Files
allenai--olmocr/olmocr/viewer/dolmaviewer_template.html
T
wehub-resource-sync 917eedffcf
Main / Python 3.11 - Docs (push) Has been cancelled
Main / Python 3.11 - Build (push) Has been cancelled
Main / Python 3.11 - Lint (push) Has been cancelled
Main / Python 3.11 - Style (push) Has been cancelled
Main / Python 3.11 - Test (push) Has been cancelled
Main / GPU CI (push) Has been cancelled
Main / Release (push) Has been cancelled
Main / Build and Push Docker Images (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:27:09 +08:00

416 lines
13 KiB
HTML

<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<title>{{ id }}</title>
<!-- KaTeX CSS -->
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.16.9/dist/katex.min.css" integrity="sha384-n8MVd4RsNIU0tAv4ct0nTaAbDJwPJzDEaqSD1odI+WdtXRGWt2kTvGFasHpSy3SV" crossorigin="anonymous">
<style>
/* CSS styles */
body {
font-family: Arial, sans-serif;
background-color: #f0f0f0;
margin: 0;
padding: 0;
display: flex;
justify-content: center;
}
.document {
background-color: #fff;
padding: 40px;
margin: 20px;
width: 60%;
box-shadow: 0px 0px 10px rgba(0, 0, 0, 0.1);
line-height: 1.8;
position: relative;
}
/* Toggle button styles */
.toggle-container {
position: sticky;
top: 20px;
float: right;
z-index: 1000;
background: white;
padding: 10px;
border-radius: 5px;
box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1);
}
.toggle-button {
display: inline-flex;
align-items: center;
gap: 10px;
padding: 8px 16px;
background: #4CAF50;
color: white;
border: none;
border-radius: 4px;
cursor: pointer;
font-size: 14px;
transition: background 0.3s;
}
.toggle-button:hover {
background: #45a049;
}
.toggle-button.raw-mode {
background: #2196F3;
}
.toggle-button.raw-mode:hover {
background: #0b7dda;
}
.page-section {
display: flex;
flex-direction: row;
margin-bottom: 20px;
transition: background-color 0.3s ease;
clear: both;
}
.page-section:hover {
background-color: #f5f5f5;
}
.page-section .text {
flex: 2;
padding: 10px;
text-align: justify;
}
.page-section .image {
flex: 1;
padding: 10px;
}
.page-section img {
max-width: 100%;
height: auto;
border: 1px solid #ccc;
}
/* Raw text display */
.text-content.raw pre {
white-space: pre-wrap;
word-wrap: break-word;
font-family: 'Courier New', monospace;
font-size: 14px;
line-height: 1.5;
background: #f5f5f5;
padding: 10px;
border-radius: 4px;
margin: 0;
}
/* Markdown rendered content */
.text-content.markdown {
font-family: Arial, sans-serif;
}
.text-content.markdown h1 { margin-top: 24px; margin-bottom: 16px; }
.text-content.markdown h2 { margin-top: 20px; margin-bottom: 14px; }
.text-content.markdown h3 { margin-top: 18px; margin-bottom: 12px; }
.text-content.markdown h4 { margin-top: 16px; margin-bottom: 10px; }
.text-content.markdown h5 { margin-top: 14px; margin-bottom: 8px; }
.text-content.markdown h6 { margin-top: 12px; margin-bottom: 6px; }
.text-content.markdown p {
margin-bottom: 1em;
}
.text-content.markdown ul, .text-content.markdown ol {
margin-bottom: 1em;
padding-left: 2em;
}
.text-content.markdown blockquote {
border-left: 4px solid #ddd;
padding-left: 1em;
margin: 1em 0;
color: #666;
}
.text-content.markdown code {
background-color: #f4f4f4;
padding: 2px 4px;
border-radius: 3px;
font-family: 'Courier New', monospace;
font-size: 0.9em;
}
.text-content.markdown pre {
background-color: #f4f4f4;
padding: 10px;
border-radius: 4px;
overflow-x: auto;
margin: 1em 0;
}
.text-content.markdown pre code {
background: none;
padding: 0;
}
table {
width: 100%;
border-collapse: collapse;
margin-bottom: 1.5em;
}
th, td {
border: 1px solid #ddd;
padding: 12px 15px;
text-align: left;
vertical-align: top;
font-size: 14px;
}
th {
background-color: #f4f4f4;
font-weight: bold;
text-transform: uppercase;
letter-spacing: 0.05em;
border-bottom: 2px solid #ccc;
}
tr:nth-child(even) {
background-color: #f9f9f9;
}
tr:hover {
background-color: #f1f1f1;
}
td img {
max-width: 100%;
height: auto;
display: block;
}
table caption {
caption-side: bottom;
text-align: right;
font-size: 12px;
color: #777;
padding: 5px 0;
}
/* KaTeX display math centering */
.katex-display {
margin: 1em 0;
}
/* Metadata styles */
.metadata-container {
background: #f8f9fa;
border: 1px solid #dee2e6;
border-radius: 8px;
padding: 15px;
margin-bottom: 20px;
font-size: 13px;
color: #495057;
}
.metadata-grid {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
gap: 10px;
}
.metadata-item {
display: flex;
align-items: baseline;
}
.metadata-label {
font-weight: 600;
color: #6c757d;
margin-right: 5px;
min-width: fit-content;
}
.metadata-value {
color: #212529;
word-break: break-word;
}
.metadata-source-file {
grid-column: 1 / -1;
margin-top: 5px;
