Files
wehub-resource-sync 461bf6fd40
CI / lint (3.11) (push) Has been cancelled
CI / lint (3.12) (push) Has been cancelled
CI / lint (3.13) (push) Has been cancelled
CI / shellcheck (push) Has been cancelled
CI / shfmt (push) Has been cancelled
CI / setup (3.11) (push) Has been cancelled
CI / setup (3.12) (push) Has been cancelled
CI / setup (3.13) (push) Has been cancelled
CI / check-licenses (3.12) (push) Has been cancelled
CI / test_unit (3.11) (push) Has been cancelled
CI / test_unit (3.12) (push) Has been cancelled
CI / test_unit (3.13) (push) Has been cancelled
CI / test_unit_no_extras (3.11) (push) Has been cancelled
CI / test_unit_no_extras (3.12) (push) Has been cancelled
CI / test_json_to_html (3.12) (push) Has been cancelled
CI / test_unit_no_extras (3.13) (push) Has been cancelled
CI / test_unit_dependency_extras (csv, 3.12, --extra csv) (push) Has been cancelled
CI / test_unit_dependency_extras (xlsx, 3.11, --extra xlsx) (push) Has been cancelled
CI / test_unit_dependency_extras (xlsx, 3.12, --extra xlsx) (push) Has been cancelled
CI / test_unit_dependency_extras (csv, 3.11, --extra csv) (push) Has been cancelled
CI / test_unit_dependency_extras (csv, 3.13, --extra csv) (push) Has been cancelled
CI / test_unit_dependency_extras (docx, 3.11, --extra docx) (push) Has been cancelled
CI / test_unit_dependency_extras (docx, 3.12, --extra docx) (push) Has been cancelled
CI / test_unit_dependency_extras (docx, 3.13, --extra docx) (push) Has been cancelled
CI / test_unit_dependency_extras (markdown, 3.11, --extra md) (push) Has been cancelled
CI / test_unit_dependency_extras (markdown, 3.12, --extra md) (push) Has been cancelled
CI / test_unit_dependency_extras (markdown, 3.13, --extra md) (push) Has been cancelled
CI / test_unit_dependency_extras (odt, 3.11, --extra odt) (push) Has been cancelled
CI / test_unit_dependency_extras (odt, 3.12, --extra odt) (push) Has been cancelled
CI / test_unit_dependency_extras (odt, 3.13, --extra odt) (push) Has been cancelled
CI / test_unit_dependency_extras (pdf-image, 3.11, --extra pdf --extra image --extra paddleocr) (push) Has been cancelled
CI / test_unit_dependency_extras (pdf-image, 3.12, --extra pdf --extra image --extra paddleocr) (push) Has been cancelled
CI / test_unit_dependency_extras (pdf-image, 3.13, --extra pdf --extra image --extra paddleocr) (push) Has been cancelled
CI / test_unit_dependency_extras (pptx, 3.11, --extra pptx) (push) Has been cancelled
CI / test_unit_dependency_extras (pptx, 3.12, --extra pptx) (push) Has been cancelled
CI / test_unit_dependency_extras (pptx, 3.13, --extra pptx) (push) Has been cancelled
CI / test_unit_dependency_extras (pypandoc, 3.11, --extra epub --extra org --extra rtf --extra rst) (push) Has been cancelled
CI / test_unit_dependency_extras (pypandoc, 3.12, --extra epub --extra org --extra rtf --extra rst) (push) Has been cancelled
CI / test_unit_dependency_extras (pypandoc, 3.13, --extra epub --extra org --extra rtf --extra rst) (push) Has been cancelled
Build And Push Docker Image / set-short-sha (push) Has been cancelled
Partition Benchmark / setup (push) Has been cancelled
Partition Benchmark / Measure and compare partition() runtime (push) Has been cancelled
CI / test_unit_dependency_extras (xlsx, 3.13, --extra xlsx) (push) Has been cancelled
CI / test_ingest_src (3.12) (push) Has been cancelled
CI / test_json_to_markdown (3.12) (push) Has been cancelled
CI / changelog (push) Has been cancelled
