#!/usr/bin/env python3
"""
自动将 comparison_report.json 转换为中文 Markdown 评测报告。

用法:
    python generate_comparison_report.py <comparison_report.json 路径>
    python generate_comparison_report.py <comparison_report.json 路径> --output <输出文件路径>
    python generate_comparison_report.py <comparison_report.json 路径> --title "自定义标题"
    python generate_comparison_report.py <comparison_report.json 路径> --background "背景说明文字"
    python generate_comparison_report.py <comparison_report.json 路径> --date 2026-03-01

示例:
    python generate_comparison_report.py \
        evaluation_results/eval_results_common_match_comparison_cncap_yolov5s_20260228_roi0/comparison_common_matches_20260228_102849/comparison_report.json

    python generate_comparison_report.py \
        evaluation_results/.../comparison_report.json \
        --output my_report.md \
        --title "ROI1 模型对比报告"
"""

import json
import re
import argparse
import sys
from datetime import date
from pathlib import Path

# Allow importing class_config from the eval_tools root
sys.path.insert(0, str(Path(__file__).parent.parent))
from class_config import REPORT_3D_CLASS_LABELS

# ── 阈值设置 ─────────────────────────────────────────────────────────────────
# AP 差异超过此阈值才标记为"优"，否则标记为"持平"
AP_TIE_THRESHOLD = 0.005       # 0.5%
METRIC_TIE_THRESHOLD = 0.005   # 用于 precision/recall/f1 的判断阈值（绝对值）
ERROR_TIE_THRESHOLD_REL = 2.0  # 3D 误差相对变化（%）小于此值视为持平


def fmt(v: float, decimals: int = 4) -> str:
    return f"{v:.{decimals}f}"


def fmt_pct(v: float) -> str:
    sign = "+" if v >= 0 else ""
    return f"{sign}{v:.2f}%"


def fmt_diff(v: float) -> str:
    sign = "+" if v >= 0 else ""
    return f"{sign}{v:.4f}"


def judge(diff: float, rel: float, higher_is_better: bool = True,
          abs_thr: float = AP_TIE_THRESHOLD, rel_thr: float = None,
          model1_name: str = "model1", model2_name: str = "model2") -> str:
    """
    根据 diff (model2 - model1) 判断哪个模型更好。
    higher_is_better=True  → diff>0 代表 model2 更好
    higher_is_better=False → diff<0 代表 model2 更好（即误差更小）
    """
    if rel_thr is not None:
        tie = abs(rel) < rel_thr
    else:
        tie = abs(diff) < abs_thr

    if tie:
        return "⚖️ 持平"

    m2_better = (diff > 0) if higher_is_better else (diff < 0)
    m2_short = model2_name.split("-")[-1]   # e.g. "cncap"
    m1_short = model1_name.split("-")[-1]   # e.g. "newdata", "mono3d"
    if m2_better:
        return f"✅ {m2_short}优"
    else:
        return f"✅ {m1_short}优"


def build_report(data: dict, model1: str, model2: str,
                 report_date: str, title: str = None, background: str = None) -> str:
    """生成完整 Markdown 报告字符串。"""

    m2d = data["2d_metrics"]
    m3d = data.get("3d_metrics", {})
    stats = data.get("match_statistics", {})
    summary = data.get("summary", {})

    # ── 名称简写 ──────────────────────────────────────────────────────────────
    m1_short = model1
    m2_short = model2
    # 取最后一段作为简称用于表格
    m1_tag = model1.split("-")[-1]    # e.g. "newdata"
    m2_tag = model2.split("-")[-1]    # e.g. "cncap"

    lines = []

    # ── 标题 ─────────────────────────────────────────────────────────────────
    auto_title = title or f"模型对比Overall指标总结 ({model1} vs {model2} - 通用数据集评测)"
    lines.append(f"# {auto_title}")
    lines.append("")
    lines.append(f"**对比模型**: {model1} vs {model2}  ")
    lines.append(f"**评测日期**: {report_date}  ")
    lines.append(f"**数据集**: 通用数据集 (Common Match Cases)  ")

    total_common = stats.get("common", None)
    m1_total = stats.get("model1_total", None)
    m2_total = stats.get("model2_total", None)
    if total_common is not None and m1_total is not None and m2_total is not None:
        lines.append(f"**匹配样本**: {total_common:,} ({model1}: {m1_total:,} | {model2}: {m2_total:,})")
    else:
        lines.append(f"**匹配样本**: N/A")
    lines.append("")

    if background:
        lines.append(f"> **背景说明**: {background}")
    else:
        lines.append(f"> **背景说明**: 本次评测对比了 {model1} 与 {model2}，评估两者在通用数据集上的2D/3D检测性能差异。")
    lines.append("")
    lines.append("---")
    lines.append("")

