Delete app.py

app.py

@@ -1,479 +0,0 @@
-import gradio as gr
-from transformers import pipeline
-import fitz
-import tempfile
-import os
-import re
-import time
-
-# Load model
-ner = pipeline("ner", model="cahya/NusaBert-ner-v1.3", aggregation_strategy="simple")
-
-# Label mapping
-LABEL_MAP = {
-    "CRD": "Kardinal", "DAT": "Tanggal", "EVT": "Peristiwa",
-    "FAC": "Fasilitas", "GPE": "Entitas Geopolitik", "LAW": "Peraturan / Undang-Undang",
-    "LOC": "Lokasi", "MON": "Uang", "NOR": "Organisasi Politik",
-    "ORD": "Ordinal", "ORG": "Organisasi", "PER": "Orang",
-    "PRC": "Persentase", "PRD": "Produk", "QTY": "Kuantitas",
-    "REG": "Agama", "TIM": "Waktu", "WOA": "Karya Seni", "LAN": "Bahasa",
-}
-
-RTF_COLOR_TABLE = [
-    (255,191,191),(174,221,255),(141,199,255),(184,255,184),(153,242,204),
-    (217,255,165),(255,229,140),(255,204,102),(204,255,218),(242,204,255),
-    (224,191,255),(255,242,178),(199,242,242),(255,186,186),(255,217,165),
-    (191,223,255),(230,218,255),(255,230,218),(204,255,242),
-]
-
-LABEL_RTF_COLOR_IDX = {
-    "PER":1,"ORG":2,"NOR":3,"LOC":4,"GPE":5,"FAC":6,"DAT":7,"TIM":8,
-    "MON":9,"CRD":10,"ORD":11,"PRC":12,"QTY":13,"LAW":14,"EVT":15,
-    "PRD":16,"REG":17,"WOA":18,"LAN":19,
-}
-
-LABEL_HEX = {
-    "PER":"#FFBFBF","ORG":"#AEDDFF","NOR":"#8DC7FF","LOC":"#B8FFB8",
-    "GPE":"#99F2CC","FAC":"#D9FFA5","DAT":"#FFE58C","TIM":"#FFCC66",
-    "MON":"#CCFFDA","CRD":"#F2CCFF","ORD":"#E0BFFF","PRC":"#FFF2B2",
-    "QTY":"#C7F2F2","LAW":"#FFBABA","EVT":"#FFD9A5","PRD":"#BFDFFF",
-    "REG":"#E6DAFF","WOA":"#FFE6DA","LAN":"#CCFFF2",
-}
-
-MAX_PDF_PAGES = 5
-# NusaBERT max 512 token ≈ ~400 kata ≈ ~2500 karakter aman
-MAX_CHUNK_CHARS = 2000
-OVERLAP_CHARS   = 150
-
-EXAMPLES = [
-    ("Contoh 1 – RUPS & Dana Cadangan",
-     "Berdasarkan Rapat Umum Pemegang Saham (RUPS) pada tanggal 24 Juni 2024 yang disahkan "
-     "oleh notaris Ashoya Ratam, S.H., M.Kn., Risalah No.124/VI/2024, Perusahaan memutuskan "
-     "antara lain menyisihkan 5% dari laba bersih untuk tahun yang berakhir 31 Desember 2023 "
-     "atau sebesar Rp5.299.075.507 sebagai dana cadangan jaminan."),
-    ("Contoh 2 – Akta Jual Beli Saham PEFINDO",
-     "Berdasarkan Akta Notaris Melinda, S.Sos., S.H., M.Kn dengan No. 17 tanggal 21 Januari "
-     "2025, Perusahaan dan Dana Pensiun Pertamina telah menandatangani Akta Jual Beli saham "
-     "dan Perusahaan telah melakukan pembayaran penuh untuk pembelian 5.170 lembar saham "
-     "PEFINDO yang dimiliki Dana Pensiun Pertamina. Dengan demikian total kepemilikan saham "
-     "Perusahaan pada tanggal 21 Januari 2025 menjadi sebanyak 37.548 lembar saham atau sama "
-     "dengan 31,92% kepemilikan di PEFINDO."),
-    ("Contoh 3 – Fasilitas Kredit Bank Permata",
-     "Pada tanggal 12 Desember 2022, PEI, entitas anak, dan PT Bank Permata Tbk "
-     "menandatangani perjanjian fasilitas money market dengan fasilitas kredit maksimum "
-     "sebesar Rp50.000.000.000. Pinjaman ini digunakan untuk keperluan stand by facility "
-     "dengan jangka waktu penarikan antara 3 (tiga) hari sampai dengan 3 (tiga) bulan "
-     "semenjak tanggal penarikan pinjaman dilakukan."),
-    ("Contoh 4 – Dividen PEFINDO Biro Kredit",
