mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-23 09:00:40 +00:00
f4ddf53590
* Feat/965 track emphasized text html (#1021) * feat: add functionality to track emphasized text (<strong>, <em>, <span>, <b>, <i> tags) in HTML * feat: add `include_tail_text` parameter to `_construct_text` * test: add test case for `_get_emphasized_texts_from_tag` * test: add `emphasized_texts` to metadata * chore: update changelog & version * fix tests * fix lint errors * chore: update changelog * chore: small comment updates * feat: update `XMLDocument._read_xml` to create `<p>` tag element for the text enclosed in the `<pre>` tag * chore: update changelog * Update ingest test fixtures (#1026) Co-authored-by: christinestraub <christinestraub@users.noreply.github.com> --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com> Co-authored-by: Matt Robinson <mrobinson@unstructured.io> * ingest-test-fixtures-update * Update ingest test fixtures (#1035) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> --------- Co-authored-by: Christine Straub <christinemstraub@gmail.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
172 lines
3.4 KiB
JSON
172 lines
3.4 KiB
JSON
[
|
|
{
|
|
"type": "Title",
|
|
"element_id": "307afee17dac4c598e361c095338decd",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1
|
|
},
|
|
"text": "Copy and paste this section for each week."
|
|
},
|
|
{
|
|
"type": "Title",
|
|
"element_id": "b980a145c5e8c9e233a0643366ba520a",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1,
|
|
"emphasized_texts": [
|
|
{
|
|
"text": "Win",
|
|
"tag": "strong"
|
|
}
|
|
]
|
|
},
|
|
"text": "Win"
|
|
},
|
|
{
|
|
"type": "ListItem",
|
|
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1
|
|
},
|
|
"text": ""
|
|
},
|
|
{
|
|
"type": "ListItem",
|
|
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1
|
|
},
|
|
"text": ""
|
|
},
|
|
{
|
|
"type": "ListItem",
|
|
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1
|
|
},
|
|
"text": ""
|
|
},
|
|
{
|
|
"type": "Title",
|
|
"element_id": "aecc044c7725a6555114285dc28fe2d1",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1,
|
|
"emphasized_texts": [
|
|
{
|
|
"text": "Needs input",
|
|
"tag": "strong"
|
|
}
|
|
]
|
|
},
|
|
"text": "Needs input"
|
|
},
|
|
{
|
|
"type": "ListItem",
|
|
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1
|
|
},
|
|
"text": ""
|
|
},
|
|
{
|
|
"type": "ListItem",
|
|
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1
|
|
},
|
|
"text": ""
|
|
},
|
|
{
|
|
"type": "ListItem",
|
|
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1
|
|
},
|
|
"text": ""
|
|
},
|
|
{
|
|
"type": "Title",
|
|
"element_id": "9d3cab2b5efed4eaef42a707dbc813da",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1,
|
|
"emphasized_texts": [
|
|
{
|
|
"text": "Focus",
|
|
"tag": "strong"
|
|
}
|
|
]
|
|
},
|
|
"text": "Focus"
|
|
},
|
|
{
|
|
"type": "ListItem",
|
|
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1
|
|
},
|
|
"text": ""
|
|
},
|
|
{
|
|
"type": "ListItem",
|
|
"element_id": "e3b0c44298fc1c149afbf4c8996fb924",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1
|
|
},
|
|
"text": ""
|
|
},
|
|
{
|
|
"type": "Title",
|
|
"element_id": "8a7525b1492fb84833f5c4a69b30f4bf",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1,
|
|
"emphasized_texts": [
|
|
{
|
|
"text": "Notes",
|
|
"tag": "strong"
|
|
}
|
|
]
|
|
},
|
|
"text": "Notes"
|
|
},
|
|
{
|
|
"type": "Title",
|
|
"element_id": "98e38cd6c5f88330322de759657563f9",
|
|
"metadata": {
|
|
"data_source": {},
|
|
"filetype": "text/html",
|
|
"page_number": 1,
|
|
"emphasized_texts": [
|
|
{
|
|
"text": "Important Links",
|
|
"tag": "strong"
|
|
}
|
|
]
|
|
},
|
|
"text": "Important Links"
|
|
}
|
|
] |