mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2026-01-03 18:54:01 +00:00
b8a8de33f4
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.
262 lines
8.2 KiB
JSON
262 lines
8.2 KiB
JSON
[
|
|
{
|
|
"element_id": "1f2a5d80586cf70bc264150f6d3f4c7c",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "GSFC: Sciences and Exploration Directorate",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "7cf7093dc3fec7fa3f7045666578e75a",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "Virtual Machine Environment Scorecard",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "b4dac8600214b4829bac302326593c47",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "Code 600: Sciences and Exploration Directorate (SED)",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "de72c858257919ced58456afa3d4412e",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "Code 610: Earth Sciences Division",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "7de2e4c70a5120577d71e2eabeac36ad",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "Code 660: Astrophysics Science Division",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "8a5c7edcf0545e74e86e9f33bbc254fd",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "Code 670: Heliophysics Science Division",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "5eb8e42b719e3e8ade72dc706bed5b9f",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "Code 690: Solar System Exploration Division",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "4875cf409fe04ada73cef724f8ed3840",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "Support offices",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "046e9117c748370b9b920c893fa52ecc",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "Code 603: Administration and Resources Management Office",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "bd3a820c31b89c5d4e1cc60c1ada41bc",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "Code 605: Science Proposal Support Office",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "e01f8f787617a1ab334f52a0bc5b4a9c",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "Code 606: Computational and Information Sciences and Technology Office ( The SEDVME project is managed out of 606).",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "3dbd91c87d3e2850a7cb31251c4a1b21",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "Code 700: Information Technology and Communication Directorate",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "36cd7086df7ce77d623ffdc1ba6a8513",
|
|
"metadata": {
|
|
"data_source": {
|
|
"record_locator": {
|
|
"protocol": "dropbox",
|
|
"remote_file_path": "/test-input/science-exploration-1p.pptx"
|
|
},
|
|
"url": "dropbox:///test-input/science-exploration-1p.pptx",
|
|
"version": "23819616053480539262630762470581852076"
|
|
},
|
|
"filetype": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1
|
|
},
|
|
"text": "Project management help, CNE, Zoned Architecture, IT Security, Production SEDVME Service Manager",
|
|
"type": "ListItem"
|
|
}
|
|
] |