Create app.py

app.py

@@ -0,0 +1,119 @@
+"""Gradio app wrapping the official `commonforms` package to convert PDFs
+into fillable forms using jbarrow's FFDNet-L object detector (CPU ONNX).
+
+- Paper: <https://arxiv.org/abs/2509.16506>
+- Model: <https://huggingface.co/jbarrow/FFDNet-L-cpu>
+- Package: <https://pypi.org/project/commonforms/>
+
+Detecta 3 classes de campos: text boxes, checkboxes (choice buttons) e signatures.
+"""
+from __future__ import annotations
+
+import os
+
+# Força CPU antes de qualquer import que possa inicializar CUDA.
+os.environ.setdefault("CUDA_VISIBLE_DEVICES", "")
+os.environ.setdefault("NVIDIA_VISIBLE_DEVICES", "")
+
+import inspect
+import tempfile
+from pathlib import Path
+
+import gradio as gr
+from commonforms import prepare_form
+from huggingface_hub import hf_hub_download
+
+_PARAMS = inspect.signature(prepare_form).parameters
+print(f"[commonforms] prepare_form signature: {list(_PARAMS.keys())}")
+
+# Pre-baixa o ONNX uma vez no startup. O `commonforms` usa ultralytics YOLO
+# por baixo, que só aceita caminho LOCAL no parâmetro `model_or_path`.
+_MODEL_REPO = "jbarrow/FFDNet-L-cpu"
+_MODEL_FILE = "FFDNet-L.onnx"
+print(f"[commonforms] baixando {_MODEL_REPO}/{_MODEL_FILE}...")
+_ONNX_PATH = hf_hub_download(repo_id=_MODEL_REPO, filename=_MODEL_FILE)
+print(f"[commonforms] ONNX local: {_ONNX_PATH}")
+
+
+def detect_fields(
+    pdf_path: str | None,
+    image_size: int,
+    use_signature_fields: bool,
+    keep_existing_fields: bool,
+) -> str:
+    if not pdf_path:
+        raise gr.Error("Envie um PDF.")
+
+    src = Path(pdf_path)
+    if not src.exists():
+        raise gr.Error(f"Arquivo não encontrado: {src}")
+
+    _, out_str = tempfile.mkstemp(suffix="_fillable.pdf")
+    out = Path(out_str)
+
+    optional = {
+        "image_size": int(image_size),
+        "use_signature_fields": bool(use_signature_fields),
+        "keep_existing_fields": bool(keep_existing_fields),
+        "device": "cpu",
+        "model_or_path": _ONNX_PATH,
+    }
+    accepted = {k: v for k, v in optional.items() if k in _PARAMS}
+    print(f"[commonforms] calling prepare_form with kwargs: {accepted}")
+
+    try:
+        prepare_form(str(src), str(out), **accepted)
+    except Exception as exc:
+        raise gr.Error(f"Falha ao processar PDF: {exc}") from exc
+
+    return str(out)
+
+
+with gr.Blocks(title="CommonForms — Form Field Detector") as demo:
+    gr.Markdown(
+        "# CommonForms — Form Field Detector\n"
+        "Converte um PDF em formulário preenchível usando **FFDNet-L** "
+        "(`jbarrow/FFDNet-L-cpu`, Object Detection ONNX em CPU). "
+        "Detecta *text boxes*, *checkboxes* e *signature fields*.\n\n"
+        "Paper: [arxiv 2509.16506](<https://arxiv.org/abs/2509.16506>)  ·  "
+        "Modelo: [jbarrow/FFDNet-L-cpu](<https://huggingface.co/jbarrow/FFDNet-L-cpu>)"
+    )
+    with gr.Row():
+        with gr.Column():
+            pdf_in = gr.File(
+                label="PDF de entrada",
+                file_types=[".pdf"],
+                type="filepath",
+            )
+            image_size = gr.Slider(
+                minimum=512,
+                maximum=2048,
+                value=1600,
+                step=32,
+                label="Image size (px)",
+                info="Tamanho usado na inferência. Maior = mais preciso, mais lento.",
+            )
+            use_sig = gr.Checkbox(
+                value=False,
+                label="Incluir signature fields",
+                info="Detecta áreas de assinatura além de text/checkbox.",
+            )
+            keep = gr.Checkbox(
+                value=False,
+                label="Manter campos já existentes",
+                info="Preserva widgets AcroForm que já estavam no PDF.",
+            )
+            btn = gr.Button("Detectar campos", variant="primary")
+        with gr.Column():
+            pdf_out = gr.File(label="PDF preenchível")
+
+    btn.click(
+        fn=detect_fields,
+        inputs=[pdf_in, image_size, use_sig, keep],
+        outputs=pdf_out,
+        api_name="detect",
+    )
+
+
+if __name__ == "__main__":
+    demo.queue(max_size=4).launch()