app.py

import gradio as gr
from pathlib import Path
import tempfile, datetime, json, shutil, os
from core import generate_report
from rag import build_or_update_index, answer_with_context

TITLE = "IR/ESG Report Generator (HF Space, Pro)"
DESC = "CSV/YAML から IR/ESG レポート（HTML/PDF/DOCX）を生成。LLM要約＋翻訳・グラフ・ベンチマーク・RAG・Hub保存に対応。"

TEMPLATES_DIR = str((Path(__file__).resolve().parent / "templates").absolute())

import shutil as _shutil
def _to_path(upload_obj, tmpdir: Path, filename: str) -> Path:
    dst = tmpdir / filename
    if upload_obj is None:
        raise ValueError(f"{filename} が未指定です。")
    if isinstance(upload_obj, (str, Path)):
        src = Path(upload_obj); _shutil.copy(src, dst); return dst
    if hasattr(upload_obj, "name"):  # NamedString
        src = Path(upload_obj.name); _shutil.copy(src, dst); return dst
    if hasattr(upload_obj, "read"):
        data = upload_obj.read()
        if isinstance(data, str): data = data.encode("utf-8")
        dst.write_bytes(data); return dst
    if isinstance(upload_obj, dict):
        if "name" in upload_obj: _shutil.copy(upload_obj["name"], dst); return dst
        if "data" in upload_obj: 
            data = upload_obj["data"]
            if isinstance(data, str): data = data.encode("utf-8")
            dst.write_bytes(data); return dst
    raise TypeError(f"Unsupported upload type: {type(upload_obj)}")

def run(company_yaml, financials_csv, esg_csv, use_llm, lang, template_key,
        tenant, push_to_hub, glossary_yaml, benchmarks_yaml, past_reports_zip):
    try:
        if not company_yaml or not financials_csv or not esg_csv:
            return "全ファイルをアップロードしてください。", None, None, None, None, ""

        with tempfile.TemporaryDirectory() as td:
            tdir = Path(td)
            cpath = _to_path(company_yaml, tdir, "company.yaml")
            fpath = _to_path(financials_csv, tdir, "financials.csv")
            epath = _to_path(esg_csv, tdir, "esg.csv")
            gpath = _to_path(glossary_yaml, tdir, "glossary.yaml") if glossary_yaml else None
            bpath = _to_path(benchmarks_yaml, tdir, "benchmarks.yaml") if benchmarks_yaml else None
            rzip  = _to_path(past_reports_zip, tdir, "past_reports.zip") if past_reports_zip else None

            
            if rzip:
                build_or_update_index(rzip, index_dir=tdir / "index")

            outdir = tdir / "out"; outdir.mkdir(parents=True, exist_ok=True)

            llm = None
            if use_llm:
                try:
                    from llm import OpenAILLM
                    llm = OpenAILLM()
                except Exception as e:
                    return f"LLM初期化エラー: {e}", None, None, None, None, ""

            html, pdf, docx, meta_json, html_text = generate_report(
                company_yaml=str(cpath),
                financials_csv=str(fpath),
                esg_csv=str(epath),
                templates_dir=TEMPLATES_DIR,
                template_name={
                    "base":"base.html.j2",
                    "tcfd":"tcfd.html.j2",
                    "sasab":"sasb.html.j2",  
                    "sasb":"sasb.html.j2",
                    "gri":"gri.html.j2",
                }.get(template_key, "base.html.j2"),
                out_html=str(outdir / "report.html"),
                out_pdf=str(outdir / "report.pdf"),
                out_docx=str(outdir / "report.docx"),
                lang=lang,
                llm=llm,
                glossary_path=str(gpath) if gpath else None,
                benchmarks_path=str(bpath) if bpath else None,
                tenant=tenant,
                rag_index_dir=str(tdir / "index") if rzip else None,
            )

