignores`](settings.md#per-file-ignores) setting:
+
+=== "pyproject.toml"
+
+    ```toml
+    [tool.ruff.lint.per-file-ignores]
+    "*.ipynb" = ["T20"]
+    ```
+
+=== "ruff.toml"
+
+    ```toml
+    [lint.per-file-ignores]
+    "*.ipynb" = ["T20"]
     ```
 
-Alternatively, pass the notebook file(s) to `ruff` on the command-line directly. For example,
-`ruff check /path/to/notebook.ipynb` will always lint `notebook.ipynb`. Similarly,
-`ruff format /path/to/notebook.ipynb` will always format `notebook.ipynb`.
+Some rules have different behavior when applied to Jupyter Notebook files. For
+example, when applied to `.py` files the
+[`module-import-not-at-top-of-file` (`E402`)](rules/module-import-not-at-top-of-file.md)
+rule detect imports at the top of a file, but for notebooks it detects imports at the top of a
+**cell**. For a given rule, the rule's documentation will always specify if it has different
+behavior when applied to Jupyter Notebook files.
 
 ## Command-line interface
 
diff --git a/docs/faq.md b/docs/faq.md
@@ -398,30 +398,8 @@ them. You can find the supported settings in the [API reference](settings.md#lin
 
 ## Does Ruff support Jupyter Notebooks?
 
-Ruff has built-in support for linting [Jupyter Notebooks](https://jupyter.org/).
-
-To opt in to linting Jupyter Notebook (`.ipynb`) files, add the `*.ipynb` pattern to your
-[`extend-include`](settings.md#extend-include) setting, like so:
-
-=== "pyproject.toml"
-
-    ```toml
-    [tool.ruff]
-    extend-include = ["*.ipynb"]
-    ```
-
-=== "ruff.toml"
-
-    ```toml
-    extend-include = ["*.ipynb"]
-    ```
-
-This will prompt Ruff to discover Jupyter Notebook (`.ipynb`) files in any specified
-directories, then lint and format them accordingly.
-
-Alternatively, pass the notebook file(s) to `ruff` on the command-line directly. For example,
-`ruff check /path/to/notebook.ipynb` will always lint `notebook.ipynb`. Similarly,
-`ruff format /path/to/notebook.ipynb` will always format `notebook.ipynb`.
+Ruff has built-in support for linting and formatting [Jupyter Notebooks](https://jupyter.org/). Refer to the
+[Jupyter Notebook section](configuration.md#jupyter-notebook-discovery) for more details.
 
 Ruff also integrates with [nbQA](https://github.com/nbQA-dev/nbQA), a tool for running linters and
 code formatters over Jupyter Notebooks.
diff --git a/ruff.schema.json b/ruff.schema.json

Original file line number	Diff line number	Diff line change
`@@ -60,6 +60,7 @@ file_resolver.force_exclude = false`
`60`	`60`	`file_resolver.include = [`
`61`	`61`	`"*.py",`
`62`	`62`	`"*.pyi",`
	`63`	`+ "*.ipynb",`
`63`	`64`	`"**/pyproject.toml",`
`64`	`65`	`]`
`65`	`66`	`file_resolver.extend_include = []`