Michał Martyniak 2d1923ac7e
Better element IDs - deterministic and document-unique hashes (#2673)
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
2024-04-24 00:05:20 -07:00

1065 lines
29 KiB
JSON

[
{
"element_id": "d9e500a6e802884f5b83fba8dcecc49e",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Welcome to your team space!",
"type": "Title"
},
{
"element_id": "25a59cf1d4c40c6cd02236d933666c2c",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "We've added some suggestions and placeholders. Everything is customizable.",
"type": "ListItem"
},
{
"element_id": "23bacd7f54743e32a6dcafc05a716f24",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"link_start_indexes": [
32,
55,
79
],
"link_texts": [
"Template - Project plan",
"Template - Meeting notes",
"Template - Weekly status report"
],
"link_urls": [
"/wiki/spaces/MFS/pages/1540126/Template+-+Project+plan",
"/wiki/spaces/MFS/pages/1605928/Template+-+Meeting+notes",
"/wiki/spaces/MFS/pages/1605942/Template+-+Weekly+status+report"
],
"page_number": 1
},
"text": "Get started with page templates:Template - Project planTemplate - Meeting notesTemplate - Weekly status report",
"type": "ListItem"
},
{
"element_id": "5ce7656ba0ef50009f78e0317954be09",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"link_start_indexes": [
10
],
"link_texts": [
"Get the most out of your team space"
],
"link_urls": [
"/wiki/spaces/MFS/pages/1605956/Get+the+most+out+of+your+team+space"
],
"page_number": 1
},
"text": "Check out Get the most out of your team space for more tips.",
"type": "ListItem"
},
{
"element_id": "cda80414ca0f2e335c3c72ec111e9a91",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "About",
"type": "Title"
},
{
"element_id": "24013ff70e4940c9f0b77dd3d8b8ec9e",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"What is your team all about?",
"What is your team all about?"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "What is your team all about?",
"type": "NarrativeText"
},
{
"element_id": "c8e6c8cc992272412585608ef094dd91",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Mission and vision",
"type": "Title"
},
{
"element_id": "a8e3e30f65b9ad23b60ef3ebc2202537",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"What is your team's mission? What is your vision?",
"What is your team's mission? What is your vision?"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "What is your team's mission? What is your vision?",
"type": "NarrativeText"
},
{
"element_id": "a57d67ba594f3d4f8a9c1ffd6ab3ed3d",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Meet the team",
"type": "Title"
},
{
"element_id": "40fe67ee68eb99624930de7af54a8477",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Add team members to your space.",
"Add team members to your space."
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Add team members to your space.",
"type": "Title"
},
{
"element_id": "00c6d24871bc0d328014fe5676fc5a9a",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Team member"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Team member",
"type": "Title"
},
{
"element_id": "b8e1449ef65afb6a5128d70cbdae8f87",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Role"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Role",
"type": "Title"
},
{
"element_id": "95d5088f0cc25f22178331dab1e595b7",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Responsibility"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Responsibility",
"type": "Title"
},
{
"element_id": "75808150fdb4d8f3b3e244537e92f6a1",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Team member"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Team member",
"type": "Title"
},
{
"element_id": "a67c2f1a5b201e9dfbe01e1e21b200e3",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Role"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Role",
"type": "Title"
},
{
"element_id": "8451c40b12ec20c35b10398a0b265b60",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Responsibility"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Responsibility",
"type": "Title"
},
{
"element_id": "c5ff2a7f278dd30eacc616697e0fd3f7",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Team member"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Team member",
"type": "Title"
},
{
"element_id": "464a4ee936def1c064e15594b4389625",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Role"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Role",
"type": "Title"
},
{
"element_id": "6ea6880df9c934cb0a1ab91a07b7616b",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Responsibility"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Responsibility",
"type": "Title"
},
{
"element_id": "52cd76a2d925992aac18b9e36906441a",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Contact us",
"type": "Title"
},
{
"element_id": "7e95e28526cea2ef1b963e0651ab8cbd",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"How can someone reach out to your team?",
"How can someone reach out to your team?"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "How can someone reach out to your team?",
"type": "NarrativeText"
},
{
"element_id": "25eac0501321e5b995c14824c90095d5",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"team@email.com"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"link_start_indexes": [
0
],
"link_texts": [
null
],
"link_urls": [
"mailto:team@email.com"
],
"page_number": 1
},
"text": "team@email.com",
"type": "ListItem"
},
{
"element_id": "6544e3a323486295c7507d1ed9233573",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Tickets"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Tickets",
"type": "ListItem"
},
{
"element_id": "77013ea2d88478c056bc21321ba02275",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Jira board"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Jira board",
"type": "ListItem"
},
{
"element_id": "5a07d153a4c65b036a6204210b8b14c2",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"#channel"
],
"emphasized_text_tags": [
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "#channel",
"type": "ListItem"
},
{
"element_id": "1f4fc38715cf9ca3c3149c2ec1192a9e",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Important Pages",
"type": "Title"
},
{
"element_id": "f8255069bc6370911a26b98ce3a1381f",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"List them here",
"List them here"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "List them here",
"type": "NarrativeText"
},
{
"element_id": "33ceff50e6f6ef818d66a8f8639cbbbb",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "",
"type": "ListItem"
},
{
"element_id": "8ae7dbeadd16a7528b2c6a81a4b96cd0",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "",
"type": "ListItem"
},
{
"element_id": "c9fafc9bdf9cfbc66991059da1e6e455",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "",
"type": "ListItem"
},
{
"element_id": "a22fc48a85b11e636b2e26fecff3f1ba",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Onboarding FAQs",
"type": "Title"
},
{
"element_id": "4ae5bf04328dd69fbacdf02ba5d4df0e",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Add resources for new hires",
"Add resources for new hires"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Add resources for new hires",
"type": "Title"
},
{
"element_id": "1917058bf8ff843a3782195b4c4a9a11",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Meeting notes",
"type": "Title"
},
{
"element_id": "01b55b27ca4f59d385dc8c777c65e551",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Add links to meeting notes",
"Add links to meeting notes"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Add links to meeting notes",
"type": "NarrativeText"
},
{
"element_id": "a932690e5e7d16afcf18cd955693fd64",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Team goals",
"type": "Title"
},
{
"element_id": "d82d6fa569c160b1731ba1ceb5430f5a",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"List them here",
"List them here"
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "List them here",
"type": "NarrativeText"
},
{
"element_id": "a3ec6f91fa124b63f4d4a3711335db9c",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Team news",
"type": "Title"
},
{
"element_id": "62996282b16b1ba3ecb5c4c9431eb94f",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"emphasized_text_contents": [
"Create a blog post to share team news. It will automatically appear here once it's published.",
"Create a blog post to share team news. It will automatically appear here once it's published."
],
"emphasized_text_tags": [
"em",
"span"
],
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Create a blog post to share team news. It will automatically appear here once it's published.",
"type": "NarrativeText"
},
{
"element_id": "96a019409dbabbd15d1468d620ec8498",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Blog stream",
"type": "Title"
},
{
"element_id": "9d29edca8d3fe280aa77a46c9e593156",
"metadata": {
"data_source": {
"date_created": "2023-06-30T17:25:25.504000",
"date_modified": "2023-06-30T17:25:30.898000",
"record_locator": {
"page_id": "229477",
"url": "https://unstructured-ingest-test.atlassian.net"
},
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/229477",
"version": "1"
},
"filetype": "text/html",
"languages": [
"eng"
],
"page_number": 1
},
"text": "Create a blog post to share news and announcements with your team and company.",
"type": "NarrativeText"
}
]