WQ_GUI/src/new/services/step12_service.py

# -*- coding: utf-8 -*-
"""
Step12 后端计算服务（数据可视化——散点/光谱/箱线/掩膜缩略/采样地图）
================================================================

纯计算函数——绝对不引用 PyQt、绝对不引用 main_view。它只：

1. 从 ``config`` 字典读取 ``generate_*`` 5 个开关；
2. 按开关依次调用 ``src/core/visualization`` 或
   ``src/postprocessing.visualization_reports`` 中的独立生成函数；
3. 每个子任务独立 try/except 隔离，单个失败不影响其它；
4. 返回结果字典 ``{status, output_path, message, mode}``。

调用入口（由 main_view 在后台 QThread 中调用）：

    execute_step12({
        "work_dir": "D:/workspace",                  # 工作目录（必填）
        "img_dir": "D:/workspace/9_ML_Prediction",   # 图像目录（可省，自动推断）
        "generate_scatter": True,        # 模型评估散点图
        "generate_spectrum": True,       # 光谱曲线图
        "generate_boxplots": True,       # 箱线图
        "generate_glint_previews": True, # 掩膜/耀斑缩略图
        "generate_sampling_maps": True,  # 采样点地图
        "models_dir": "D:/8_Supervised_Model_Training",  # 散点图依赖（可省，自动推断）
        "training_csv_path": "D:/7_Water_Quality_Indices/training_with_indices.csv",  # 光谱/箱线依赖（可省，自动推断）
        "output_dir": "D:/14_visualization",  # 输出目录（可省 → work_dir/14_visualization）
        "enabled": True,
    })

返回字典字段：

* ``status``       : "completed" | "skipped" | "error"
* ``output_path``  : 输出目录路径（失败时为 None）
* ``message``      : 人类可读说明
* ``mode``         : "viz_generate"（便于 UI 提示）

设计取舍
--------
- 旧 panel 把所有图嵌入 matplotlib 画布；service 端只生成 PNG 文件，
  完全离线——view 层不再嵌入任何 chart widget。
- 单个可视化失败时 ``results[sub] = {"status": "error", ...}``，
  但外层 status 仍然 = "completed"（局部失败不等于全部失败）。
- 完全没有可用数据（连 work_dir 都不存在）时才返回 status="error"。
"""

from __future__ import annotations

from pathlib import Path
from typing import Any, Dict

from src.new.services._output_resolver import get_user_output_path, is_user_specified, resolve_output_dir


def _resolve_output_dir(config: Dict[str, Any], work_dir: str) -> tuple[Path, str]:
    """根据 output_dir / work_dir 计算可视化输出目录

    使用共享解析器强制执行"用户优先"规则——用户指定 output_dir 时直接用其值
    （step12 的 output_dir 本身就是一个目录），否则用 work_dir/14_visualization 默认。

    注意：step12 与其他步骤不同——output_dir 直接表示目录而非文件路径，
    所以使用 Path(user_path) 而非 .parent。
    """
    user_path = get_user_output_path(config, "output_dir", "output_path")
    if user_path:
        return Path(user_path), "user"
    return Path(work_dir) / "14_visualization", "default"


def _resolve_models_dir(work_dir: str, models_dir: str | None) -> str:
    """自动推断模型目录"""
    if models_dir and Path(models_dir).is_dir():
        return models_dir
    cand = Path(work_dir) / "8_Supervised_Model_Training"
    return str(cand) if cand.is_dir() else (models_dir or "")


def _resolve_training_csv(work_dir: str, training_csv_path: str | None) -> str:
    """自动推断训练 CSV"""
    if training_csv_path and Path(training_csv_path).is_file():
        return training_csv_path
    for sub in (
        "7_Water_Quality_Indices",
        "6_Spectral_Feature_Extraction",
        "4_processed_data",
        "visualization",
    ):
        d = Path(work_dir) / sub
        if not d.is_dir():
            continue
        cands = sorted(d.glob("*.csv"))
        if cands:
            return str(cands[0])
    return training_csv_path or ""


def _try_scatter(work_dir: str, output_dir: Path) -> Dict[str, Any]:
    """生成模型评估散点图（依赖 models_dir + training_csv_path）"""
    from src.core.visualization.scatter_plot import generate_model_scatter_plots

    models_dir = _resolve_models_dir(work_dir, None)
    training_csv = _resolve_training_csv(work_dir, None)
    if not models_dir or not Path(models_dir).is_dir():
        raise FileNotFoundError(f"模型目录不存在: {models_dir or '(自动推断失败)'}")
    if not training_csv or not Path(training_csv).is_file():
        raise FileNotFoundError(f"训练 CSV 不存在: {training_csv or '(自动推断失败)'}")

    out_sub = output_dir / "scatter_plots"
    paths = generate_model_scatter_plots(
        models_dir=models_dir,
        training_csv_path=training_csv,
        output_dir=str(out_sub),
    )
    return {"status": "completed", "count": len(paths), "output_dir": str(out_sub)}


def _try_spectrum(work_dir: str, output_dir: Path) -> Dict[str, Any]:
    """生成光谱曲线对比图（依赖 training CSV）"""
    from src.core.visualization.spectrum_plot import generate_spectrum_comparison_plots

    training_csv = _resolve_training_csv(work_dir, None)
    if not training_csv or not Path(training_csv).is_file():
        raise FileNotFoundError(f"训练 CSV 不存在: {training_csv or '(自动推断失败)'}")

    out_sub = output_dir / "spectrum_plots"
    paths = generate_spectrum_comparison_plots(
        csv_path=training_csv,
        output_dir=str(out_sub),
    )
    return {"status": "completed", "count": len(paths), "output_dir": str(out_sub)}


