mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2026-01-05 20:00:56 +00:00
Canonicalize JSON produced for ingest tests such that incidental changes is _form_ of the JSON objects (keys moving around) that does not change the _content_ of that JSON object does not trigger an ingest-test failure.
128 lines
3.7 KiB
JSON
128 lines
3.7 KiB
JSON
[
|
|
{
|
|
"element_id": "1df8eeb8be847c3a1a7411e3be3e0396",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-20T23:48:13.303000+00:00",
|
|
"date_modified": "2023-06-20T23:48:13.303000+00:00",
|
|
"record_locator": {
|
|
"protocol": "gs",
|
|
"remote_file_path": "utic-test-ingest-fixtures/nested-1/fake-text.txt"
|
|
},
|
|
"url": "gs://utic-test-ingest-fixtures/nested-1/fake-text.txt",
|
|
"version": "CKyIrMaE0/8CEAE="
|
|
},
|
|
"filetype": "text/plain",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "This is a test document to use for unit tests.",
|
|
"type": "NarrativeText"
|
|
},
|
|
{
|
|
"element_id": "a9d4657034aa3fdb5177f1325e912362",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-20T23:48:13.303000+00:00",
|
|
"date_modified": "2023-06-20T23:48:13.303000+00:00",
|
|
"record_locator": {
|
|
"protocol": "gs",
|
|
"remote_file_path": "utic-test-ingest-fixtures/nested-1/fake-text.txt"
|
|
},
|
|
"url": "gs://utic-test-ingest-fixtures/nested-1/fake-text.txt",
|
|
"version": "CKyIrMaE0/8CEAE="
|
|
},
|
|
"filetype": "text/plain",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Doylestown, PA 18901",
|
|
"type": "Address"
|
|
},
|
|
{
|
|
"element_id": "9c218520320f238595f1fde74bdd137d",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-20T23:48:13.303000+00:00",
|
|
"date_modified": "2023-06-20T23:48:13.303000+00:00",
|
|
"record_locator": {
|
|
"protocol": "gs",
|
|
"remote_file_path": "utic-test-ingest-fixtures/nested-1/fake-text.txt"
|
|
},
|
|
"url": "gs://utic-test-ingest-fixtures/nested-1/fake-text.txt",
|
|
"version": "CKyIrMaE0/8CEAE="
|
|
},
|
|
"filetype": "text/plain",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Important points:",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "39a3ae572581d0f1fe7511fd7b3aa414",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-20T23:48:13.303000+00:00",
|
|
"date_modified": "2023-06-20T23:48:13.303000+00:00",
|
|
"record_locator": {
|
|
"protocol": "gs",
|
|
"remote_file_path": "utic-test-ingest-fixtures/nested-1/fake-text.txt"
|
|
},
|
|
"url": "gs://utic-test-ingest-fixtures/nested-1/fake-text.txt",
|
|
"version": "CKyIrMaE0/8CEAE="
|
|
},
|
|
"filetype": "text/plain",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Hamburgers are delicious",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "fc1adcb8eaceac694e500a103f9f698f",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-20T23:48:13.303000+00:00",
|
|
"date_modified": "2023-06-20T23:48:13.303000+00:00",
|
|
"record_locator": {
|
|
"protocol": "gs",
|
|
"remote_file_path": "utic-test-ingest-fixtures/nested-1/fake-text.txt"
|
|
},
|
|
"url": "gs://utic-test-ingest-fixtures/nested-1/fake-text.txt",
|
|
"version": "CKyIrMaE0/8CEAE="
|
|
},
|
|
"filetype": "text/plain",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "Dogs are the best",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "0b61e826b1c4ab05750184da72b89f83",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-06-20T23:48:13.303000+00:00",
|
|
"date_modified": "2023-06-20T23:48:13.303000+00:00",
|
|
"record_locator": {
|
|
"protocol": "gs",
|
|
"remote_file_path": "utic-test-ingest-fixtures/nested-1/fake-text.txt"
|
|
},
|
|
"url": "gs://utic-test-ingest-fixtures/nested-1/fake-text.txt",
|
|
"version": "CKyIrMaE0/8CEAE="
|
|
},
|
|
"filetype": "text/plain",
|
|
"languages": [
|
|
"eng"
|
|
]
|
|
},
|
|
"text": "I love fuzzy blankets",
|
|
"type": "ListItem"
|
|
}
|
|
] |