ken_nogi/PythonProj/ScanOCR/build/build_package.py

# -*- coding: utf-8 -*-
"""
配布パッケージ生成スクリプト。

開発者PC上で1回実行すると、dist/ScanOCR/ 配下に
Python embeddable版・依存pipパッケージ・tesseract-ocr・poppler一式を含む
配布用フォルダを生成する。

前提:
  - ネットワーク接続必須
  - 7-Zip（7zコマンド）がPATHに通っていること（tesseractインストーラー展開用）

使い方:
    python build/build_package.py
"""
from __future__ import annotations

import shutil
import subprocess
import tempfile
import urllib.request
import zipfile
from pathlib import Path

REPO_ROOT = Path(__file__).resolve().parent.parent
DIST_DIR = REPO_ROOT / "dist" / "ScanOCR"

PYTHON_VERSION = "3.11.9"
PYTHON_EMBED_URL = (
    f"https://www.python.org/ftp/python/{PYTHON_VERSION}/"
    f"python-{PYTHON_VERSION}-embed-amd64.zip"
)
GET_PIP_URL = "https://bootstrap.pypa.io/get-pip.py"
PIP_PACKAGES = ["opencv-python", "pdf2image", "pytesseract", "pillow", "numpy"]

TESSERACT_VERSION = "5.4.0.20240606"
TESSERACT_INSTALLER_URL = (
    "https://github.com/UB-Mannheim/tesseract/releases/download/"
    f"v{TESSERACT_VERSION}/tesseract-ocr-w64-setup-{TESSERACT_VERSION}.exe"
)

POPPLER_VERSION = "24.02.0-0"
POPPLER_ZIP_URL = (
    "https://github.com/oschwartz10612/poppler-windows/releases/download/"
    f"v{POPPLER_VERSION}/Release-{POPPLER_VERSION}.zip"
)

CODE_FILES = (
    "extract_and_rename.py",
    "box_detector.py",
    "config_loader.py",
    "file_ops.py",
    "lock_manager.py",
    "logger.py",
)

RUNTIME_FOLDERS = ("テンプレート", "スキャン", "アウトプット", "成功", "失敗", "ログ")


def download(url: str, dest: Path) -> None:
    print(f"ダウンロード: {url}")
    urllib.request.urlretrieve(url, dest)


def prepare_dist_dir() -> None:
    if DIST_DIR.exists():
        shutil.rmtree(DIST_DIR)
    DIST_DIR.mkdir(parents=True)


def copy_code_files() -> Path:
    script_dst = DIST_DIR / "スクリプト"
    script_dst.mkdir(parents=True)
    for name in CODE_FILES:
        shutil.copy2(REPO_ROOT / "スクリプト" / name, script_dst / name)
    shutil.copy2(REPO_ROOT / "OCR仕分け実行.bat", DIST_DIR / "OCR仕分け実行.bat")
    shutil.copy2(REPO_ROOT / "config.txt", DIST_DIR / "config.txt")
    return script_dst


def setup_python(script_dst: Path, tmp_dir: Path) -> None:
    python_dir = script_dst / "python"
    python_dir.mkdir(parents=True)

    zip_path = tmp_dir / "python-embed.zip"
    download(PYTHON_EMBED_URL, zip_path)
    with zipfile.ZipFile(zip_path) as zf:
        zf.extractall(python_dir)

    pth_files = list(python_dir.glob("python*._pth"))
    if not pth_files:
        raise RuntimeError("python*._pth が見つかりません（embeddable zipの構成が変わった可能性）")
    pth_path = pth_files[0]
    content = pth_path.read_text(encoding="utf-8")
    content = content.replace("#import site", "import site")
    pth_path.write_text(content, encoding="utf-8")

    get_pip_path = tmp_dir / "get-pip.py"
    download(GET_PIP_URL, get_pip_path)
    python_exe = python_dir / "python.exe"
    subprocess.run([str(python_exe), str(get_pip_path)], check=True)
    subprocess.run(
        [str(python_exe), "-m", "pip", "install", *PIP_PACKAGES],
        check=True,
    )


SEVEN_ZIP_FALLBACK_PATHS = (
    r"C:\Program Files\7-Zip\7z.exe",
    r"C:\Program Files (x86)\7-Zip\7z.exe",
)


def find_7zip_exe() -> str:
    found = shutil.which("7z")
    if found:
        return found
    for candidate in SEVEN_ZIP_FALLBACK_PATHS:
        if Path(candidate).exists():
            return candidate
    raise RuntimeError(
        "7-Zip（7z.exe）が見つかりません。PATHに通すか、標準的な場所にインストールしてください。"
    )


def setup_tesseract(script_dst: Path, tmp_dir: Path) -> None:
    tools_dst = script_dst / "tools" / "tesseract"
    tools_dst.mkdir(parents=True)

    installer_path = tmp_dir / "tesseract-setup.exe"
    download(TESSERACT_INSTALLER_URL, installer_path)

    seven_zip_exe = find_7zip_exe()
    extract_dir = tmp_dir / "tesseract-extract"
    extract_dir.mkdir()
    subprocess.run(
        [seven_zip_exe, "x", str(installer_path), f"-o{extract_dir}", "-y"],
        check=True,
    )
    for item in extract_dir.iterdir():
        shutil.move(str(item), str(tools_dst / item.name))


def setup_poppler(script_dst: Path, tmp_dir: Path) -> None:
    tools_parent = script_dst / "tools"
    tools_parent.mkdir(parents=True, exist_ok=True)
    tools_dst = tools_parent / "poppler"

    zip_path = tmp_dir / "poppler.zip"
    download(POPPLER_ZIP_URL, zip_path)
    extract_dir = tmp_dir / "poppler-extract"
    with zipfile.ZipFile(zip_path) as zf:
        zf.extractall(extract_dir)

    inner_items = list(extract_dir.iterdir())
    source_dir = inner_items[0] if len(inner_items) == 1 else extract_dir
    shutil.move(str(source_dir), str(tools_dst))


def create_runtime_folders() -> None:
    for name in RUNTIME_FOLDERS:
        (DIST_DIR / name).mkdir(parents=True, exist_ok=True)


def main() -> None:
    prepare_dist_dir()
    script_dst = copy_code_files()

    with tempfile.TemporaryDirectory() as tmp:
        tmp_dir = Path(tmp)
        setup_python(script_dst, tmp_dir)
        setup_tesseract(script_dst, tmp_dir)
        setup_poppler(script_dst, tmp_dir)

    create_runtime_folders()
    print(f"配布パッケージ生成完了: {DIST_DIR}")


if __name__ == "__main__":
    main()