Nomad changes

tools/benchmark-harness/fixtures/ipynb/mime.json

@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/jupyter/mime.ipynb",
+  "file_type": "ipynb",
+  "file_size": 4144,
+  "expected_frameworks": ["kreuzberg"],
+  "metadata": {
+    "description": "Jupyter notebook demonstrating MIME type display formatters and custom repr_mimebundle",
+    "source": "pandoc-test-suite",
+    "size_category": "tiny"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/ipynb/mime.txt",
+    "markdown_file": "../../../../test_documents/ground_truth/ipynb/mime.md",
+    "source": "pandoc"
+  }
+}

tools/benchmark-harness/fixtures/ipynb/mime_out.json

@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/jupyter/mime.out.ipynb",
+  "file_type": "ipynb",
+  "file_size": 3764,
+  "expected_frameworks": ["kreuzberg"],
+  "metadata": {
+    "description": "Jupyter notebook with executed MIME type outputs including text, HTML, markdown, and LaTeX representations",
+    "source": "pandoc-test-suite",
+    "size_category": "tiny"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/ipynb/mime.out.txt",
+    "markdown_file": "../../../../test_documents/ground_truth/ipynb/mime.out.md",
+    "source": "pandoc"
+  }
+}

tools/benchmark-harness/fixtures/ipynb/rank.json

@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/jupyter/rank.ipynb",
+  "file_type": "ipynb",
+  "file_size": 1556,
+  "expected_frameworks": ["kreuzberg"],
+  "metadata": {
+    "description": "Jupyter notebook with matplotlib plot output and image rendering",
+    "source": "pandoc-test-suite",
+    "size_category": "tiny"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/ipynb/rank.txt",
+    "markdown_file": "../../../../test_documents/ground_truth/ipynb/rank.md",
+    "source": "pandoc"
+  }
+}

tools/benchmark-harness/fixtures/ipynb/simple.json

@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/jupyter/simple.ipynb",
+  "file_type": "ipynb",
+  "file_size": 23791,
+  "expected_frameworks": ["kreuzberg"],
+  "metadata": {
+    "description": "Jupyter notebook with markdown cells, code cells with HTML output, and cell attachments",
+    "source": "pandoc-test-suite",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/ipynb/simple.txt",
+    "markdown_file": "../../../../test_documents/ground_truth/ipynb/simple.md",
+    "source": "pandoc"
+  }
+}

tools/benchmark-harness/fixtures/ipynb/test_notebook.json

@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/vendored/markitdown/ipynb/test_notebook.ipynb",
+  "file_type": "ipynb",
+  "file_size": 1408,
+  "expected_frameworks": ["kreuzberg", "markitdown", "pandoc", "tika"],
+  "metadata": {
+    "description": "Document from markitdown test suite",
+    "source": "markitdown",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/ipynb/test_notebook.txt",
+    "source": "pandoc",
+    "markdown_file": "../../../../test_documents/ground_truth/ipynb/test_notebook.md"
+  }
+}