mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-12-31 09:17:17 +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>''
```
44 lines
2.7 KiB
JSON
44 lines
2.7 KiB
JSON
[
|
|
{
|
|
"element_id": "2428404551304d4db5925f6afee11ed5",
|
|
"metadata": {
|
|
"category_depth": 0,
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"parent_id": "517f8559ba594270bdd67e1b02bf19a2",
|
|
"text_as_html": "<table class=\"Table\" id=\"2428404551304d4db5925f6afee11ed5\"><tr><th>Header 1</th><th>Header 2</th></tr><tr><td>Row 1, Cell 1</td><td>Row 1, Cell 2</td></tr><tr><td>Row 2, Cell 1</td><td>Row 2, Cell 2</td></tr></table>"
|
|
},
|
|
"text": "Header 1 Header 2 Row 1, Cell 1 Row 1, Cell 2 Row 2, Cell 1 Row 2, Cell 2",
|
|
"type": "Table"
|
|
},
|
|
{
|
|
"element_id": "9f91cae321c74b31bb1c83ac86cd7afb",
|
|
"metadata": {
|
|
"category_depth": 0,
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"parent_id": "517f8559ba594270bdd67e1b02bf19a2",
|
|
"text_as_html": "<table class=\"Table\" id=\"9f91cae321c74b31bb1c83ac86cd7afb\"><tr><th colspan=\"3\">Big Table Header</th></tr><tr><td rowspan=\"2\">Merged Cell 1</td><td>Cell 2</td><td>Cell 3</td></tr><tr><td colspan=\"2\">Merged Cell 4 and 5</td></tr><tr><td>Cell 6</td><td>Cell 7</td><td>Cell 8</td></tr><tr><td>Cell 9</td><td colspan=\"2\">A cell with a lot of text. Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.</td></tr><tr><td>Cell 10</td><td>Cell 11</td><td>Cell 12</td></tr></table>"
|
|
},
|
|
"text": "Big Table Header Merged Cell 1 Cell 2 Cell 3 Merged Cell 4 and 5 Cell 6 Cell 7 Cell 8 Cell 9 A cell with a lot of text. Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Cell 10 Cell 11 Cell 12",
|
|
"type": "Table"
|
|
},
|
|
{
|
|
"element_id": "da6c34391e544b3480e45d68f40870fa",
|
|
"metadata": {
|
|
"category_depth": 0,
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng"
|
|
],
|
|
"parent_id": "517f8559ba594270bdd67e1b02bf19a2",
|
|
"text_as_html": "<table class=\"TableOfContents\" id=\"da6c34391e544b3480e45d68f40870fa\"><tr><th>Chapter</th><th>Title</th><th>Page</th></tr><tr><td>1</td><td>Introduction</td><td>1</td></tr><tr><td>2</td><td>Getting Started</td><td>5</td></tr><tr><td>3</td><td>Basic Concepts</td><td>12</td></tr><tr><td>4</td><td>Advanced Topics</td><td>25</td></tr><tr><td>5</td><td>Conclusion</td><td>40</td></tr></table>"
|
|
},
|
|
"text": "Chapter Title Page 1 Introduction 1 2 Getting Started 5 3 Basic Concepts 12 4 Advanced Topics 25 5 Conclusion 40",
|
|
"type": "Table"
|
|
}
|
|
] |