-     "Berdasarkan Rapat Umum Pemegang Saham Tahunan tanggal 28 Juni 2024, pemegang saham "
-     "PEFINDO Biro Kredit menyetujui pembagian dividen untuk Perusahaan sebesar Rp6.637.962.683."),
-    ("Contoh 5 – Regulasi Bursa Karbon",
-     "Peraturan Presiden RI No. 98 Tahun 2021 tentang Penyelenggaraan Nilai Ekonomi Karbon "
-     "untuk Pencapaian Target Kontribusi yang Ditetapkan Secara Nasional dan Pengendalian "
-     "Emisi Gas Rumah Kaca dalam Pembangunan Nasional mengatur mengenai mekanisme pencapaian "
-     "NDC. Undang-undang RI No. 4 Tahun 2023 tentang Pengembangan dan Penguatan Sektor "
-     "Keuangan menegaskan bahwa tugas pengaturan dan pengawasan bursa karbon dilakukan oleh "
-     "Otoritas Jasa Keuangan."),
-]
-
-
-# ── Helpers ──────────────────────────────────────────────────────────────────
-
-def clean_word(word: str) -> str:
-    return word.replace("▁", " ").replace("##", "").strip()
-
-def get_label_id(raw_label: str) -> str:
-    label_id = raw_label.replace("B-","").replace("I-","").replace("B_","").replace("I_","")
-    return label_id.split("-")[-1].upper().strip()
-
-def escape_rtf(text: str) -> str:
-    out = []
-    for ch in text:
-        if ch == '\\': out.append('\\\\')
-        elif ch == '{': out.append('\\{')
-        elif ch == '}': out.append('\\}')
-        elif ord(ch) > 127: out.append(f'\\u{ord(ch)}?')
-        else: out.append(ch)
-    return ''.join(out)
-
-def build_rtf_color_table() -> str:
-    entries = "\\red0\\green0\\blue0;"
-    for r,g,b in RTF_COLOR_TABLE:
-        entries += f"\\red{r}\\green{g}\\blue{b};"
-    return "{\\colortbl ;" + entries + "}"
-
-def text_to_rtf_with_highlights(text: str, entity_map: dict) -> str:
-    sorted_entities = sorted(entity_map.items(), key=lambda x: len(x[0]), reverse=True)
-    spans = []
-    used = [False] * len(text)
-    for entity_lower, label_id in sorted_entities:
-        if not entity_lower:
-            continue
-        pattern = re.compile(re.escape(entity_lower), re.IGNORECASE)
-        for m in pattern.finditer(text):
-            s, e = m.start(), m.end()
-            if any(used[i] for i in range(s, e)):
-                continue
-            spans.append((s, e, label_id))
-            for i in range(s, e):
-                used[i] = True
-    spans.sort(key=lambda x: x[0])
-    rtf_parts = []
-    cursor = 0
-    for s, e, label_id in spans:
-        if cursor < s:
-            rtf_parts.append(escape_rtf(text[cursor:s]))
-        color_idx = LABEL_RTF_COLOR_IDX.get(label_id, 1)
-        highlighted = escape_rtf(text[s:e])
-        rtf_parts.append(f"{{\\highlight{color_idx} {highlighted}}}")
-        cursor = e
-    if cursor < len(text):
-        rtf_parts.append(escape_rtf(text[cursor:]))
-    return "".join(rtf_parts)
-
-def wrap_rtf(content: str) -> str:
-    color_table = build_rtf_color_table()
-    content_rtf = content.replace("\r\n","\n").replace("\r","\n").replace("\n","\\par\n")
-    return (
-        "{\\rtf1\\ansi\\ansicpg1252\\deff0\n"
-        "{\\fonttbl{\\f0\\froman\\fcharset0 Times New Roman;}}\n"
-        f"{color_table}\n"
-        "\\widowctrl\\wpaper12240\\wpaperh15840\n"
