"""
# JS to read binary file upload as base64 into the hidden textbox
BINARY_UPLOAD_JS = """
function setupBinaryUpload() {
const input = document.getElementById('binary-file-input');
if (!input) return;
input.addEventListener('change', function(e) {
const file = e.target.files[0];
if (!file) return;
// Update file name display
const nameSpan = document.getElementById('binary-file-name');
if (nameSpan) nameSpan.textContent = file.name + ' (' + (file.size / 1024).toFixed(1) + ' KB)';
// Store filename
const fnBox = document.querySelectorAll('#binary-filename textarea');
if (fnBox.length > 0) {
fnBox[0].value = file.name;
fnBox[0].dispatchEvent(new Event('input', {bubbles: true}));
}
// Read as base64
const reader = new FileReader();
reader.onload = function(ev) {
const b64 = ev.target.result.split(',')[1];
const textareas = document.querySelectorAll('#binary-b64-data textarea');
if (textareas.length > 0) {
textareas[0].value = b64;
textareas[0].dispatchEvent(new Event('input', {bubbles: true}));
}
};
reader.readAsDataURL(file);
});
}
setTimeout(setupBinaryUpload, 1000);
"""
# JS to read .nc file upload as base64 into the hidden textbox
NC_UPLOAD_JS = """
function setupNcUpload() {
const input = document.getElementById('nc-file-input');
if (!input) return;
input.addEventListener('change', function(e) {
const file = e.target.files[0];
if (!file) return;
const nameSpan = document.getElementById('nc-file-name');
if (nameSpan) nameSpan.textContent = file.name + ' (' + (file.size / 1024).toFixed(1) + ' KB)';
const reader = new FileReader();
reader.onload = function(ev) {
const b64 = ev.target.result.split(',')[1];
const textareas = document.querySelectorAll('#nc-b64-data textarea');
if (textareas.length > 0) {
textareas[0].value = b64;
textareas[0].dispatchEvent(new Event('input', {bubbles: true}));
}
};
reader.readAsDataURL(file);
});
}
setTimeout(setupNcUpload, 1200);
"""
with gr.Blocks(title="Nacrith CPU") as demo:
gr.HTML(HEADER_HTML)
# ---- Tab 1: Compress Text ----
with gr.Tab("Compress Text"):
gr.Markdown("Compress text using trigram arithmetic coding (TC01 format).")
text_input = gr.Textbox(
label="Input Text",
placeholder="Paste or type text here (up to ~4000 characters)...",
lines=8,
)
compress_text_btn = gr.Button("Compress Text", variant="primary", size="lg")
compress_text_results = gr.Markdown()
compress_text_download = gr.HTML()
compress_text_b64 = gr.Textbox(
label="Compressed data (base64) -- copy to Decompress tab to verify",
lines=3,
show_copy_button=True,
)
compress_text_btn.click(
fn=compress_text,
inputs=[text_input],
outputs=[compress_text_results, compress_text_download, compress_text_b64],
)
gr.Examples(
examples=[
["The quick brown fox jumps over the lazy dog. This is a simple test of the neural compression system."],
["In the beginning, the universe was created. This has made a lot of people very angry and has been widely regarded as a bad move. The story so far: In the beginning the Universe was created. This has made a lot of people very angry and been widely regarded as a bad move."],
["Machine learning is a subset of artificial intelligence that focuses on building systems that learn from data. Unlike traditional programming where rules are explicitly coded, machine learning algorithms identify patterns in data and make decisions with minimal human intervention. Deep learning, a further subset, uses neural networks with many layers to model complex patterns in large amounts of data."],
],
inputs=[text_input],
label="Try these examples",
)
# ---- Tab 2: Upload Text/Binary ----
with gr.Tab("Upload Text/Binary"):
gr.Markdown(
"Upload any file (up to 1 MB) to compress.\n\n"
"The format is auto-detected: text files use trigram compression (TC01), "
"binary files use hybrid compression (NC05) where text-like regions are "
"trigram-compressed and binary regions are gzip/lzma-compressed."
)
gr.HTML(
'
'
''
''
'
'
)
# Hidden textboxes to receive data from JS
binary_b64_data = gr.Textbox(visible=False, elem_id="binary-b64-data")
binary_filename = gr.Textbox(visible=False, elem_id="binary-filename")
compress_file_btn = gr.Button("Compress", variant="primary", size="lg")
compress_file_results = gr.Markdown()
compress_file_download = gr.HTML()
compress_file_btn.click(
fn=compress_file_b64,
inputs=[binary_b64_data, binary_filename],
outputs=[compress_file_results, compress_file_download],
)
# ---- Tab 3: Decompress ----
with gr.Tab("Decompress"):
gr.Markdown(
"Upload a `.nc` file to decompress, or paste base64 data from the Compress Text tab.\n\n"
"Supports both TC01 (text) and NC05 (binary) formats."
)
gr.HTML(
'
'
''
''
'
'
)
nc_b64_data = gr.Textbox(visible=False, elem_id="nc-b64-data")
decompress_file_btn = gr.Button("Decompress File", variant="primary", size="lg")
gr.Markdown("**Or** paste base64 data:")
decompress_b64_input = gr.Textbox(
label="Compressed data (base64)",
placeholder="Paste base64 data here...",
lines=3,
)
decompress_b64_btn = gr.Button("Decompress Base64", variant="primary", size="lg")
decompress_results = gr.Markdown()
decompress_download = gr.HTML()
decompress_text_output = gr.Textbox(
label="Decompressed Text",
lines=10,
interactive=False,
)
decompress_file_btn.click(
fn=decompress_file_b64,
inputs=[nc_b64_data],
outputs=[decompress_results, decompress_download, decompress_text_output],
)
decompress_b64_btn.click(
fn=decompress_b64,
inputs=[decompress_b64_input],
outputs=[decompress_results, decompress_download, decompress_text_output],
)
gr.Markdown("""
---
**How it works:** Trigram tables precomputed from large text corpora predict the next token at each step.
Those predictions feed an arithmetic coder -- high-confidence predictions cost nearly zero bits.
The same tables run on both sides, guaranteeing perfect lossless reconstruction. No GPU required.
**Text (TC01):** Text is tokenized and trigram-compressed directly. Achieves ~15% ratio on English text (2.5x better than gzip).
**Binary (NC05):** Files are segmented into text-like and binary regions. Text regions are trigram-compressed;
binary regions are compressed with gzip or lzma. The hybrid approach beats gzip on files with significant text content.
Apache 2.0 | Made by [Roberto Tacconelli](https://github.com/st4ck) | [tacconelli.rob@gmail.com](tacconelli.rob@gmail.com) | [roberto@elizetaplus.com](roberto@elizetaplus.com)
""")
# Inject upload JS
gr.HTML(f"")
gr.HTML(f"")
demo.queue()
demo.launch()