    # ── 2D Overall ────────────────────────────────────────────────────────────
    ov = m2d["overall"]
    lines.append("## 📊 2D检测指标 (Overall)")
    lines.append("")
    lines.append("### 总体性能对比")
    lines.append("")
    lines.append(f"| 指标 | {model1} | {model2} | 差异 | 相对变化 | 结果 |")
    lines.append("|------|" + "---|" * 5)

    def ov_row(key, label, higher_is_better=True):
        v1 = ov[key][model1]
        v2 = ov[key][model2]
        diff = ov[key]["diff"]
        rel = ov[key]["relative_change_%"]
        j = judge(diff, rel, higher_is_better, abs_thr=METRIC_TIE_THRESHOLD,
                  model1_name=model1, model2_name=model2)
        return f"| **{label}** | {fmt(v1)} | {fmt(v2)} | {fmt_diff(diff)} | {fmt_pct(rel)} | {j} |"

    lines.append(ov_row("precision", "PRECISION"))
    lines.append(ov_row("recall", "RECALL"))
    lines.append(ov_row("f1_score", "F1-Score"))
    lines.append(ov_row("map", "mAP"))
    lines.append("")

    # 关键发现
    prec_diff = ov["precision"]["relative_change_%"]
    rec_diff = ov["recall"]["relative_change_%"]
    map_diff = ov["map"]["relative_change_%"]
    f1_diff = ov["f1_score"]["relative_change_%"]

    ap_wins = summary.get("2d", {}).get("ap", {}).get("wins", "?")
    ap_losses = summary.get("2d", {}).get("ap", {}).get("losses", "?")
    ap_ties = summary.get("2d", {}).get("ap", {}).get("ties", "?")

    lines.append("### 关键发现")
    lines.append("")
    lines.append(f"- 📊 **Precision**: {model2}{'领先' if prec_diff > 0 else '落后'}{fmt_pct(abs(prec_diff))}，{'误检率略低' if prec_diff > 0 else '误检率略高'}")
    lines.append(f"- 📊 **Recall**: {model1 if rec_diff < 0 else model2}领先{fmt_pct(abs(rec_diff))}，检出率{'更高' if rec_diff < 0 else '更低'}")
    lines.append(f"- 📊 **mAP**: {model2 if map_diff > 0 else model1}领先{fmt_pct(abs(map_diff))}（{'极小差异，基本持平' if abs(map_diff) < 2 else '有一定差距'}）")
    lines.append(f"- 📊 **F1-Score**: {'两模型基本持平' if abs(f1_diff) < 1 else (model2 + '更优' if f1_diff > 0 else model1 + '更优')}（差距{fmt_pct(abs(f1_diff))}）")
    lines.append(f"- ⚖️ **类别赢负统计 (AP)**: {m2_tag}赢{ap_wins}类, {m1_tag}赢{ap_losses}类, 平局{ap_ties}类")
    lines.append("")

    lines.append("---")
    lines.append("")

    # ── 2D Per-Class ──────────────────────────────────────────────────────────
    pc = m2d.get("per_class", {})
    lines.append("## 📋 2D检测指标 (Per Class)")
    lines.append("")
    lines.append("### 各类别性能对比")
    lines.append("")
    lines.append(f"| 类别 | Precision ({m1_tag}) | Precision ({m2_tag}) | Recall ({m1_tag}) | Recall ({m2_tag}) | F1 ({m1_tag}) | F1 ({m2_tag}) | AP ({m1_tag}) | AP ({m2_tag}) | AP差异 | 结果 |")
    lines.append("|------|" + "---|" * 10)

