mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-09-29 02:12:18 +00:00
5bb95b5841
This PR:
- Fixes removing HTML tags that exist in <td> cells
- stripping function was in general problematic to implement in easy and
straightforward way (you can't modify `descendants` in-place). So I
decided instead of patching something in table cell I added stripping
everywhere in the same consistent way. This is why some tests needed
small edits with removing one white-space in each tag. I believe this
won't cause any problems for downstream tasks.
Tested HTML:
```html
<table class="Table">
<tbody>
<tr>
<td colspan="2">
Some text
</td>
<td>
<input checked="" class="Checkbox" type="checkbox"/>
</td>
</tr>
</tbody>
</table>
```
Before & After
```html
'<table class="Table" id="..."> <tbody> <tr> <td colspan="2">Some text</td><td></td></tr></tbody></table>'
'<table class="Table" id="..."><tbody><tr><td colspan="2">Some text</td><td><input checked="" type="checkbox"/></td></tr></tbody></table>''
```
162 lines
5.6 KiB
JSON
162 lines
5.6 KiB
JSON
[
|
|
{
|
|
"element_id": "3a6b156a81764e17be128264241f8136",
|
|
"metadata": {
|
|
"category_depth": 0,
|
|
"filename": "example.pdf",
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1,
|
|
"parent_id": "897a8a47377c4ad6aab839a929879537",
|
|
"text_as_html": "<div class=\"Page\" data-page-number=\"1\" id=\"3a6b156a81764e17be128264241f8136\" />"
|
|
},
|
|
"text": "",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "45b3d0053468484ba1c7b53998115412",
|
|
"metadata": {
|
|
"category_depth": 1,
|
|
"filename": "example.pdf",
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1,
|
|
"parent_id": "3a6b156a81764e17be128264241f8136",
|
|
"text_as_html": "<header class=\"Header\" id=\"45b3d0053468484ba1c7b53998115412\" />"
|
|
},
|
|
"text": "",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "c95473e8a3704fc2b418697f9fddb27b",
|
|
"metadata": {
|
|
"category_depth": 2,
|
|
"filename": "example.pdf",
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1,
|
|
"parent_id": "45b3d0053468484ba1c7b53998115412",
|
|
"text_as_html": "<h1 class=\"Title\" id=\"c95473e8a3704fc2b418697f9fddb27b\">Header</h1>"
|
|
},
|
|
"text": "Header",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "379cbfdc16d44bd6a59e6cfabe6438d5",
|
|
"metadata": {
|
|
"category_depth": 2,
|
|
"filename": "example.pdf",
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1,
|
|
"parent_id": "45b3d0053468484ba1c7b53998115412",
|
|
"text_as_html": "<time class=\"CalendarDate\" id=\"379cbfdc16d44bd6a59e6cfabe6438d5\">Date: October 30, 2023</time>"
|
|
},
|
|
"text": "Date: October 30, 2023",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "637c2f6935fb4353a5f73025ce04619d",
|
|
"metadata": {
|
|
"category_depth": 1,
|
|
"filename": "example.pdf",
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1,
|
|
"parent_id": "3a6b156a81764e17be128264241f8136",
|
|
"text_as_html": "<form class=\"Form\" id=\"637c2f6935fb4353a5f73025ce04619d\"><label class=\"FormField\" for=\"company-name\" id=\"50027cccbe1948c9853ce0de37b635c2\">From field name</label><input class=\"FormFieldValue\" id=\"0032242af75c4b37984ea7fea9aac74c\" value=\"Example value\" /></form>"
|
|
},
|
|
"text": "From field name Example value",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "592422373ed741b68a077e2003f8ed81",
|
|
"metadata": {
|
|
"category_depth": 1,
|
|
"filename": "example.pdf",
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1,
|
|
"parent_id": "3a6b156a81764e17be128264241f8136",
|
|
"text_as_html": "<section class=\"Section\" id=\"592422373ed741b68a077e2003f8ed81\" />"
|
|
},
|
|
"text": "",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "dc3792d4422e444f90876b56d0cfb20d",
|
|
"metadata": {
|
|
"category_depth": 2,
|
|
"filename": "example.pdf",
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1,
|
|
"parent_id": "592422373ed741b68a077e2003f8ed81",
|
|
"text_as_html": "<table class=\"Table\" id=\"dc3792d4422e444f90876b56d0cfb20d\"><thead><tr><th>Description</th><th>Row header</th></tr></thead><tbody><tr><td>Value description</td><td><span>50 $</span><span>(1.32 %)</span></td></tr></tbody></table>"
|
|
},
|
|
"text": "Description Row header Value description 50 $ (1.32 %)",
|
|
"type": "Table"
|
|
},
|
|
{
|
|
"element_id": "1032242af75c4b37984ea7fea9aac74c",
|
|
"metadata": {
|
|
"category_depth": 1,
|
|
"filename": "example.pdf",
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1,
|
|
"parent_id": "3a6b156a81764e17be128264241f8136",
|
|
"text_as_html": "<section class=\"Section\" id=\"1032242af75c4b37984ea7fea9aac74c\" />"
|
|
},
|
|
"text": "",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "2a4e2c4a689f4f9a8c180b6b521e45c3",
|
|
"metadata": {
|
|
"category_depth": 2,
|
|
"filename": "example.pdf",
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1,
|
|
"parent_id": "1032242af75c4b37984ea7fea9aac74c",
|
|
"text_as_html": "<h2 class=\"Subtitle\" id=\"2a4e2c4a689f4f9a8c180b6b521e45c3\">2. Subtitle</h2>"
|
|
},
|
|
"text": "2. Subtitle",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "5591f7a4df01447e82515ce45f686fbe",
|
|
"metadata": {
|
|
"category_depth": 2,
|
|
"filename": "example.pdf",
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"page_number": 1,
|
|
"parent_id": "1032242af75c4b37984ea7fea9aac74c",
|
|
"text_as_html": "<p class=\"NarrativeText\" id=\"5591f7a4df01447e82515ce45f686fbe\">Paragraph text</p>"
|
|
},
|
|
"text": "Paragraph text",
|
|
"type": "NarrativeText"
|
|
}
|
|
] |