-        "\\margl1800\\margr1800\\margt1440\\margb1440\n"
-        "\\f0\\fs24\\sl360\\slmult1\n"
-        f"{content_rtf}"
-        "}"
-    )
-
-def _build_debug_html(lines: list) -> str:
-    rows = "".join(
-        f'<div style="padding:6px 10px; border-bottom:1px solid rgba(255,255,255,0.07); '
-        f'font-size:13px; color:#cbd5e1; font-family:monospace;">{line}</div>'
-        for line in lines
-    )
-    return f"""
-    <div style="margin-top:12px; background:rgba(15,23,42,0.85); border:1px solid rgba(99,102,241,0.35);
-                border-radius:12px; overflow:hidden;">
-        <div style="background:linear-gradient(135deg,#1e40af,#6d28d9); padding:8px 14px;
-                    font-size:11px; font-weight:700; letter-spacing:0.1em; color:#fff;">
-            🔍 DEBUG — WAKTU PER LANGKAH
-        </div>
-        {rows}
-    </div>"""
-
-
-# ── NER Teks ─────────────────────────────────────────────────────────────────
-
-def run_ner(text: str):
-    if not text or not text.strip():
-        return "<p style='color:#94a3b8; font-style:italic; padding:16px;'>Masukkan teks terlebih dahulu.</p>"
-    results = ner(text.strip())
-    if not results:
-        return "<p style='color:#94a3b8; font-style:italic; padding:16px;'>Tidak ada entitas yang ditemukan.</p>"
-
-    rows_html = ""
-    row_num = 1
-    seen_words = set()
-    for ent in results:
-        raw_label = ent["entity_group"]
-        label_id  = get_label_id(raw_label)
-        label_idn = LABEL_MAP.get(label_id, raw_label)
-        word      = clean_word(ent["word"])
-        if not word: continue
-        word_key = word.lower()
-        if word_key in seen_words: continue
-        seen_words.add(word_key)
-        hex_color = LABEL_HEX.get(label_id, "#e2e8f0")
-        score     = f"{ent['score']:.2%}"
-        row_bg    = "#f8faff" if row_num % 2 == 0 else "#ffffff"
-        rows_html += f"""
-        <tr style="background:{row_bg};">
-            <td style="padding:9px 14px;border-bottom:1px solid #e8edf5;text-align:center;color:#64748b;font-size:12px;">{row_num}</td>
-            <td style="padding:9px 14px;border-bottom:1px solid #e8edf5;font-weight:600;color:#1e293b;">{word}</td>
-            <td style="padding:9px 14px;border-bottom:1px solid #e8edf5;">
-                <span style="background:{hex_color};padding:3px 10px;border-radius:20px;font-size:12px;font-weight:600;color:#1e293b;">{label_idn}</span>
-            </td>
-            <td style="padding:9px 14px;border-bottom:1px solid #e8edf5;font-size:12px;color:#64748b;text-align:center;">{score}</td>
-        </tr>"""
-        row_num += 1
-
-    if not rows_html:
-        return "<p style='color:#94a3b8; font-style:italic; padding:16px;'>Tidak ada entitas yang ditemukan.</p>"
-
-    return f"""
-    <div style="overflow-x:auto;margin-top:4px;border-radius:12px;border:1px solid #e2e8f0;box-shadow:0 2px 12px rgba(0,0,0,0.06);">
-        <table style="width:100%;border-collapse:collapse;font-size:14px;font-family:'Segoe UI',sans-serif;">
-            <thead>
-                <tr style="background:linear-gradient(135deg,#1e40af,#6d28d9);">
-                    <th style="padding:12px 14px;color:#fff;width:55px;font-weight:600;font-size:12px;letter-spacing:0.05em;">NO</th>
