Add jupyter notebook cell ids in 4.5+ if missing (#6853)

**Summary** See
https://github.com/astral-sh/ruff/issues/6834#issuecomment-1691202417

**Test Plan** Added a new notebook

Cargo.lock

@@ -876,8 +876,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "be4136b2a15dd319360be1c07d9933517ccf0be8f16bf62a3bee4f0d618df427"
 dependencies = [
  "cfg-if",
+ "js-sys",
  "libc",
  "wasi 0.11.0+wasi-snapshot-preview1",
+ "wasm-bindgen",
 ]
 
 [[package]]
@@ -2128,6 +2130,7 @@ dependencies = [
  "typed-arena",
  "unicode-width",
  "unicode_names2",
+ "uuid",
  "wsl",
 ]
 
@@ -3346,9 +3349,26 @@ checksum = "711b9620af191e0cdc7468a8d14e709c3dcdb115b36f838e601583af800a370a"
 
 [[package]]
 name = "uuid"
-version = "1.4.0"
+version = "1.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d023da39d1fde5a8a3fe1f3e01ca9632ada0a63e9797de55a879d6e2236277be"
+checksum = "79daa5ed5740825c40b389c5e50312b9c86df53fccd33f281df655642b43869d"
+dependencies = [
+ "getrandom",
+ "rand",
+ "uuid-macro-internal",
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "uuid-macro-internal"
+version = "1.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f7e1ba1f333bd65ce3c9f27de592fcbc256dafe3af2717f56d7c87761fbaccf4"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.23",
+]
 
 [[package]]
 name = "valuable"

Cargo.toml

@@ -50,6 +50,7 @@ tracing = "0.1.37"
 tracing-indicatif = "0.3.4"
 tracing-subscriber = { version = "0.3.17", features = ["env-filter"] }
 unicode-width = "0.1.10"
+uuid = { version = "1.4.1", features = ["v4", "fast-rng", "macro-diagnostics", "js"] }
 wsl = { version = "0.1.0" }
 
 # v1.0.1

crates/ruff/Cargo.toml

@@ -77,6 +77,7 @@ toml = { workspace = true }
 typed-arena = { version = "2.0.2" }
 unicode-width = { workspace = true }
 unicode_names2 = { version = "0.6.0", git = "https://github.com/youknowone/unicode_names2.git", rev = "4ce16aa85cbcdd9cc830410f1a72ef9a235f2fde" }
+uuid = { workspace = true, features = ["v4", "fast-rng", "macro-diagnostics", "js"] }
 wsl = { version = "0.1.0" }
 
 [dev-dependencies]

crates/ruff/resources/test/fixtures/jupyter/add_missing_cell_id.ipynb

@@ -0,0 +1,37 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import math\n",
+    "import os\n",
+    "\n",
+    "math.pi"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python (ruff)",
+   "language": "python",
+   "name": "ruff"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

crates/ruff/src/jupyter/notebook.rs

@@ -9,6 +9,7 @@ use itertools::Itertools;
 use once_cell::sync::OnceCell;
 use serde::Serialize;
 use serde_json::error::Category;
+use uuid::Uuid;
 
 use ruff_diagnostics::Diagnostic;
 use ruff_python_parser::lexer::lex;
@@ -156,7 +157,7 @@ impl Notebook {
                 TextRange::default(),
             )
         })?;
-        let raw_notebook: RawNotebook = match serde_json::from_reader(reader.by_ref()) {
+        let mut raw_notebook: RawNotebook = match serde_json::from_reader(reader.by_ref()) {
             Ok(notebook) => notebook,
             Err(err) => {
                 // Translate the error into a diagnostic
@@ -262,6 +263,23 @@ impl Notebook {
             cell_offsets.push(current_offset);
         }
 
+        // Add cell ids to 4.5+ notebooks if they are missing
+        // https://github.com/astral-sh/ruff/issues/6834
+        // https://github.com/jupyter/enhancement-proposals/blob/master/62-cell-id/cell-id.md#required-field
+        if raw_notebook.nbformat == 4 && raw_notebook.nbformat_minor >= 5 {
+            for cell in &mut raw_notebook.cells {
+                let id = match cell {
+                    Cell::Code(cell) => &mut cell.id,
+                    Cell::Markdown(cell) => &mut cell.id,
+                    Cell::Raw(cell) => &mut cell.id,
+                };
+                if id.is_none() {
+                    // https://github.com/jupyter/enhancement-proposals/blob/master/62-cell-id/cell-id.md#questions
+                    *id = Some(Uuid::new_v4().to_string());
+                }
+            }
+        }
+
         Ok(Self {
             raw: raw_notebook,
             index: OnceCell::new(),
@@ -662,21 +680,27 @@ print("after empty cells")
         Ok(())
     }
 
-    #[test]
-    fn test_no_cell_id() -> Result<()> {
-        let path = "no_cell_id.ipynb".to_string();
-        let source_notebook = read_jupyter_notebook(path.as_ref())?;
+    // Version <4.5, don't emit cell ids
+    #[test_case(Path::new("no_cell_id.ipynb"), false; "no_cell_id")]
+    // Version 4.5, cell ids are missing and need to be added
+    #[test_case(Path::new("add_missing_cell_id.ipynb"), true; "add_missing_cell_id")]
+    fn test_cell_id(path: &Path, has_id: bool) -> Result<()> {
+        let source_notebook = read_jupyter_notebook(path)?;
         let source_kind = SourceKind::IpyNotebook(source_notebook);
         let (_, transformed) = test_contents(
             &source_kind,
-            path.as_ref(),
+            path,
             &settings::Settings::for_rule(Rule::UnusedImport),
         );
         let linted_notebook = transformed.into_owned().expect_ipy_notebook();
         let mut writer = Vec::new();
         linted_notebook.write_inner(&mut writer)?;
         let actual = String::from_utf8(writer)?;
-        assert!(!actual.contains(r#""id":"#));
+        if has_id {
+            assert!(actual.contains(r#""id": ""#));
+        } else {
+            assert!(!actual.contains(r#""id":"#));
+        }
         Ok(())
     }
 }