            repo_tmp = Path("./tmp"); repo_tmp.mkdir(exist_ok=True)
            ts = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
            prefix = f"{tenant or 'default'}-{ts}"
            html_out = repo_tmp / f"{prefix}.html"
            pdf_out  = repo_tmp / f"{prefix}.pdf"
            docx_out = repo_tmp / f"{prefix}.docx"
            meta_out = repo_tmp / f"{prefix}.json"
            _shutil.copy(html, html_out)
            _shutil.copy(pdf, pdf_out)
            _shutil.copy(docx, docx_out)
            Path(meta_out).write_text(json.dumps(meta_json, ensure_ascii=False, indent=2), encoding="utf-8")

            if push_to_hub:
                try:
                    from huggingface_hub import HfApi
                    api = HfApi()
                    repo_id = os.environ.get("HF_DATASET_REPO", "your-org/ir-esg-reports")
                    base_path = f"{tenant or 'default'}/{ts}"
                    for p, name in [(html_out,"report.html"),(pdf_out,"report.pdf"),(docx_out,"report.docx"),(meta_out,"report.json")]:
                        api.upload_file(
                            path_or_fileobj=str(p),
                            path_in_repo=f"{base_path}/{name}",
                            repo_id=repo_id,
                            repo_type="dataset"
                        )
                except Exception as e:
                    meta_json["hub_error"] = str(e)
                    Path(meta_out).write_text(json.dumps(meta_json, ensure_ascii=False, indent=2), encoding="utf-8")

            return "生成が完了しました。", str(html_out), str(pdf_out), str(docx_out), str(meta_out), html_text

    except Exception as e:
        import traceback
        tb = traceback.format_exc(limit=20)
        return f"エラー: {e}\n--- trace ---\n{tb}", None, None, None, None, ""


with gr.Blocks(title=TITLE) as demo:
    gr.Markdown(f"# {TITLE}\n{DESC}")

    with gr.Row():
        company_yaml = gr.File(label="company.yaml（会社情報・年度等）", file_types=[".yaml", ".yml"])
        financials_csv = gr.File(label="financials.csv（財務KPI）", file_types=[".csv", ".xlsx"])
        esg_csv = gr.File(label="esg_metrics.csv（ESG指標）", file_types=[".csv", ".xlsx"])

    with gr.Row():
        use_llm = gr.Checkbox(label="LLMで要約/翻訳を行う（OPENAI_API_KEY2 必須）", value=True)
        lang = gr.Dropdown(choices=["ja","en","zh","ko","de","fr"], value="ja", label="出力言語")
        template_key = gr.Dropdown(choices=["base","tcfd","sasb","gri"], value="base", label="テンプレート")
        tenant = gr.Textbox(label="テナント名（会社識別子）", value="HitC")

    with gr.Row():
        glossary_yaml = gr.File(label="glossary.yaml（用語集・任意）", file_types=[".yaml", ".yml"])
        benchmarks_yaml = gr.File(label="benchmarks.yaml（業界平均など・任意）", file_types=[".yaml", ".yml"])
        past_reports_zip = gr.File(label="過去レポートZip（RAG用・任意）", file_types=[".zip"])
        push_to_hub = gr.Checkbox(label="生成物を Hugging Face Hub（Datasets）へ保存", value=False)

    run_btn = gr.Button("レポート生成")

    status = gr.Textbox(label="ステータス", interactive=False)
    html_file = gr.File(label="HTMLダウンロード")
    pdf_file = gr.File(label="PDFダウンロード")
    docx_file = gr.File(label="DOCXダウンロード")
    meta_file = gr.File(label="メタ情報(JSON)")
    html_preview = gr.HTML(label="HTMLプレビュー（抜粋）")

    run_btn.click(
        fn=run,
        inputs=[company_yaml, financials_csv, esg_csv, use_llm, lang, template_key, tenant, push_to_hub, glossary_yaml, benchmarks_yaml, past_reports_zip],
        outputs=[status, html_file, pdf_file, docx_file, meta_file, html_preview]
    )

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