Nomad changes

2026-06-01 23:40:55 +02:00
parent 72b1a0a6ed
commit b4c07d3693
5723 changed files with 1130655 additions and 0 deletions
--- a/tools/benchmark-harness/fixtures/doc/duplicate-paragraphs.json
+++ b/tools/benchmark-harness/fixtures/doc/duplicate-paragraphs.json
@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/vendored/unstructured/doc/duplicate-paragraphs.doc",
+  "file_type": "doc",
+  "file_size": 18432,
+  "expected_frameworks": ["kreuzberg", "tika", "unstructured"],
+  "metadata": {
+    "description": "Document from unstructured test suite",
+    "source": "unstructured",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/doc/duplicate-paragraphs.txt",
+    "source": "pandoc",
+    "markdown_file": "../../../../test_documents/ground_truth/doc/duplicate-paragraphs.md"
+  }
+}
--- a/tools/benchmark-harness/fixtures/doc/fake-doc-emphasized-text.json
+++ b/tools/benchmark-harness/fixtures/doc/fake-doc-emphasized-text.json
@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/vendored/unstructured/doc/fake-doc-emphasized-text.doc",
+  "file_type": "doc",
+  "file_size": 27648,
+  "expected_frameworks": ["kreuzberg", "tika", "unstructured"],
+  "metadata": {
+    "description": "Document from unstructured test suite",
+    "source": "unstructured",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/doc/fake-doc-emphasized-text.txt",
+    "source": "pandoc",
+    "markdown_file": "../../../../test_documents/ground_truth/doc/fake-doc-emphasized-text.md"
+  }
+}
--- a/tools/benchmark-harness/fixtures/doc/fake.json
+++ b/tools/benchmark-harness/fixtures/doc/fake.json
@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/vendored/unstructured/doc/fake.doc",
+  "file_type": "doc",
+  "file_size": 18432,
+  "expected_frameworks": ["kreuzberg", "tika", "unstructured"],
+  "metadata": {
+    "description": "Document from unstructured test suite",
+    "source": "unstructured",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/doc/fake.txt",
+    "source": "pandoc",
+    "markdown_file": "../../../../test_documents/ground_truth/doc/fake.md"
+  }
+}
--- a/tools/benchmark-harness/fixtures/doc/simple.json
+++ b/tools/benchmark-harness/fixtures/doc/simple.json
@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/vendored/unstructured/doc/simple.doc",
+  "file_type": "doc",
+  "file_size": 15872,
+  "expected_frameworks": ["kreuzberg", "tika", "unstructured"],
+  "metadata": {
+    "description": "Document from unstructured test suite",
+    "source": "unstructured",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/doc/simple.txt",
+    "source": "pandoc",
+    "markdown_file": "../../../../test_documents/ground_truth/doc/simple.md"
+  }
+}
--- a/tools/benchmark-harness/fixtures/doc/unit_test_lists.json
+++ b/tools/benchmark-harness/fixtures/doc/unit_test_lists.json
@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/doc/unit_test_lists.doc",
+  "file_type": "doc",
+  "file_size": 16384,
+  "expected_frameworks": ["kreuzberg"],
+  "metadata": {
+    "description": "doc test: unit_test_lists",
+    "source": "pandoc-generated",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/doc/unit_test_lists.txt",
+    "markdown_file": "../../../../test_documents/ground_truth/doc/unit_test_lists.md",
+    "source": "pandoc"
+  }
+}