mirror of
https://github.com/docling-project/docling-core.git
synced 2026-05-17 13:10:44 +00:00
23badf2a1d
* Add forward slash to singleton tags See issue #354 on docling-project/docling-core Signed-off-by: 15mbp <100952997+15mbp@users.noreply.github.com> * test(HTML): fix ground truth data files Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> --------- Signed-off-by: 15mbp <100952997+15mbp@users.noreply.github.com> Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Co-authored-by: 15mbp <100952997+15mbp@users.noreply.github.com>
133 lines
3.2 KiB
HTML
Vendored
133 lines
3.2 KiB
HTML
Vendored
<!DOCTYPE html>
|
|
<html>
|
|
<head>
|
|
<meta charset="UTF-8"/>
|
|
<title>dummy_doc</title>
|
|
<meta name="generator" content="Docling HTML Serializer"/>
|
|
<style>
|
|
html {
|
|
background-color: #f5f5f5;
|
|
font-family: Arial, sans-serif;
|
|
line-height: 1.6;
|
|
}
|
|
body {
|
|
max-width: 800px;
|
|
margin: 0 auto;
|
|
padding: 2rem;
|
|
background-color: white;
|
|
box-shadow: 0 0 10px rgba(0,0,0,0.1);
|
|
}
|
|
h1, h2, h3, h4, h5, h6 {
|
|
color: #333;
|
|
margin-top: 1.5em;
|
|
margin-bottom: 0.5em;
|
|
}
|
|
h1 {
|
|
font-size: 2em;
|
|
border-bottom: 1px solid #eee;
|
|
padding-bottom: 0.3em;
|
|
}
|
|
table {
|
|
border-collapse: collapse;
|
|
margin: 1em 0;
|
|
width: 100%;
|
|
}
|
|
th, td {
|
|
border: 1px solid #ddd;
|
|
padding: 8px;
|
|
text-align: left;
|
|
}
|
|
th {
|
|
background-color: #f2f2f2;
|
|
font-weight: bold;
|
|
}
|
|
figure {
|
|
margin: 1.5em 0;
|
|
text-align: center;
|
|
}
|
|
figcaption {
|
|
color: #666;
|
|
font-style: italic;
|
|
margin-top: 0.5em;
|
|
}
|
|
img {
|
|
max-width: 100%;
|
|
height: auto;
|
|
}
|
|
pre {
|
|
background-color: #f6f8fa;
|
|
border-radius: 3px;
|
|
padding: 1em;
|
|
overflow: auto;
|
|
}
|
|
code {
|
|
font-family: monospace;
|
|
background-color: #f6f8fa;
|
|
padding: 0.2em 0.4em;
|
|
border-radius: 3px;
|
|
}
|
|
pre code {
|
|
background-color: transparent;
|
|
padding: 0;
|
|
}
|
|
.formula {
|
|
text-align: center;
|
|
padding: 0.5em;
|
|
margin: 1em 0;
|
|
background-color: #f9f9f9;
|
|
}
|
|
.formula-not-decoded {
|
|
text-align: center;
|
|
padding: 0.5em;
|
|
margin: 1em 0;
|
|
background: repeating-linear-gradient(
|
|
45deg,
|
|
#f0f0f0,
|
|
#f0f0f0 10px,
|
|
#f9f9f9 10px,
|
|
#f9f9f9 20px
|
|
);
|
|
}
|
|
.page-break {
|
|
page-break-after: always;
|
|
border-top: 1px dashed #ccc;
|
|
margin: 2em 0;
|
|
}
|
|
.key-value-region {
|
|
background-color: #f9f9f9;
|
|
padding: 1em;
|
|
border-radius: 4px;
|
|
margin: 1em 0;
|
|
}
|
|
.key-value-region dt {
|
|
font-weight: bold;
|
|
}
|
|
.key-value-region dd {
|
|
margin-left: 1em;
|
|
margin-bottom: 0.5em;
|
|
}
|
|
.form-container {
|
|
border: 1px solid #ddd;
|
|
padding: 1em;
|
|
border-radius: 4px;
|
|
margin: 1em 0;
|
|
}
|
|
.form-item {
|
|
margin-bottom: 0.5em;
|
|
}
|
|
.image-classification {
|
|
font-size: 0.9em;
|
|
color: #666;
|
|
margin-top: 0.5em;
|
|
}
|
|
</style>
|
|
</head>
|
|
<body>
|
|
<div class='page'>
|
|
<h1>DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis</h1>
|
|
<figure><figcaption><div class="caption">Figure 1: Four examples of complex page layouts across different document categories</div> <div data-annotation-kind="classification">bar chart</div> <div data-annotation-kind="description">...</div> <div data-annotation-kind="molecule_data">CC1=NNC(C2=CN3C=CN=C3C(CC3=CC(F)=CC(F)=C3)=N2)=N1</div></figcaption></figure>
|
|
<table><caption><div data-annotation-kind="description">A description annotation for this table.</div></caption></table>
|
|
</div>
|
|
</body>
|
|
</html>
|