-                    <th style="padding:12px 14px;color:#fff;text-align:left;font-weight:600;font-size:12px;letter-spacing:0.05em;">KATA / FRASA</th>
-                    <th style="padding:12px 14px;color:#fff;text-align:left;font-weight:600;font-size:12px;letter-spacing:0.05em;">ENTITAS</th>
-                    <th style="padding:12px 14px;color:#fff;width:90px;font-weight:600;font-size:12px;letter-spacing:0.05em;">SKOR</th>
-                </tr>
-            </thead>
-            <tbody>{rows_html}</tbody>
-        </table>
-    </div>"""
-
-
-# ── NER PDF → RTF ─────────────────────────────────────────────────────────────
-
-def run_ner_pdf(pdf_file):
-    # return: (out_path, legend_html, warn_html, debug_html)
-    if pdf_file is None:
-        return None, "", "<p style='color:#94a3b8;font-style:italic;padding:16px;'>Unggah file PDF terlebih dahulu.</p>", ""
-
-    pdf_path = pdf_file if isinstance(pdf_file, str) else pdf_file.name
-    doc = fitz.open(pdf_path)
-    page_count = len(doc)
-
-    if page_count > MAX_PDF_PAGES:
-        doc.close()
-        return None, "", f"""
-        <div style="background:#fff1f2;border:1.5px solid #fda4af;border-radius:12px;
-                    padding:16px 20px;display:flex;align-items:center;gap:12px;">
-            <span style="font-size:24px;">⚠️</span>
-            <div>
-                <p style="margin:0;font-weight:700;color:#be123c;font-size:15px;">PDF Terlalu Banyak Halaman</p>
-                <p style="margin:4px 0 0;color:#9f1239;font-size:13px;">
-                    File Anda memiliki <strong>{page_count} halaman</strong>.
-                    Maksimal <strong>{MAX_PDF_PAGES} halaman</strong>.
-                </p>
-            </div>
-        </div>""", ""
-
-    debug_lines = []
-    t_total = time.time()
-
-    # ── LANGKAH 1: Ekstrak teks ──
-    t0 = time.time()
-    pages_text = [page.get_text() for page in doc]
-    doc.close()
-    full_text = "\n\n".join(pages_text)
-    char_count = len(full_text)
-    t1 = time.time()
-    debug_lines.append(f"✅ <b>Langkah 1</b> — Ekstrak teks PDF: <b>{t1-t0:.3f}s</b> | {char_count:,} karakter | {page_count} halaman")
-
-    # ── LANGKAH 2: Chunking ──
-    t0 = time.time()
-    chunks = []
-    start = 0
-    while start < len(full_text):
-        end = min(start + MAX_CHUNK_CHARS, len(full_text))
-        chunks.append(full_text[start:end])
-        if end == len(full_text):
-            break
-        start = end - OVERLAP_CHARS
-    t1 = time.time()
-    debug_lines.append(f"✅ <b>Langkah 2</b> — Chunking teks: <b>{t1-t0:.4f}s</b> | {len(chunks)} chunk @ {MAX_CHUNK_CHARS} karakter")
-
-    # ── LANGKAH 3: NER model (ini yang biasanya paling lama) ──
-    t0 = time.time()
-    all_ner_results = []
-    chunk_times = []
-    for i, chunk in enumerate(chunks):
-        tc = time.time()
-        chunk_results = ner(chunk.strip())
-        chunk_times.append(time.time() - tc)
-        all_ner_results.extend(chunk_results)
-    t1 = time.time()
-    avg_chunk = sum(chunk_times)/len(chunk_times) if chunk_times else 0
-    debug_lines.append(
-        f"✅ <b>Langkah 3</b> — NER model: <b>{t1-t0:.2f}s</b> total | "
