"""Path-first unified CLI: one file or one directory, routed by suffix."""

from __future__ import annotations

import argparse
import sys
from pathlib import Path

from .commands import run_input, run_verify
from .logging_utils import default_log_path, setup_run_logger
from .runtime import PipelineProvider, RuntimeConfig

PROJECT_ROOT = Path(__file__).resolve().parent.parent
LEGACY_COMMANDS = {"image", "pdf", "batch"}


def _add_device_options(parser: argparse.ArgumentParser, default: str | None) -> None:
    parser.add_argument("--device", choices=("cpu", "gpu"), default=default or "cpu", help="运行设备")
    parser.add_argument("--device-id", type=int, default=0, help="GPU 编号")
    parser.add_argument("--threads", type=int, default=None, help="CPU 线程数")
    parser.add_argument("--log-file", type=Path, default=None, help="日志文件路径")
    parser.add_argument("--verbose", action="store_true", help="输出详细日志")


def build_input_parser(device_override: str | None = None) -> argparse.ArgumentParser:
    parser = argparse.ArgumentParser(
        prog="ocr.py",
        description="自动按文件后缀处理图片/PDF；输入目录时批量使用同一路由逻辑",
        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
    )
    parser.add_argument("input", type=Path, help="图片、PDF 或目录")
    parser.add_argument("--recursive", action="store_true", help="目录模式递归扫描子目录")
    parser.add_argument("--output", type=Path, default=PROJECT_ROOT / "outputs", help="PDF 输出根目录")
    parser.add_argument("--fail-fast", action="store_true", help="单文件失败后立即停止目录任务")

    # Image options
    parser.add_argument("--warmup", type=int, default=0, help="首张图片预热轮数")
    parser.add_argument("--rounds", type=int, default=1, help="每张图片推理轮数")
    parser.add_argument("--benchmark-json", type=Path, default=None, help="单图片 Benchmark JSON 路径")
    parser.add_argument("--no-result", action="store_true", help="不记录图片 OCR 文本块")

    # PDF options
    parser.add_argument(
        "--pdf-mode",
        "--mode",
        dest="pdf_mode",
        choices=("hybrid", "text", "ocr"),
        default="hybrid",
        help="PDF 处理模式",
    )
    parser.add_argument("--pages", help="PDF 页码范围，例如 1-5,8,10-")
    parser.add_argument("--dpi", type=int, default=144, help="PDF OCR 页面渲染 DPI")
    parser.add_argument("--password", help="PDF 密码")
    parser.add_argument("--resume", action="store_true", help="PDF 断点续传")
    parser.add_argument("--overwrite", action="store_true", help="覆盖已有 PDF 输出")
    parser.add_argument("--keep-rendered", action="store_true", help="保留 OCR 页面 PNG")
    parser.add_argument("--max-new-tokens", type=int, default=None, help="VLM 最大生成 token")
    parser.add_argument("--min-pixels", type=int, default=None, help="VLM 最小输入像素")
    parser.add_argument("--max-pixels", type=int, default=None, help="VLM 最大输入像素")
    parser.add_argument("--text-min-chars", type=int, default=50, help="有效文本最小字符数")
    parser.add_argument("--text-min-printable-ratio", type=float, default=0.85, help="可打印字符比例阈值")
    parser.add_argument("--text-min-content-ratio", type=float, default=0.60, help="字母/数字/CJK 比例阈值")
    parser.add_argument("--text-max-replacement-ratio", type=float, default=0.02, help="替换字符最大比例")
    parser.add_argument("--text-min-density", type=float, default=25.0, help="文本密度阈值")
    _add_device_options(parser, device_override)
    return parser


def build_verify_parser(device_override: str | None = None) -> argparse.ArgumentParser:
    parser = argparse.ArgumentParser(
        prog="ocr.py verify",
        description="验证 CPU/GPU Paddle 环境",
        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
    )
    _add_device_options(parser, device_override)
    return parser


def normalize_argv(argv: list[str]) -> tuple[str, list[str]]:
    """Keep old image/pdf/batch prefixes as compatibility aliases."""
    if argv and argv[0] == "verify":
        return "verify", argv[1:]
    if argv and argv[0] in LEGACY_COMMANDS:
        return "input", argv[1:]
    return "input", argv


def main(device: str | None = None, argv: list[str] | None = None) -> int:
    raw_argv = list(sys.argv[1:] if argv is None else argv)
    command, normalized = normalize_argv(raw_argv)
    parser = build_verify_parser(device) if command == "verify" else build_input_parser(device)
    args = parser.parse_args(normalized)
    if device is not None:
        args.device = device

    if command == "verify":
        stem = "verify"
        category = "verify"
    else:
        stem = args.input.stem or args.input.name or "input"
        category = "input"
    log_file = args.log_file or default_log_path(PROJECT_ROOT, category, stem, device=args.device)
    logger = setup_run_logger(f"ocr.{category}.{args.device}", log_file, verbose=args.verbose)
    logger.info(
        "COMMAND_STARTED command=%s input=%s device=%s log=%s",
        command,
        getattr(args, "input", None),
        args.device,
        log_file,
    )

    provider = PipelineProvider(
        RuntimeConfig(device=args.device, threads=args.threads, device_id=args.device_id),
        logger,
    )
    try:
        if command == "verify":
            return run_verify(args, provider, logger, PROJECT_ROOT)
        if args.warmup < 0 or args.rounds < 1:
            raise ValueError("--warmup 必须 >= 0，--rounds 必须 >= 1")
        return run_input(args, provider, logger, PROJECT_ROOT)
    except Exception as exc:
        logger.exception("COMMAND_FAILED command=%s error=%s", command, exc)
        return 1