app.py

import os
import re
import time
import fitz
import gradio as gr

from transformers import pipeline

# 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",
}

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
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 highlight_html(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])
    parts = []
    cursor = 0
    for s, e, label_id in spans:
        if cursor < s:
            parts.append(text[cursor:s].replace("\n", "<br>"))
        hex_color = LABEL_HEX.get(label_id, "#e2e8f0")
        label_idn = LABEL_MAP.get(label_id, label_id)
        word = text[s:e]
        parts.append(
            f'<mark style="background:{hex_color};border-radius:4px;padding:1px 4px;'
            f'font-weight:600;" title="{label_idn}">{word}</mark>'
        )
        cursor = e
    if cursor < len(text):
        parts.append(text[cursor:].replace("\n", "<br>"))
    return (
        '<div style="font-family:\'DM Sans\',sans-serif;font-size:14px;line-height:2;'
        'color:#1e293b;background:#fff;border-radius:12px;padding:20px 24px;'
        'border:1px solid #e2e8f0;white-space:pre-wrap;">'
        + "".join(parts) + "</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>"""

def run_ner_file(upload_file):
    if upload_file is None:
        return "<p style='color:#94a3b8;font-style:italic;padding:16px;'>Unggah file terlebih dahulu.</p>", ""

    file_path = upload_file if isinstance(upload_file, str) else upload_file.name
    ext = os.path.splitext(file_path)[-1].lower()

    if ext == ".txt":
        with open(file_path, "r", encoding="utf-8", errors="replace") as f:
            full_text = f.read()
        page_count = 1
    elif ext == ".pdf":
        doc = fitz.open(file_path)
        page_count = len(doc)
        if page_count > MAX_PDF_PAGES:
            doc.close()
            return (
                f"<p style='color:#be123c;padding:16px;'>PDF terlalu banyak halaman "
                f"({page_count}). Maks {MAX_PDF_PAGES} halaman.</p>", ""
            )
        full_text = "\n\n".join(page.get_text() for page in doc)
        doc.close()
    else:
        return "<p style='color:#be123c;padding:16px;'>Format tidak didukung.</p>", ""

    # Chunking
    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

    # NER
    all_ner_results = []
    for chunk in chunks:
        all_ner_results.extend(ner(chunk.strip()))

    if not all_ner_results:
        return "<p style='color:#94a3b8;padding:16px;'>Tidak ada entitas ditemukan.</p>", ""

    # Bangun entity_map
    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

    if not entity_map:
        return "<p style='color:#94a3b8;padding:16px;'>Tidak ada entitas ditemukan.</p>", ""

    highlighted = highlight_html(full_text, entity_map)

    # Badge legend
    found_labels = set(entity_map.values())
    badges = "".join(
        f'<span style="background:{LABEL_HEX.get(l,"#e2e8f0")};border-radius:20px;'
        f'padding:3px 10px;font-size:12px;font-weight:600;color:#1e293b;margin:3px;">'
        f'{LABEL_MAP.get(l, l)}</span>'
        for l in sorted(found_labels)
    )
    legend_html = f'<div style="margin-bottom:12px;line-height:2;">{badges}</div>'

    return highlighted, legend_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") 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 File"):
            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 file .pdf (maks 5 halaman) atau .txt.</p>'
                       )
                gr.HTML('<div class="section-heading">Unggah File</div>')
                pdf_input = gr.File(label="", file_types=[".pdf", ".txt"], type="filepath")
                analyze_pdf_btn = gr.Button("Analisis & Highlight Entitas", elem_id="analyze-pdf-btn")
                
                gr.HTML('<div class="section-heading" style="margin-top:20px;">Entitas Ditemukan</div>')
                pdf_legend = gr.HTML(value="")
                gr.HTML('<div class="section-heading" style="margin-top:12px;">Teks Ter-highlight</div>')
                pdf_output = 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)

    analyze_pdf_btn.click(
        fn=run_ner_file,
        inputs=pdf_input,
        outputs=[pdf_output, pdf_legend],
    )

if __name__ == "__main__":
    demo.launch(css=CUSTOM_CSS)