-        f"{len(chunks)} chunk | avg/chunk: {avg_chunk:.2f}s | {len(all_ner_results)} entitas raw"
-    )
-    # Detail per chunk
-    for i, ct in enumerate(chunk_times):
-        debug_lines.append(f"&nbsp;&nbsp;&nbsp;↳ chunk {i+1}/{len(chunks)}: {ct:.2f}s ({len(chunks[i])} karakter)")
-
-    if not all_ner_results:
-        dh = _build_debug_html(debug_lines)
-        return None, "", "<p style='color:#94a3b8;padding:16px;'>Tidak ada entitas ditemukan.</p>", dh
-
-    # ── LANGKAH 4: Bangun entity_map ──
-    t0 = time.time()
-    entity_map: dict[str, str] = {}
-    for ent in all_ner_results:
-        word = clean_word(ent["word"])
-        if len(word) < 2: continue
-        label_id = get_label_id(ent["entity_group"])
-        w_lower = word.lower()
-        if w_lower not in entity_map:
-            entity_map[w_lower] = label_id
-    t1 = time.time()
-    debug_lines.append(f"✅ <b>Langkah 4</b> — Bangun entity_map: <b>{t1-t0:.4f}s</b> | {len(entity_map)} entitas unik")
-
-    if not entity_map:
-        dh = _build_debug_html(debug_lines)
-        return None, "", "<p style='color:#94a3b8;padding:16px;'>Tidak ada entitas ditemukan.</p>", dh
-
-    # ── LANGKAH 5: Highlight → RTF content ──
-    t0 = time.time()
-    rtf_content = text_to_rtf_with_highlights(full_text, entity_map)
-    t1 = time.time()
-    debug_lines.append(f"✅ <b>Langkah 5</b> — Highlight & build RTF content: <b>{t1-t0:.4f}s</b>")
-
-    # ── LANGKAH 6: Tulis file .rtf ──
-    t0 = time.time()
-    rtf_full = wrap_rtf(rtf_content)
-    out_fd, out_path = tempfile.mkstemp(suffix=".rtf")
-    with os.fdopen(out_fd, "w", encoding="ascii", errors="replace") as f:
-        f.write(rtf_full)
-    t1 = time.time()
-    debug_lines.append(f"✅ <b>Langkah 6</b> — Tulis file RTF: <b>{t1-t0:.4f}s</b> | {len(rtf_full):,} bytes")
-
-    t_end = time.time()
-    debug_lines.append(f"⏱ <b>TOTAL WAKTU: {t_end-t_total:.2f}s</b>")
-
-    debug_html = _build_debug_html(debug_lines)
-    found_labels: set[str] = set(entity_map.values())
-
-    # ── Legend ──
-    legend_rows = ""
-    for label_id in sorted(found_labels):
-        label_idn = LABEL_MAP.get(label_id, label_id)
-        hex_color = LABEL_HEX.get(label_id, "#e2e8f0")
-        legend_rows += f"""
-        <tr>
-            <td style="padding:8px 14px;border-bottom:1px solid #e8edf5;">
-                <span style="display:inline-block;width:24px;height:24px;border-radius:6px;
-                             background:{hex_color};vertical-align:middle;border:1px solid rgba(0,0,0,0.1);"></span>
-            </td>
-            <td style="padding:8px 14px;border-bottom:1px solid #e8edf5;font-weight:600;color:#1e293b;font-size:13px;">{label_id}</td>
-            <td style="padding:8px 14px;border-bottom:1px solid #e8edf5;color:#475569;font-size:13px;">{label_idn}</td>
-        </tr>"""
-
-    legend_html = f"""
-    <div style="margin-top:4px;">
-        <p style="font-size:13px;color:#64748b;margin-bottom:10px;">
-            Ditemukan <strong style='color:#1e40af;'>{len(found_labels)}</strong> jenis entitas
-            dari <strong style='color:#1e40af;'>{page_count}</strong> halaman PDF.