padding-top: 10px;
border-top: 1px solid #dee2e6;
}
</style>
<!-- Marked.js for Markdown parsing -->
<script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
<!-- KaTeX JavaScript -->
<script src="https://cdn.jsdelivr.net/npm/katex@0.16.9/dist/katex.min.js" integrity="sha384-XjKyOOlGwcjNTAIQHIpgOno0Hl1YQqzUOEleOLALmuqehneUG+vnGctmUb0ZY0l8" crossorigin="anonymous"></script>
</head>
<body>
<div class="document">
<div class="toggle-container">
<button class="toggle-button" id="toggleView">
<span id="toggleText">📝 Markdown View</span>
</button>
</div>
<!-- Metadata Section -->
<div class="metadata-container">
<div class="metadata-grid">
{% if metadata.source %}
<div class="metadata-item">
<span class="metadata-label">Source:</span>
<span class="metadata-value">{{ metadata.source }}</span>
</div>
{% endif %}
{% if metadata.olmocr_version %}
<div class="metadata-item">
<span class="metadata-label">OlmOCR:</span>
<span class="metadata-value">v{{ metadata.olmocr_version }}</span>
</div>
{% endif %}
{% if metadata.created %}
<div class="metadata-item">
<span class="metadata-label">Created:</span>
<span class="metadata-value">{{ metadata.created }}</span>
</div>
{% endif %}
{% if metadata.pdf_pages %}
<div class="metadata-item">
<span class="metadata-label">Pages:</span>
<span class="metadata-value">{{ metadata.pdf_pages }}</span>
</div>
{% endif %}
{% if metadata.tokens_in %}
<div class="metadata-item">
<span class="metadata-label">Tokens In:</span>
<span class="metadata-value">{{ metadata.tokens_in }}</span>
</div>
{% endif %}
{% if metadata.tokens_out %}
<div class="metadata-item">
<span class="metadata-label">Tokens Out:</span>
<span class="metadata-value">{{ metadata.tokens_out }}</span>
</div>
{% endif %}
{% if attributes.primary_language %}
<div class="metadata-item">
<span class="metadata-label">Language:</span>
<span class="metadata-value">{{ attributes.primary_language[0] }}</span>
</div>
{% endif %}
{% if attributes.rotation_correction %}
<div class="metadata-item">
<span class="metadata-label">Rotation:</span>
<span class="metadata-value">{{ attributes.rotation_correction[0] }}°</span>
</div>
{% endif %}
{% if metadata.source_file %}
<div class="metadata-item metadata-source-file">
<span class="metadata-label">File:</span>
<span class="metadata-value">{{ metadata.source_file }}</span>
</div>
{% endif %}
</div>
</div>
{% for page in pages %}
<div class="page-section" id="page-{{ page.page_num }}">
<div class="text">
<div class="text-content markdown" data-raw-text="{{ page.text }}">
<!-- Content will be rendered by JavaScript -->
</div>
</div>
{% if page.image %}
<div class="image">
<a href="{{ s3_link }}#page={{ page.page_num }}" target="_blank">
<img src="data:image/webp;base64,{{ page.image }}" alt="Page {{ page.page_num }} Image">
</a>
</div>
{% endif %}
</div>
{% endfor %}
</div>
<script>
// Store the current view mode
let isMarkdownView = true;
// Configure marked options
marked.setOptions({
breaks: true,
gfm: true,
tables: true,
headerIds: false,
mangle: false
});
// Function to render LaTeX expressions to HTML
function renderLatexToHtml(text) {
const patterns = [
{ regex: /\$\$([\s\S]+?)\$\$/g, display: true }, // Display math $$...$$
{ regex: /\\\[([\s\S]+?)\\\]/g, display: true }, // Display math \[...\]
{ regex: /\\\((.+?)\\\)/g, display: false } // Inline math \(...\)
];
let result = text;
patterns.forEach(({ regex, display }) => {
result = result.replace(regex, (match, latex) => {
try {
return katex.renderToString(latex, {
displayMode: display,
throwOnError: false
});
} catch (e) {
return match; // Return original if error
}
});
});
return result;
}
// Function to render markdown and LaTeX
function renderMarkdown() {
document.querySelectorAll('.text-content').forEach(element => {
const rawText = element.getAttribute('data-raw-text');
if (isMarkdownView) {
element.className = 'text-content markdown';
// Render LaTeX first, then markdown
element.innerHTML = marked.parse(renderLatexToHtml(rawText));
} else {
element.className = 'text-content raw';
element.innerHTML = '<pre>' + rawText + '</pre>';
}
});
}
// Toggle button functionality
document.getElementById('toggleView').addEventListener('click', function() {
isMarkdownView = !isMarkdownView;
const button = this;
const toggleText = document.getElementById('toggleText');
if (isMarkdownView) {
button.className = 'toggle-button';
toggleText.textContent = '📝 Markdown View';
} else {
button.className = 'toggle-button raw-mode';
toggleText.textContent = '📄 Raw Text View';
}
renderMarkdown();
});
// Initial render when page loads
document.addEventListener('DOMContentLoaded', function() {
renderMarkdown();
});
</script>
</body>
</html>