| <html> | |
| <head> | |
| <title>Chunky | Sentence Segmentation Service</title> | |
| <meta name="description" content="Chunky is a sentence segmentation service."> | |
| <meta name="viewport" content="width=device-width, initial-scale=1"> | |
| <meta http-equiv="Content-Type" content="text/html; charset=utf-8"> | |
| <style> | |
| body { | |
| margin: 0; | |
| font-family: ui-monospace, | |
| Menlo, Monaco, | |
| "Cascadia Mono", "Segoe UI Mono", | |
| "Roboto Mono", | |
| "Oxygen Mono", | |
| "Ubuntu Mono", | |
| "Source Code Pro", | |
| "Fira Mono", | |
| "Droid Sans Mono", | |
| "Consolas", "Courier New", monospace; | |
| } | |
| main { | |
| margin: 0 auto; | |
| padding: 1rem; | |
| max-width: 73ch; | |
| } | |
| ul { | |
| list-style: square; | |
| } | |
| div[data-autogrow]:has(textarea) { | |
| display: grid; | |
| } | |
| div[data-autogrow]:has(textarea)::after { | |
| content: attr(data-autogrow) ' '; | |
| white-space: pre-wrap; | |
| visibility: hidden; | |
| } | |
| div[data-autogrow]:has(textarea)>textarea { | |
| resize: none; | |
| overflow: hidden; | |
| } | |
| div[data-autogrow]:has(textarea)>textarea, | |
| div[data-autogrow]:has(textarea)::after { | |
| grid-area: 1 / 1 / 2 / 2; | |
| border: 1px solid currentColor; | |
| padding: 0.5rem; | |
| font: inherit; | |
| text-wrap: stable; | |
| } | |
| </style> | |
| </head> | |
| <body> | |
| <main> | |
| <h1>chunky</h1> | |
| <p>Sentence Segmentation Service</p> | |
| <form action="/split" method="post" enctype="multipart/form-data"> | |
| <label for="text">Text:</label><br> | |
| <div data-autogrow=""> | |
| <textarea name="text" id="text" rows="1" maxlength="16000"></textarea> | |
| </div> | |
| <input type="submit" value="Split Sentences"> | |
| </form> | |
| {% if sentences %} | |
| <button id="copy" type="button">copy</button> | |
| {%endif %} | |
| <ul> | |
| {% for sentence in sentences %} | |
| <li>{{ sentence }}</li> | |
| {% endfor %} | |
| </ul> | |
| <section> | |
| <h2>References</h2> | |
| <article> | |
| <header> | |
| <h3>Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation</h3> | |
| <p>by Markus Frohmann, Igor Sterner, Ivan Vulić, Benjamin Minixhofer, and Markus Schedl</p> | |
| </header> | |
| <p> | |
| <cite> | |
| Frohmann, M., Sterner, I., Vulić, I., Minixhofer, B., & Schedl, M. (2024). Segment Any Text: A Universal | |
| Approach for Robust, Efficient and Adaptable Sentence Segmentation. | |
| <em>arXiv preprint arXiv:2406.16678</em>. | |
| <a href="https://doi.org/10.48550/arXiv.2406.16678">https://doi.org/10.48550/arXiv.2406.16678</a> | |
| </cite> | |
| </p> | |
| </article> | |
| </section> | |
| </main> | |
| <noscript> | |
| {{sentences|safe|trim}} | |
| </noscript> | |
| <script> | |
| const textarea = document.querySelector("textarea"); | |
| if (textarea) { | |
| textarea.addEventListener("input", (e) => { | |
| textarea.parentElement.dataset["autogrow"] = textarea.value; | |
| }) | |
| } | |
| document.querySelector("button#copy").addEventListener("click", (e) => { | |
| navigator.clipboard.writeText(document.querySelector("noscript").textContent.trim() ?? "[]") | |
| }) | |
| </script> | |
| </body> | |
| </html> |