mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-09 13:18:24 +00:00
feat(cli): add option for html with split-page mode (#1355)
* updated the cli to output html in split-page mode Signed-off-by: Peter Staar <taa@zurich.ibm.com> * add pin for new docling-core with html split argument Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * relock with fixed html export in docling-core Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update test results Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update more tests Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update example Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update lock with docling-core fixes Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update test results Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add again chunking extras Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
committed by
GitHub
parent
0de70e7991
commit
c0ba88edf1
@@ -1,74 +1,129 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<html>
|
||||
<head>
|
||||
<link rel="icon" type="image/png"
|
||||
href="https://raw.githubusercontent.com/docling-project/docling/refs/heads/main/docs/assets/logo.svg"/>
|
||||
<meta charset="UTF-8">
|
||||
<title>
|
||||
Powered by Docling
|
||||
</title>
|
||||
<style>
|
||||
<meta charset="UTF-8">
|
||||
<title>word_tables</title>
|
||||
<meta name="generator" content="Docling HTML Serializer">
|
||||
<style>
|
||||
html {
|
||||
background-color: LightGray;
|
||||
background-color: #f5f5f5;
|
||||
font-family: Arial, sans-serif;
|
||||
line-height: 1.6;
|
||||
}
|
||||
body {
|
||||
margin: 0 auto;
|
||||
width:800px;
|
||||
padding: 30px;
|
||||
background-color: White;
|
||||
font-family: Arial, sans-serif;
|
||||
box-shadow: 10px 10px 10px grey;
|
||||
max-width: 800px;
|
||||
margin: 0 auto;
|
||||
padding: 2rem;
|
||||
background-color: white;
|
||||
box-shadow: 0 0 10px rgba(0,0,0,0.1);
|
||||
}
|
||||
figure{
|
||||
display: block;
|
||||
width: 100%;
|
||||
margin: 0px;
|
||||
margin-top: 10px;
|
||||
margin-bottom: 10px;
|
||||
h1, h2, h3, h4, h5, h6 {
|
||||
color: #333;
|
||||
margin-top: 1.5em;
|
||||
margin-bottom: 0.5em;
|
||||
}
|
||||
img {
|
||||
display: block;
|
||||
margin: auto;
|
||||
margin-top: 10px;
|
||||
margin-bottom: 10px;
|
||||
max-width: 640px;
|
||||
max-height: 640px;
|
||||
h1 {
|
||||
font-size: 2em;
|
||||
border-bottom: 1px solid #eee;
|
||||
padding-bottom: 0.3em;
|
||||
}
|
||||
table {
|
||||
min-width:500px;
|
||||
background-color: White;
|
||||
border-collapse: collapse;
|
||||
cell-padding: 5px;
|
||||
margin: auto;
|
||||
margin-top: 10px;
|
||||
margin-bottom: 10px;
|
||||
border-collapse: collapse;
|
||||
margin: 1em 0;
|
||||
width: 100%;
|
||||
}
|
||||
th, td {
|
||||
border: 1px solid black;
|
||||
padding: 8px;
|
||||
border: 1px solid #ddd;
|
||||
padding: 8px;
|
||||
text-align: left;
|
||||
}
|
||||
th {
|
||||
font-weight: bold;
|
||||
background-color: #f2f2f2;
|
||||
font-weight: bold;
|
||||
}
|
||||
table tr:nth-child(even) td{
|
||||
background-color: LightGray;
|
||||
figure {
|
||||
margin: 1.5em 0;
|
||||
text-align: center;
|
||||
}
|
||||
math annotation {
|
||||
display: none;
|
||||
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 {
|
||||
background: repeating-linear-gradient(
|
||||
45deg, /* Angle of the stripes */
|
||||
LightGray, /* First color */
|
||||
LightGray 10px, /* Length of the first color */
|
||||
White 10px, /* Second color */
|
||||
White 20px /* Length of the second color */
|
||||
);
|
||||
margin: 0;
|
||||
text-align: center;
|
||||
text-align: center;
|
||||
padding: 0.5em;
|
||||
margin: 1em 0;
|
||||
background: repeating-linear-gradient(
|
||||
45deg,
|
||||
#f0f0f0,
|
||||
#f0f0f0 10px,
|
||||
#f9f9f9 10px,
|
||||
#f9f9f9 20px
|
||||
);
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
.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'>
|
||||
<h2>Test with tables</h2>
|
||||
<p>A uniform table</p>
|
||||
<table><tbody><tr><th>Header 0.0</th><th>Header 0.1</th><th>Header 0.2</th></tr><tr><td>Cell 1.0</td><td>Cell 1.1</td><td>Cell 1.2</td></tr><tr><td>Cell 2.0</td><td>Cell 2.1</td><td>Cell 2.2</td></tr></tbody></table>
|
||||
@@ -86,4 +141,6 @@
|
||||
<table><tbody><tr><th>Header 0.0</th><th>Header 0.1</th><th>Header 0.2</th><th></th><th></th></tr><tr><td>Cell 1.0</td><td rowspan="2">Merged Cell 1.1 2.1</td><td>Cell 1.2</td><td></td><td></td></tr><tr><td>Cell 2.0</td><td>Cell 2.2</td><td></td><td></td></tr><tr><td>Cell 3.0</td><td rowspan="2">Merged Cell 3.1 4.1</td><td>Cell 3.2</td><td rowspan="3"></td><td></td></tr><tr><td>Cell 4.0</td><td>Cell 4.2</td><td rowspan="2">Merged Cell 4.4 5.4</td></tr><tr><td></td><td></td><td></td></tr><tr><td></td><td></td><td></td><td></td><td></td></tr><tr><td colspan="5"></td></tr><tr><td></td><td></td><td></td><td></td><td>Cell 8.4</td></tr></tbody></table>
|
||||
<p></p>
|
||||
<p></p>
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user