-            Buka file <strong>.rtf</strong> di <strong>Microsoft Word</strong> atau <strong>LibreOffice Writer</strong>.
-        </p>
-        <div style="overflow-x:auto;border-radius:12px;border:1px solid #e2e8f0;box-shadow:0 2px 12px rgba(0,0,0,0.06);">
-            <table style="width:100%;border-collapse:collapse;font-family:'Segoe UI',sans-serif;">
-                <thead>
-                    <tr style="background:linear-gradient(135deg,#1e40af,#6d28d9);">
-                        <th style="padding:11px 14px;color:#fff;font-size:12px;letter-spacing:0.05em;width:50px;">WARNA</th>
-                        <th style="padding:11px 14px;color:#fff;font-size:12px;letter-spacing:0.05em;text-align:left;">KODE</th>
-                        <th style="padding:11px 14px;color:#fff;font-size:12px;letter-spacing:0.05em;text-align:left;">NAMA ENTITAS</th>
-                    </tr>
-                </thead>
-                <tbody>{legend_rows}</tbody>
-            </table>
-        </div>
-    </div>"""
-
-    return out_path, legend_html, "", debug_html
-
-
-# ── CSS ───────────────────────────────────────────────────────────────────────
-
-CUSTOM_CSS = """
-@import url('https://fonts.googleapis.com/css2?family=Playfair+Display:wght@700;900&family=DM+Sans:wght@400;500;600&display=swap');
-.gradio-container{max-width:100%!important;padding:0!important;background:linear-gradient(160deg,#0f172a 0%,#1e1b4b 40%,#0f172a 100%)!important;min-height:100vh;}
-#hero-header{background:linear-gradient(135deg,#1e40af 0%,#6d28d9 50%,#be185d 100%);padding:40px 48px 36px;margin:0 0 24px;border-radius:16px;text-align:center;position:relative;overflow:hidden;}
-#hero-header::before{content:'';position:absolute;inset:0;background:url("data:image/svg+xml,%3Csvg width='60' height='60' viewBox='0 0 60 60' xmlns='http://www.w3.org/2000/svg'%3E%3Cg fill='none' fill-rule='evenodd'%3E%3Cg fill='%23ffffff' fill-opacity='0.04'%3E%3Cpath d='M36 34v-4h-2v4h-4v2h4v4h2v-4h4v-2h-4zm0-30V0h-2v4h-4v2h4v4h2V6h4V4h-4zM6 34v-4H4v4H0v2h4v4h2v-4h4v-2H6zM6 4V0H4v4H0v2h4v4h2V6h4V4H6z'/%3E%3C/g%3E%3C/g%3E%3C/svg%3E");}
-.tab-nav{background:rgba(255,255,255,0.05)!important;border-radius:12px!important;padding:4px!important;border:1px solid rgba(255,255,255,0.1)!important;margin:0!important;}
-.tab-nav button{background:transparent!important;color:#94a3b8!important;border-radius:8px!important;padding:10px 24px!important;font-family:'DM Sans',sans-serif!important;font-weight:600!important;font-size:14px!important;transition:all 0.2s!important;}
-.tab-nav button.selected{background:linear-gradient(135deg,#1e40af,#6d28d9)!important;color:#ffffff!important;box-shadow:0 4px 12px rgba(109,40,217,0.4)!important;}
-label span{color:#cbd5e1!important;font-family:'DM Sans',sans-serif!important;font-weight:600!important;font-size:12px!important;letter-spacing:0.07em!important;text-transform:uppercase!important;}
-textarea,.gr-textbox textarea{background:rgba(15,23,42,0.7)!important;border:1.5px solid rgba(255,255,255,0.12)!important;border-radius:10px!important;color:#e2e8f0!important;font-family:'DM Sans',sans-serif!important;font-size:14px!important;padding:14px!important;transition:border 0.2s!important;}
-textarea:focus{border-color:#6d28d9!important;outline:none!important;}
