Fix AttributeError when raw cell contains non-dict YAML content (#1451)

* Add test notebook to reproduce issue with invalid YAML in raw cell
* Fix AttributeError when raw cell contains non-dict YAML content
* Add an example notebook with complex YAML-like content

Co-authored-by: mwouts <[email protected]>
Co-authored-by: copilot-swe-agent[bot] <[email protected]>
Co-authored-by: Marc Wouts <[email protected]>

Author: Copilot

src/jupytext/header.py

@@ -330,9 +330,12 @@ def metadata_and_cell_to_metadata(nb, fmt, unsupported_keys=None):
                 except (yaml.parser.ParserError, yaml.scanner.ScannerError):
                     logging.warning("[jupytext] failed to parse YAML in raw cell")
                 else:
-                    nb.cells = nb.cells[1:]
-                    if "root_level_metadata_filter" not in fmt and default_root_level_metadata_filter(fmt) == "all":
-                        metadata.setdefault("jupytext", {})["root_level_metadata_filter"] = "-" + ",-".join(frontmatter)
-                    metadata = recursive_update(frontmatter, metadata, overwrite=False)
+                    if not isinstance(frontmatter, dict):
+                        logging.warning("[jupytext] YAML header in raw cell is not a dictionary")
+                    else:
+                        nb.cells = nb.cells[1:]
+                        if "root_level_metadata_filter" not in fmt and default_root_level_metadata_filter(fmt) == "all":
+                            metadata.setdefault("jupytext", {})["root_level_metadata_filter"] = "-" + ",-".join(frontmatter)
+                        metadata = recursive_update(frontmatter, metadata, overwrite=False)
     nb.metadata = metadata
     return nb

tests/data/notebooks/inputs/ipynb_py/raw_cell_with_complex_yaml_like_content.ipynb

@@ -0,0 +1,42 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "b32297a4",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "\n",
+    "This is a complex paragraph\n",
+    "that is split over multiple lines.\n",
+    "\n",
+    "It also includes blank lines.\n",
+    "\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "id": "0b3bde0a",
+   "source": [
+    "print(\"Hello, World!\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

tests/data/notebooks/inputs/ipynb_py/raw_cell_with_non_dict_yaml_content.ipynb

@@ -0,0 +1,36 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "b32297a4",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "Content.\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "id": "0b3bde0a",
+   "source": [
+    "print(\"Hello, World!\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

tests/data/notebooks/outputs/ipynb_to_Rmd/raw_cell_with_complex_yaml_like_content.Rmd

@@ -0,0 +1,18 @@
+---
+
+This is a complex paragraph
+that is split over multiple lines.
+
+It also includes blank lines.
+
+
+jupyter:
+  kernelspec:
+    display_name: Python 3
+    language: python
+    name: python3
+---
+
+```{python}
+print("Hello, World!")
+```

tests/data/notebooks/outputs/ipynb_to_Rmd/raw_cell_with_non_dict_yaml_content.Rmd

@@ -0,0 +1,12 @@
+---
+Content.
+jupyter:
+  kernelspec:
+    display_name: Python 3
+    language: python
+    name: python3
+---
+
+```{python}
+print("Hello, World!")
+```

tests/data/notebooks/outputs/ipynb_to_hydrogen/raw_cell_with_complex_yaml_like_content.py

@@ -0,0 +1,17 @@
+# ---
+#
+# This is a complex paragraph
+# that is split over multiple lines.
+#
+# It also includes blank lines.
+#
+#
+# jupyter:
+#   kernelspec:
+#     display_name: Python 3
+#     language: python
+#     name: python3
+# ---
+
+# %%
+print("Hello, World!")

tests/data/notebooks/outputs/ipynb_to_hydrogen/raw_cell_with_non_dict_yaml_content.py

@@ -0,0 +1,11 @@
+# ---
+# Content.
+# jupyter:
+#   kernelspec:
+#     display_name: Python 3
+#     language: python
+#     name: python3
+# ---
+
+# %%
+print("Hello, World!")

tests/data/notebooks/outputs/ipynb_to_md/raw_cell_with_complex_yaml_like_content.md

@@ -0,0 +1,18 @@
+---
+
+This is a complex paragraph
+that is split over multiple lines.
+
+It also includes blank lines.
+
+
+jupyter:
+  kernelspec:
+    display_name: Python 3
+    language: python
+    name: python3
+---
+
+```python
+print("Hello, World!")
+```

tests/data/notebooks/outputs/ipynb_to_md/raw_cell_with_non_dict_yaml_content.md

@@ -0,0 +1,12 @@
+---
+Content.
+jupyter:
+  kernelspec:
+    display_name: Python 3
+    language: python
+    name: python3
+---
+
+```python
+print("Hello, World!")
+```

tests/data/notebooks/outputs/ipynb_to_myst/raw_cell_with_complex_yaml_like_content.md

@@ -0,0 +1,23 @@
+---
+kernelspec:
+  display_name: Python 3
+  language: python
+  name: python3
+---
+
+```{raw-cell}
+
+---
+
+This is a complex paragraph
+that is split over multiple lines.
+
+It also includes blank lines.
+
+
+---
+```
+
+```{code-cell}
+print("Hello, World!")
+```