app.py

"""Anonimizzatore Gare d'Appalto — UI Gradio."""
import gradio as gr

from config import MODES, DEFAULT_MIN_SCORE, SEVERITY_COLORS, SEVERITY_LABELS, SEVERITY_ORDER
from pipeline import anonymize
from renderers import render_highlighted_text, render_anonymized_text, render_categorized_report
from utils import extract_pdf_text
from demo_text import DEMO_TEXT


# ---------------------------------------------------------------------------
# Handlers
# ---------------------------------------------------------------------------
def _process(text: str, mode: str, min_score: float, use_regex: bool):
    if not text or not text.strip():
        e = '<div style="padding:40px; text-align:center; color:#6b7280; font-family:Arial,sans-serif;">Inserisci del testo per iniziare.</div>'
        return e, e, e
    anon_text, entities = anonymize(text, mode, min_score, use_regex)
    return (
        render_highlighted_text(text, entities),
        render_anonymized_text(anon_text),
        render_categorized_report(text, entities),
    )


def handle_text(text, mode, min_score, use_regex):
    return _process(text, mode, min_score, use_regex)


def handle_pdf(pdf_file, mode, min_score, use_regex):
    def _err(msg):
        e = f'<div style="padding:40px; text-align:center; color:#6b7280; font-family:Arial,sans-serif;">{msg}</div>'
        return e, e, e
    if pdf_file is None:
        return _err("Carica un PDF per iniziare.")
    raw = extract_pdf_text(pdf_file)
    if not raw.strip():
        return _err("⚠️ Impossibile estrarre testo dal PDF (scansionato?).")
    return _process(raw, mode, min_score, use_regex)


# ---------------------------------------------------------------------------
# Legenda gravità
# ---------------------------------------------------------------------------
def _legend_html() -> str:
    badges = []
    for sev in SEVERITY_ORDER:
        c = SEVERITY_COLORS[sev]
        badges.append(
            f'<span style="background:{c["bg"]}; border-left:3px solid {c["border"]}; '
            f'padding:3px 10px; border-radius:4px; color:{c["text"]}; '
            f'font-size:0.85em; font-weight:500;">Gravità {SEVERITY_LABELS[sev]}</span>'
        )
    return (
        '<div style="display:flex; gap:8px; flex-wrap:wrap; margin:8px 0; '
        'font-family:Arial,Helvetica,sans-serif;">'
        + "".join(badges) + '</div>'
    )


# ---------------------------------------------------------------------------
# CSS
# ---------------------------------------------------------------------------
_CSS = """
.gradio-container {
    max-width: 1200px !important;
    margin: 0 auto !important;
    font-family: Arial, Helvetica, sans-serif !important;
}
.gradio-container * { font-family: Arial, Helvetica, sans-serif !important; }
.header-block h1  { margin-bottom: 4px !important; font-weight: 700; }
.section-label {
    font-size: 0.78em !important; font-weight: 700 !important;
    text-transform: uppercase; letter-spacing: 0.06em;
    color: #6b7280 !important; margin-bottom: 6px !important;
}
button.primary { font-weight: 600 !important; }
"""

# ---------------------------------------------------------------------------
# UI
# ---------------------------------------------------------------------------
with gr.Blocks(
    title="Anonimizzatore Gare d'Appalto",
    theme=gr.themes.Soft(primary_hue="blue", neutral_hue="slate",
                         font=["Arial", "Helvetica", "sans-serif"]),
    css=_CSS,
) as demo:

    with gr.Row(elem_classes=["header-block"]):
        gr.Markdown(
            "# 🔒 Anonimizzatore Gare d'Appalto\n"
            "Pipeline a 3 livelli: **Regex** → **NER** (Italian_NER_XXL_v2) → "
            "**GLiNER** (PII_ITA zero-shot), con doppio passaggio regex finale."
        )

    gr.Markdown("### Impostazioni", elem_classes=["section-label"])

    mode_radio = gr.Radio(
        choices=list(MODES.keys()),
        value=list(MODES.keys())[0],
        label="Modalità di offuscamento",
    )

    with gr.Row(equal_height=True):
        score_slider = gr.Slider(
            minimum=0.0, maximum=1.0, value=DEFAULT_MIN_SCORE, step=0.05,
            label="Score minimo di confidenza", scale=3,
        )
        use_regex_chk = gr.Checkbox(
            value=True, label="Livello 1: regex appalti", scale=1,
        )

    gr.Markdown("### Input", elem_classes=["section-label"])
    with gr.Tabs():
        with gr.TabItem("📝 Testo"):
            txt_in = gr.Textbox(
                label=None, lines=10,
                placeholder="Incolla il testo del documento di gara…",
                show_label=False,
            )
            with gr.Row():
                txt_btn  = gr.Button("Anonimizza",        variant="primary",   size="lg", scale=3)
                demo_btn = gr.Button("📋 Carica esempio", variant="secondary",  size="lg", scale=1)

        with gr.TabItem("📄 PDF"):
            pdf_in  = gr.File(label="Carica un PDF", file_types=[".pdf"])
            pdf_btn = gr.Button("Anonimizza", variant="primary", size="lg")

    gr.HTML(_legend_html())

    gr.Markdown("### Risultato", elem_classes=["section-label"])
    with gr.Tabs():
        with gr.TabItem("🎨 Evidenziato"):
            out_highlighted = gr.HTML()
        with gr.TabItem("🔒 Anonimizzato"):
            out_anonymized  = gr.HTML()
        with gr.TabItem("📊 Report"):
            out_report      = gr.HTML()

    outputs       = [out_highlighted, out_anonymized, out_report]
    inputs_common = [mode_radio, score_slider, use_regex_chk]

    txt_btn.click(handle_text, inputs=[txt_in, *inputs_common], outputs=outputs)
    pdf_btn.click(handle_pdf,  inputs=[pdf_in, *inputs_common], outputs=outputs)
    demo_btn.click(lambda: DEMO_TEXT, inputs=None, outputs=txt_in)

demo.launch()