def _try_boxplots(work_dir: str, output_dir: Path) -> Dict[str, Any]:
    """生成水质参数箱型图（依赖 training CSV）"""
    from src.core.visualization.boxplot import generate_boxplots

    training_csv = _resolve_training_csv(work_dir, None)
    if not training_csv or not Path(training_csv).is_file():
        raise FileNotFoundError(f"训练 CSV 不存在: {training_csv or '(自动推断失败)'}")

    out_sub = output_dir / "boxplots"
    paths = generate_boxplots(
        csv_path=training_csv,
        output_dir=str(out_sub),
    )
    return {"status": "completed", "count": len(paths), "output_dir": str(out_sub)}


def _try_glint_previews(work_dir: str, output_dir: Path) -> Dict[str, Any]:
    """生成耀斑分析影像预览图"""
    from src.postprocessing.visualization_reports import ReportGenerator

    rg = ReportGenerator(output_dir=str(output_dir))
    paths = rg.generate_glint_deglint_previews(
        work_dir=work_dir,
        output_subdir="glint_deglint_previews",
        generate_glint=True,
        generate_deglint=True,
    )
    return {"status": "completed", "count": len(paths), "output_dir": str(output_dir / "glint_deglint_previews")}


def _try_sampling_maps(work_dir: str, output_dir: Path) -> Dict[str, Any]:
    """生成采样点地图"""
    from src.postprocessing.visualization_reports import ReportGenerator

    rg = ReportGenerator(output_dir=str(output_dir))
    p = rg.generate_sampling_point_map(output_subdir="sampling_maps")
    return {"status": "completed" if p else "error", "path": p, "output_dir": str(output_dir / "sampling_maps")}


def execute_step12(config: Dict[str, Any]) -> Dict[str, Any]:
    """Step 12 后端计算入口——纯函数"""
    work_dir: str = config.get("work_dir") or ""
    img_dir: str = config.get("img_dir") or ""
    enabled: bool = bool(config.get("enabled", True))
    output_dir: str = config.get("output_dir") or ""
    # 5 个开关：缺省默认 True（与旧 panel 行为一致）
    gen_scatter = bool(config.get("generate_scatter", True))
    gen_spectrum = bool(config.get("generate_spectrum", True))
    gen_boxplots = bool(config.get("generate_boxplots", True))
    gen_glint = bool(config.get("generate_glint_previews", True))
    gen_sampling = bool(config.get("generate_sampling_maps", True))

    output_path, _source = _resolve_output_dir(config, work_dir)
    mode = "viz_generate"

    # ---------- 提前失败检查 ----------
    if not enabled:
        return {
            "status": "skipped",
            "output_path": None,
            "message": "用户禁用此步骤（enabled=False）",
            "mode": mode,
        }
    if not work_dir:
        return {
            "status": "error",
            "output_path": None,
            "message": "未提供工作目录（work_dir）",
            "mode": mode,
        }
    if not Path(work_dir).is_dir():
        return {
            "status": "error",
            "output_path": None,
            "message": f"工作目录不存在: {work_dir}",
            "mode": mode,
        }

    output_path.mkdir(parents=True, exist_ok=True)
    # img_dir 仅作提示用，不强制校验
    _ = img_dir

    # ---------- 逐项执行（独立 try/except 隔离） ----------
    results: Dict[str, Dict[str, Any]] = {}
    n_ok = 0
    n_skip = 0
    n_err = 0

    tasks = []
    if gen_scatter:
        tasks.append(("scatter", _try_scatter))
    if gen_spectrum:
        tasks.append(("spectrum", _try_spectrum))
    if gen_boxplots:
        tasks.append(("boxplots", _try_boxplots))
    if gen_glint:
        tasks.append(("glint_previews", _try_glint_previews))
    if gen_sampling:
        tasks.append(("sampling_maps", _try_sampling_maps))

    if not tasks:
        return {
            "status": "completed",
            "output_path": str(output_path).replace("\\", "/"),
            "message": "无可视化任务（5 个开关全部 False）",
            "mode": mode,
        }

    print(f"[Step12 Service] 工作目录: {work_dir}")
    print(f"[Step12 Service] 输出目录: {output_path}")
    print(f"[Step12 Service] 子任务: {[n for n, _ in tasks]}")

    for name, fn in tasks:
        try:
            r = fn(work_dir, output_path)
            results[name] = r
            if r.get("status") == "completed":
                n_ok += 1
                print(f"  ✅ {name}: count={r.get('count', r.get('path', '?'))}")
            else:
                n_err += 1
                print(f"  ⚠ {name}: status={r.get('status')}")
        except FileNotFoundError as e:
            results[name] = {"status": "skipped", "reason": str(e)}
            n_skip += 1
            print(f"  ↻ {name}: 跳过（缺数据）: {e}")
        except Exception as e:  # noqa: BLE001
            results[name] = {"status": "error", "message": f"{type(e).__name__}: {e}"}
            n_err += 1
            print(f"  ❌ {name}: {type(e).__name__}: {e}")

    # ---------- 汇总 ----------
    # 局部失败不算全局失败——只有当所有任务都缺数据时才算 skipped
    if n_ok == 0 and n_err == 0:
        return {
            "status": "skipped",
            "output_path": None,
            "message": f"全部 {n_skip} 个子任务缺数据被跳过（models_dir/training_csv 等前置产物不存在）",
            "mode": mode,
        }

    return {
        "status": "completed",
        "output_path": str(output_path).replace("\\", "/"),
        "message": (
            f"可视化完成：成功 {n_ok} / 失败 {n_err} / 跳过 {n_skip}；"
            f"目录: {output_path.name or output_path}"
        ),
        "mode": mode,
    }