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/rtf/accent.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/accent.rtf",
"file_type": "rtf",
"file_size": 50,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "rtf test: accent",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/rtf/accent.txt",
"markdown_file": "../../../../test_documents/ground_truth/rtf/accent.md",
"source": "pandoc"
}
}

16
tools/benchmark-harness/fixtures/rtf/bookmark.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/bookmark.rtf",
"file_type": "rtf",
"file_size": 168,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "rtf test: bookmark",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/rtf/bookmark.txt",
"markdown_file": "../../../../test_documents/ground_truth/rtf/bookmark.md",
"source": "pandoc"
}
}

16
tools/benchmark-harness/fixtures/rtf/extraction_test.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/extraction_test.rtf",
"file_type": "rtf",
"file_size": 4262,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "rtf test: extraction_test",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/rtf/extraction_test.txt",
"markdown_file": "../../../../test_documents/ground_truth/rtf/extraction_test.md",
"source": "pandoc"
}
}

16
tools/benchmark-harness/fixtures/rtf/fake-doc.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/vendored/unstructured/rtf/fake-doc.rtf",
"file_type": "rtf",
"file_size": 408,
"expected_frameworks": ["kreuzberg", "pandoc", "tika", "unstructured"],
"metadata": {
"description": "Document from unstructured test suite",
"source": "unstructured",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/rtf/fake-doc.txt",
"source": "pandoc",
"markdown_file": "../../../../test_documents/ground_truth/rtf/fake-doc.md"
}
}

16
tools/benchmark-harness/fixtures/rtf/footnote.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/footnote.rtf",
"file_type": "rtf",
"file_size": 563,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "rtf test: footnote",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/rtf/footnote.txt",
"markdown_file": "../../../../test_documents/ground_truth/rtf/footnote.md",
"source": "pandoc"
}
}

16
tools/benchmark-harness/fixtures/rtf/formatting.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/formatting.rtf",
"file_type": "rtf",
"file_size": 40193,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "rtf test: formatting",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/rtf/formatting.txt",
"markdown_file": "../../../../test_documents/ground_truth/rtf/formatting.md",
"source": "pandoc"
}
}

16
tools/benchmark-harness/fixtures/rtf/heading.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/heading.rtf",
"file_type": "rtf",
"file_size": 45457,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "RTF test document: heading",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"markdown_file": "../../../../test_documents/ground_truth/rtf/heading.md",
"source": "pandoc",
"text_file": "../../../../test_documents/ground_truth/rtf/heading.txt"
}
}

16
tools/benchmark-harness/fixtures/rtf/image.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/image.rtf",
"file_type": "rtf",
"file_size": 32795,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "rtf test: image",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/rtf/image.txt",
"markdown_file": "../../../../test_documents/ground_truth/rtf/image.md",
"source": "pandoc"
}
}

16
tools/benchmark-harness/fixtures/rtf/link.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/link.rtf",
"file_type": "rtf",
"file_size": 261,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "rtf test: link",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/rtf/link.txt",
"markdown_file": "../../../../test_documents/ground_truth/rtf/link.md",
"source": "pandoc"
}
}

16
tools/benchmark-harness/fixtures/rtf/list_complex.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/list_complex.rtf",
"file_type": "rtf",
"file_size": 63224,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "RTF test document: list_complex",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"markdown_file": "../../../../test_documents/ground_truth/rtf/list_complex.md",
"source": "pandoc",
"text_file": "../../../../test_documents/ground_truth/rtf/list_complex.txt"
}
}

16
tools/benchmark-harness/fixtures/rtf/list_simple.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/list_simple.rtf",
"file_type": "rtf",
"file_size": 1712,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "rtf test: list_simple",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/rtf/list_simple.txt",
"markdown_file": "../../../../test_documents/ground_truth/rtf/list_simple.md",
"source": "pandoc"
}
}

16
tools/benchmark-harness/fixtures/rtf/lorem_ipsum.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/lorem_ipsum.rtf",
"file_type": "rtf",
"file_size": 3956,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "rtf test: lorem_ipsum",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/rtf/lorem_ipsum.txt",
"markdown_file": "../../../../test_documents/ground_truth/rtf/lorem_ipsum.md",
"source": "pandoc"
}
}

16
tools/benchmark-harness/fixtures/rtf/table_error_codes.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/table_error_codes.rtf",
"file_type": "rtf",
"file_size": 5300,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "RTF test document: table_error_codes",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"markdown_file": "../../../../test_documents/ground_truth/rtf/table_error_codes.md",
"source": "pandoc",
"text_file": "../../../../test_documents/ground_truth/rtf/table_error_codes.txt"
}
}

16
tools/benchmark-harness/fixtures/rtf/table_simple.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/table_simple.rtf",
"file_type": "rtf",
"file_size": 241,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "RTF test document: table_simple",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"markdown_file": "../../../../test_documents/ground_truth/rtf/table_simple.md",
"source": "pandoc",
"text_file": "../../../../test_documents/ground_truth/rtf/table_simple.txt"
}
}

16
tools/benchmark-harness/fixtures/rtf/tables.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/tables.rtf",
"file_type": "rtf",
"file_size": 8499,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "rtf test: tables",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/rtf/tables.txt",
"markdown_file": "../../../../test_documents/ground_truth/rtf/tables.md",
"source": "pandoc"
}
}

16
tools/benchmark-harness/fixtures/rtf/unicode.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/unicode.rtf",
"file_type": "rtf",
"file_size": 92,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "RTF test document: unicode",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"markdown_file": "../../../../test_documents/ground_truth/rtf/unicode.md",
"source": "pandoc",
"text_file": "../../../../test_documents/ground_truth/rtf/unicode.txt"
}
}

16
tools/benchmark-harness/fixtures/rtf/word_sample.json Normal file
View File

@@ -0,0 +1,16 @@
{
"document": "../../../../test_documents/rtf/word_sample.rtf",
"file_type": "rtf",
"file_size": 163580,
"expected_frameworks": ["kreuzberg"],
"metadata": {
"description": "rtf test: word_sample",
"source": "pandoc-generated",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/rtf/word_sample.txt",
"markdown_file": "../../../../test_documents/ground_truth/rtf/word_sample.md",
"source": "pandoc"
}
}