CI / test_dockerfile (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
Build And Push Docker Image / build-images (linux/amd64, opensource-linux-8core) (push) Has been cancelled
Build And Push Docker Image / build-images (linux/arm64, ubuntu-24.04-arm) (push) Has been cancelled
Build And Push Docker Image / publish-images (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:33:56 +08:00

134 lines
3.8 KiB
JSON

[
{
"type": "NarrativeText",
"element_id": "fc01503614e0f12f585427cccf81cf86",
"text": "This is a test document to use for unit tests.",
"metadata": {
"filename": "fake-text.txt",
"languages": [
"eng"
],
"filetype": "text/plain",
"data_source": {
"url": "https://unstructuredio.sharepoint.com/Shared%20Documents/fake-text.txt",
"version": "1.0",
"record_locator": {
"server_path": "/Shared Documents/fake-text.txt",
"site_url": "https://unstructuredio.sharepoint.com"
},
"date_created": "1686891895.0",
"date_modified": "1686891895.0"
}
}
},
{
"type": "Address",
"element_id": "d06d10c0722ac08a2488076a48e858d5",
"text": "Doylestown, PA 18901",
"metadata": {
"filename": "fake-text.txt",
"languages": [
"eng"
],
"filetype": "text/plain",
"data_source": {
"url": "https://unstructuredio.sharepoint.com/Shared%20Documents/fake-text.txt",
"version": "1.0",
"record_locator": {
"server_path": "/Shared Documents/fake-text.txt",
"site_url": "https://unstructuredio.sharepoint.com"
},
"date_created": "1686891895.0",
"date_modified": "1686891895.0"
}
}
},
{
"type": "Title",
"element_id": "a190164de573571375ecf759a5027a3a",
"text": "Important points:",
"metadata": {
"filename": "fake-text.txt",
"languages": [
"eng"
],
"filetype": "text/plain",
"data_source": {
"url": "https://unstructuredio.sharepoint.com/Shared%20Documents/fake-text.txt",
"version": "1.0",
"record_locator": {
"server_path": "/Shared Documents/fake-text.txt",
"site_url": "https://unstructuredio.sharepoint.com"
},
"date_created": "1686891895.0",
"date_modified": "1686891895.0"
}
}
},
{
"type": "ListItem",
"element_id": "64c58eb106608ad05424e47bbcdef7dc",
"text": "Hamburgers are delicious",
"metadata": {
"filename": "fake-text.txt",
"languages": [
"eng"
],
"filetype": "text/plain",
"data_source": {
"url": "https://unstructuredio.sharepoint.com/Shared%20Documents/fake-text.txt",
"version": "1.0",
"record_locator": {
"server_path": "/Shared Documents/fake-text.txt",
"site_url": "https://unstructuredio.sharepoint.com"
},
"date_created": "1686891895.0",
"date_modified": "1686891895.0"
}
}
},
{
"type": "ListItem",
"element_id": "9210d7882755a60fc82272a0e93df94f",
"text": "Dogs are the best",
"metadata": {
"filename": "fake-text.txt",
"languages": [
"eng"
],
"filetype": "text/plain",
"data_source": {
"url": "https://unstructuredio.sharepoint.com/Shared%20Documents/fake-text.txt",
"version": "1.0",
"record_locator": {
"server_path": "/Shared Documents/fake-text.txt",
"site_url": "https://unstructuredio.sharepoint.com"
},
"date_created": "1686891895.0",
"date_modified": "1686891895.0"
}
}
},
{
"type": "ListItem",
"element_id": "970dd4ac687529e2d2126e0a51cb7c27",
"text": "I love fuzzy blankets",
"metadata": {
"filename": "fake-text.txt",
"languages": [
"eng"
],
"filetype": "text/plain",
"data_source": {
"url": "https://unstructuredio.sharepoint.com/Shared%20Documents/fake-text.txt",
"version": "1.0",
"record_locator": {
"server_path": "/Shared Documents/fake-text.txt",
"site_url": "https://unstructuredio.sharepoint.com"
},
"date_created": "1686891895.0",
"date_modified": "1686891895.0"
}
}
}
]