-.example-btn{display:block!important;width:100%!important;text-align:left!important;padding:12px 16px!important;margin-bottom:8px!important;background:rgba(30,64,175,0.15)!important;border:1px solid rgba(99,102,241,0.30)!important;border-radius:10px!important;cursor:pointer!important;font-size:13px!important;line-height:1.6!important;color:#cbd5e1!important;white-space:normal!important;height:auto!important;font-family:'DM Sans',sans-serif!important;transition:all 0.2s!important;}
-.example-btn:hover{background:rgba(109,40,217,0.25)!important;border-color:#6d28d9!important;color:#e2e8f0!important;transform:translateX(3px);}
-#analyze-btn,#analyze-pdf-btn{background:linear-gradient(135deg,#1e40af,#6d28d9)!important;color:white!important;font-weight:700!important;font-size:15px!important;border-radius:10px!important;padding:12px 0!important;margin-top:8px!important;font-family:'DM Sans',sans-serif!important;letter-spacing:0.03em!important;box-shadow:0 4px 16px rgba(109,40,217,0.35)!important;transition:all 0.2s!important;border:none!important;}
-#analyze-btn:hover,#analyze-pdf-btn:hover{transform:translateY(-2px)!important;box-shadow:0 6px 24px rgba(109,40,217,0.50)!important;}
-.section-heading{font-family:'DM Sans',sans-serif;font-weight:700;font-size:11px;letter-spacing:0.12em;text-transform:uppercase;color:#ffffff!important;margin-bottom:12px;display:flex;align-items:center;gap:8px;}
-.section-heading::before{content:'';display:inline-block;width:18px;height:2px;background:linear-gradient(90deg,#6d28d9,#be185d);border-radius:2px;}
-.gr-file{background:rgba(15,23,42,0.7)!important;border:1.5px dashed rgba(99,102,241,0.40)!important;border-radius:10px!important;color:#94a3b8!important;}
-.gr-file-download{background:rgba(30,64,175,0.2)!important;border:1px solid rgba(99,102,241,0.4)!important;border-radius:10px!important;color:#a5b4fc!important;font-family:'DM Sans',sans-serif!important;}
-#center-col{max-width:780px!important;margin:0 auto!important;width:100%!important;padding:0 8px!important;}
-#footer{text-align:center;padding:20px;color:rgba(148,163,184,0.5);font-family:'DM Sans',sans-serif;font-size:12px;letter-spacing:0.04em;}
-.gradio-container h3{color:#e2e8f0!important;}
-#center-col p{color:#94a3b8!important;}
-"""
-
-HERO_HTML = """
-<div id="hero-header">
-    <p style="font-family:'DM Sans',sans-serif;font-size:12px;font-weight:700;letter-spacing:0.20em;text-transform:uppercase;color:rgba(165,180,252,0.8);margin:0 0 10px;">Tugas Kelompok · NLP &amp; Text Mining</p>
-    <h1 style="font-family:'Playfair Display',serif;font-size:clamp(32px,5vw,56px);font-weight:900;color:#ffffff;margin:0 0 8px;line-height:1.1;text-shadow:0 2px 20px rgba(109,40,217,0.5);">
-        NER <span style="color:#a78bfa;">for</span> Financial Statements
-    </h1>
-    <p style="font-family:'DM Sans',sans-serif;font-size:clamp(13px,2vw,16px);color:rgba(203,213,225,0.85);margin:0 auto 18px;max-width:640px;line-height:1.6;">
-        Implementasi Named Entity Recognition pada Kumpulan<br>Laporan-laporan Keuangan Bahasa Indonesia
-    </p>
-    <div style="display:inline-flex;align-items:center;gap:8px;background:rgba(0,0,0,0.25);border:1px solid rgba(255,255,255,0.15);border-radius:20px;padding:6px 16px 6px 8px;">
-        <span style="background:linear-gradient(135deg,#1e40af,#6d28d9);border-radius:12px;padding:3px 10px;font-size:11px;font-weight:700;color:#fff;letter-spacing:0.05em;">MODEL</span>
-        <span style="font-family:monospace;font-size:13px;color:#a5b4fc;">cahya/NusaBert-ner-v1.3</span>
-    </div>
-</div>
-"""
-
-
-# ── Gradio UI ─────────────────────────────────────────────────────────────────
