mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2026-01-06 04:11:08 +00:00
2d1923ac7e
Part two of: https://github.com/Unstructured-IO/unstructured/pull/2842 Main changes compared to part one: * hash computation includes element's sequence number on page, page number, document filename and its text * there are more test for deterministic behavior of IDs returned by partitioning functions + their uniqueness (guaranteed at the document level, and high probability across multiple documents) This PR addresses the following issue: https://github.com/Unstructured-IO/unstructured/issues/2461
40 lines
1.1 KiB
JSON
40 lines
1.1 KiB
JSON
[
|
|
{
|
|
"element_id": "7997025526d4d565f2442e6c10be4c3d",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-10-16T22:37:02.481000+00:00",
|
|
"date_modified": "2023-10-16T22:37:07.918000+00:00",
|
|
"record_locator": {
|
|
"hubspot_id": "41286477879"
|
|
}
|
|
},
|
|
"filename": "41286477879.txt",
|
|
"filetype": "text/plain",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Call with Testing Ipsum",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "1111265d062cb14df259b8a212466554",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-10-16T22:37:02.481000+00:00",
|
|
"date_modified": "2023-10-16T22:37:07.918000+00:00",
|
|
"record_locator": {
|
|
"hubspot_id": "41286477879"
|
|
}
|
|
},
|
|
"filename": "41286477879.txt",
|
|
"filetype": "text/plain",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "<div style=\"\" dir=\"auto\" data-top-level=\"true\"><p style=\"margin:0;\">Log discussing details on call done with Testing Ipsum contact at 5:00pm.</p></div>",
|
|
"type": "NarrativeText"
|
|
}
|
|
] |