mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-08 20:58:11 +00:00
fix(html): slow table parsing (#2582)
* fix(html): simplify parsing of simple table cells Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * tests(html): add test for rich table cells Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * fix(html): ensure table cells with formatted text are parsed as RichTableCell Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * refactor(html): simplify process_rich_table_cells since only rich cells are processed Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * fix(html): formatted cell runs should be parsed as text items respecting the order Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * chore: pin latest docling-core and update uv.lock Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * chore: upgrade dependencies on uv.lock Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> --------- Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
This commit is contained in:
Cesar Berrospi Ramis
committed by
GitHub
GitHub
parent
8da3d287ed
commit
0ba8d5d9e3
167
tests/data/html/html_rich_table_cells.html
vendored
Normal file
167
tests/data/html/html_rich_table_cells.html
vendored
Normal file
@@ -0,0 +1,167 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<title>Rich Table Cells in HTML</title>
|
||||
<style>
|
||||
table { border-collapse: collapse; width: 90%; margin: 1em auto; }
|
||||
th, td { border: 1px solid #aaa; padding: 0.5rem; text-align: left; vertical-align: top; }
|
||||
th { background:#f2f2f2; }
|
||||
</style>
|
||||
</head>
|
||||
|
||||
<body>
|
||||
|
||||
<h1>Rich Table Cells in HTML</h1>
|
||||
|
||||
<!-- Simple data table -->
|
||||
<table>
|
||||
<caption>Basic duck facts</caption>
|
||||
<thead>
|
||||
<tr><th>Name</th><th>Habitat</th><th>Comment</th></tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<!-- empty cell -->
|
||||
<tr><td>Wood Duck</td><td> </td><td>Often seen near ponds.</td></tr>
|
||||
|
||||
<!-- plain text -->
|
||||
<tr><td>Mallard</td><td>Ponds, lakes, rivers</td><td>Quack</td></tr>
|
||||
|
||||
<!-- formatted text -->
|
||||
<tr>
|
||||
<td>Goose (not a duck!)</td>
|
||||
<td style="color:#777;">Water & wetlands</td>
|
||||
<td><strong>Large</strong>, <em>loud</em>, <u>noisy</u>, <s>small</s></td>
|
||||
</tr>
|
||||
|
||||
<!-- list -->
|
||||
<tr>
|
||||
<td>Teal</td>
|
||||
<td>
|
||||
<ul style="margin:0;padding-left:1.2rem;">
|
||||
<li>Pond</li>
|
||||
<li>Marsh</li>
|
||||
<li>Riverbank</li>
|
||||
</ul>
|
||||
</td>
|
||||
<td>
|
||||
<ol style="margin:0;padding-left:1.2rem;">
|
||||
<li>Fly south in winter</li>
|
||||
<li>Build nest on ground</li>
|
||||
</ol>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<!-- Table with mixed cell content -->
|
||||
<table>
|
||||
<caption>Duck family tree (simplified)</caption>
|
||||
<thead>
|
||||
<tr><th>Genus</th><th>Species</th></tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td>Aythya<br><small>(Diving ducks)</small></td>
|
||||
<td>Hawser, Common Pochard</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Lophonetta<br><small>(Pintail group)</small></td>
|
||||
<td>Fulvous Whistling Duck</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Oxyura<br><small>(Benthic ducks)</small></td>
|
||||
<td>Wigee, Banded Water‑screw</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<!-- Table with a mix of cell types and a nested table -->
|
||||
<table>
|
||||
<caption>Duck‑related actions</caption>
|
||||
<thead>
|
||||
<tr style="background:#cce5ff;">
|
||||
<th colspan="2">Action</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td><strong>Swim</strong></td>
|
||||
<td>Gracefully glide on H<sub>2</sub>O surfaces.</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><em>Fly</em></td>
|
||||
<td> </td> <!-- empty cell -->
|
||||
</tr>
|
||||
<tr>
|
||||
<td><u>Quack</u></td>
|
||||
<td>
|
||||
<table>
|
||||
<thead>
|
||||
<tr><th>Type</th><th>Sound</th></tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td>Short</td>
|
||||
<td>“quak”</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Long</td>
|
||||
<td>“quaaaaaack”</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<!-- Table with links -->
|
||||
<table>
|
||||
<caption>Famous Ducks with Images</caption>
|
||||
<thead>
|
||||
<tr><th>Name</th><th>Description</th><th>Image</th></tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<!-- Plain link to a PNG/JPG file -->
|
||||
<tr>
|
||||
<td>Donald Duck</td>
|
||||
<td>Cartoon character.</td>
|
||||
<td><a href="https://en.wikipedia.org/wiki/Donald_Duck#/media/File:Donald_Duck_angry_transparent_background.png" target="_blank">View PNG</a></td>
|
||||
</tr>
|
||||
|
||||
<!-- Thumbnail image that opens in a new tab -->
|
||||
<tr>
|
||||
<td>White-headed duck</td>
|
||||
<td>A small diving duck some 45 cm (18 in) long.</td>
|
||||
<td>
|
||||
<a href="https://upload.wikimedia.org/wikipedia/commons/thumb/a/ab/Witkopeend_-_white-headed_duck_-_Oxyura_leucocephala_3.tif/lossy-page1-1920px-Witkopeend_-_white-headed_duck_-_Oxyura_leucocephala_3.tif.jpg" target="_blank">
|
||||
<img class="thumb"
|
||||
src="https://upload.wikimedia.org/wikipedia/commons/thumb/a/ab/Witkopeend_-_white-headed_duck_-_Oxyura_leucocephala_3.tif/lossy-page1-250px-Witkopeend_-_white-headed_duck_-_Oxyura_leucocephala_3.tif.jpg"
|
||||
alt="White-headed duck thumbnail">
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
|
||||
<!-- Link to a larger image with a caption -->
|
||||
<tr>
|
||||
<td>Mandarin Duck</td>
|
||||
<td>Known for its striking plumage.</td>
|
||||
<td>
|
||||
<a href="https://upload.wikimedia.org/wikipedia/commons/thumb/7/75/Mandarin_duck_%28Aix_galericulata%29.jpg/250px-Mandarin_duck_%28Aix_galericulata%29.jpg" target="_blank">
|
||||
View Full‑Size Image
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
|
||||
<!-- Empty image cell (to illustrate the empty case) -->
|
||||
<tr>
|
||||
<td>Unknown Duck</td>
|
||||
<td>No photo available.</td>
|
||||
<td> </td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user