-
-with gr.Blocks(title="NER for Financial Statements", css=CUSTOM_CSS) as demo:
-
-    gr.HTML(HERO_HTML)
-
-    with gr.Tabs(elem_classes="tab-nav"):
-
-        with gr.Tab("Analisis Teks"):
-            with gr.Column(elem_id="center-col"):
-                gr.HTML('<div class="section-heading">Contoh Teks</div>')
-                example_btns = []
-                for title, body in EXAMPLES:
-                    btn = gr.Button(f"📌 {title}\n\n{body}", elem_classes="example-btn")
-                    example_btns.append((btn, body))
-
-                gr.HTML('<div class="section-heading" style="margin-top:20px;">Input Teks</div>')
-                text_input = gr.Textbox(lines=9, placeholder="Ketik atau tempel teks laporan keuangan di sini…", label="", show_label=False)
-                analyze_btn = gr.Button("Lakukan Analisis", elem_id="analyze-btn")
-
-                gr.HTML('<div class="section-heading" style="margin-top:20px;">Hasil Analisis Entitas</div>')
-                text_output = gr.HTML(value="<p style='color:#64748b;font-size:14px;font-family:DM Sans,sans-serif;padding:20px;text-align:center;'>Masukkan teks lalu klik Lakukan Analisis.</p>")
-
-        with gr.Tab("Analisis PDF"):
-            with gr.Column(elem_id="center-col"):
-                gr.HTML(
-                    '<p style="color:#94a3b8;font-family:DM Sans,sans-serif;font-size:13px;margin:0 0 16px;">'
-                    'Unggah PDF laporan keuangan (maks. <strong style="color:#a78bfa;">5 halaman</strong>). '
-                    'Output: file <strong style="color:#a78bfa;">.rtf</strong> dengan stabilo warna — '
-                    'bisa dibuka di <strong>Microsoft Word</strong> atau <strong>LibreOffice</strong>.</p>'
-                )
-                gr.HTML('<div class="section-heading">Unggah PDF</div>')
-                pdf_input = gr.File(label="", file_types=[".pdf"], type="filepath")
-                analyze_pdf_btn = gr.Button("Highlight Entitas → Download RTF", elem_id="analyze-pdf-btn")
-                pdf_warning = gr.HTML(value="")
-
-                with gr.Column(visible=False) as pdf_results_col:
-                    gr.HTML('<div class="section-heading" style="margin-top:20px;">Download Hasil RTF</div>')
-                    pdf_output = gr.File(label="", file_types=[".rtf"], interactive=False)
-                    gr.HTML('<div class="section-heading" style="margin-top:20px;">Keterangan Warna Entitas</div>')
-                    pdf_legend = gr.HTML(value="")
-                    # Debug panel — selalu tampil setelah proses
-                    pdf_debug = gr.HTML(value="")
-
-    gr.HTML('<div id="footer">NER for Financial Statements 2026</div>')
-
-    # Wiring
-    for btn, body in example_btns:
-        btn.click(fn=lambda b=body: b, inputs=[], outputs=text_input)
-
-    analyze_btn.click(fn=run_ner, inputs=text_input, outputs=text_output)
-    text_input.submit(fn=run_ner, inputs=text_input, outputs=text_output)
-
-    def handle_pdf(pdf_file):
-        out_path, legend_html, warn_html, debug_html = run_ner_pdf(pdf_file)
-        show = gr.Column(visible=out_path is not None)
-        return out_path, legend_html, warn_html, debug_html, show
-
-    analyze_pdf_btn.click(
-        fn=handle_pdf,
-        inputs=pdf_input,
-        outputs=[pdf_output, pdf_legend, pdf_warning, pdf_debug, pdf_results_col],
-    )
-
-if __name__ == "__main__":
-    demo.launch()