hjess/fil
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Nomad changes
All checks were successful
Deploy fil (kreuzberg) / deploy (push) Successful in 49s
Details

Browse Source
This commit is contained in:
Henrik Jess Nielsen
2026-06-01 23:40:55 +02:00
parent 72b1a0a6ed
commit b4c07d3693
5723 changed files with 1130655 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
tools/benchmark-harness/fixtures/csv/csv-comma-in-cell.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/vendored/docling/csv/csv-comma-in-cell.csv",
"file_type": "csv",
"file_size": 46,
"expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/csv/csv-comma-in-cell.txt",
"source": "pandoc",
"markdown_file": "../../../../test_documents/ground_truth/csv/csv-comma-in-cell.md"
}
}

16
tools/benchmark-harness/fixtures/csv/csv-comma.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/vendored/docling/csv/csv-comma.csv",
"file_type": "csv",
"file_size": 1005,
"expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/csv/csv-comma.txt",
"source": "pandoc",
"markdown_file": "../../../../test_documents/ground_truth/csv/csv-comma.md"
}
}

16
tools/benchmark-harness/fixtures/csv/csv-inconsistent-header.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/vendored/docling/csv/csv-inconsistent-header.csv",
"file_type": "csv",
"file_size": 42,
"expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/csv/csv-inconsistent-header.txt",
"source": "pandoc",
"markdown_file": "../../../../test_documents/ground_truth/csv/csv-inconsistent-header.md"
}
}

16
tools/benchmark-harness/fixtures/csv/csv-pipe.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/vendored/docling/csv/csv-pipe.csv",
"file_type": "csv",
"file_size": 997,
"expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/csv/csv-pipe.txt",
"source": "pandoc",
"markdown_file": "../../../../test_documents/ground_truth/csv/csv-pipe.md"
}
}

16
tools/benchmark-harness/fixtures/csv/csv-semicolon.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/vendored/docling/csv/csv-semicolon.csv",
"file_type": "csv",
"file_size": 997,
"expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/csv/csv-semicolon.txt",
"source": "pandoc",
"markdown_file": "../../../../test_documents/ground_truth/csv/csv-semicolon.md"
}
}

16
tools/benchmark-harness/fixtures/csv/csv-tab.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/vendored/docling/csv/csv-tab.csv",
"file_type": "csv",
"file_size": 997,
"expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/csv/csv-tab.txt",
"source": "pandoc",
"markdown_file": "../../../../test_documents/ground_truth/csv/csv-tab.md"
}
}

16
tools/benchmark-harness/fixtures/csv/csv-too-few-columns.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/vendored/docling/csv/csv-too-few-columns.csv",
"file_type": "csv",
"file_size": 44,
"expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/csv/csv-too-few-columns.txt",
"source": "pandoc",
"markdown_file": "../../../../test_documents/ground_truth/csv/csv-too-few-columns.md"
}
}

16
tools/benchmark-harness/fixtures/csv/csv-too-many-columns.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/vendored/docling/csv/csv-too-many-columns.csv",
"file_type": "csv",
"file_size": 46,
"expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/csv/csv-too-many-columns.txt",
"source": "pandoc",
"markdown_file": "../../../../test_documents/ground_truth/csv/csv-too-many-columns.md"
}
}

16
tools/benchmark-harness/fixtures/csv/data_table.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/csv/data_table.csv",
"file_type": "csv",
"file_size": 476,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "csv test: data_table",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/csv/data_table.txt",
"markdown_file": "../../../../test_documents/ground_truth/csv/data_table.md",
"source": "pandoc"
}
}

16
tools/benchmark-harness/fixtures/csv/stanley_cups.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/csv/stanley_cups.csv",
"file_type": "csv",
"file_size": 91,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "csv test: stanley_cups",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/csv/stanley_cups.txt",
"markdown_file": "../../../../test_documents/ground_truth/csv/stanley_cups.md",
"source": "pandoc"
}
}

16
tools/benchmark-harness/fixtures/csv/test_mskanji.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/vendored/markitdown/csv/test_mskanji.csv",
"file_type": "csv",
"file_size": 70,
"expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
"metadata": {
"description": "Document from markitdown test suite",
"source": "markitdown",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/csv/test_mskanji.txt",
"source": "pandoc",
"markdown_file": "../../../../test_documents/ground_truth/csv/test_mskanji.md"
}
}