    adv_m2 = []   # model2 明显更好的类别
    adv_m1 = []   # model1 明显更好的类别

    for cls, cd in pc.items():
        prec1 = cd["precision"][model1]
        prec2 = cd["precision"][model2]
        rec1  = cd["recall"][model1]
        rec2  = cd["recall"][model2]
        f1_1  = cd["f1_score"][model1]
        f1_2  = cd["f1_score"][model2]
        ap1   = cd["ap"][model1]
        ap2   = cd["ap"][model2]
        ap_d  = cd["ap"]["diff"]
        ap_r  = cd["ap"]["relative_change_%"]
        j = judge(ap_d, ap_r, True, abs_thr=AP_TIE_THRESHOLD,
                  model1_name=model1, model2_name=model2)
        lines.append(
            f"| **{cls}** | {fmt(prec1)} | {fmt(prec2)} | {fmt(rec1)} | {fmt(rec2)} "
            f"| {fmt(f1_1)} | {fmt(f1_2)} | {fmt(ap1)} | {fmt(ap2)} | {fmt_diff(ap_d)} | {j} |"
        )
        if abs(ap_r) >= 2.0:   # 相对变化>=2%才算显著
            if ap_d > 0:
                adv_m2.append((cls, ap1, ap2, ap_r))
            elif ap_d < 0:
                adv_m1.append((cls, ap1, ap2, ap_r))

    lines.append("")
    lines.append("### 类别分析")
    lines.append("")

    if adv_m2:
        lines.append(f"**{model2} 优势类别** (AP更高):")
        for cls, ap1, ap2, rel in sorted(adv_m2, key=lambda x: -x[3]):
            mark = "**大幅领先**" if rel > 8 else "领先"
            lines.append(f"- {cls}: {m2_tag} {fmt(ap2)} > {m1_tag} {fmt(ap1)}（{mark}{fmt_pct(rel)}）")
        lines.append("")

    if adv_m1:
        lines.append(f"**{model1} 优势类别** (AP更高):")
        for cls, ap1, ap2, rel in sorted(adv_m1, key=lambda x: x[3]):
            mark = "**大幅领先**" if abs(rel) > 8 else "领先"
            lines.append(f"- {cls}: {m1_tag} {fmt(ap1)} > {m2_tag} {fmt(ap2)}（{mark}{fmt_pct(abs(rel))}）")
        lines.append("")

    lines.append("---")
    lines.append("")

    # ── 3D Metrics ────────────────────────────────────────────────────────────
    if m3d:
        lines.append("## 🎯 3D检测指标")
        lines.append("")

        cls_labels = REPORT_3D_CLASS_LABELS

        for cls_key, cls_label in cls_labels.items():
            if cls_key not in m3d:
                continue
            cd = m3d[cls_key]
            ov3 = cd.get("overall", {})
            if not ov3:
                continue
            n = cd.get("common_samples")
            n_str = f"{n:,} 个样本" if n is not None else "N/A 个样本"

            lines.append(f"### {cls_label} - {n_str}")
            lines.append("")
            lines.append(f"| 指标 | {model1} | {model2} | 差异 | 相对变化 | 结果 |")
            lines.append("|------|" + "---|" * 5)

            def row3d(key, label, higher_is_better=False):
                if key not in ov3:
                    return None
                v1 = ov3[key][model1]["mean"]
                v2 = ov3[key][model2]["mean"]
                diff = ov3[key]["diff"]
                rel = ov3[key]["relative_change_%"]
                j = judge(diff, rel, higher_is_better,
                          rel_thr=ERROR_TIE_THRESHOLD_REL,
                          model1_name=model1, model2_name=model2)
                return f"| **{label}** | {fmt(v1)} | {fmt(v2)} | {fmt_diff(diff)} | {fmt_pct(rel)} | {j} |"

            for row in [
                row3d("lateral_error",               "Lateral Error"),
                row3d("longitudinal_error",           "Longitudinal Error"),
                row3d("longitudinal_relative_error",  "Longitudinal Relative Error"),
                row3d("heading_error",                "Heading Error"),
                row3d("heading_error_relaxed",        "Heading Error Relaxed"),
            ]:
                if row is not None:
                    lines.append(row)

            if "reversal_info" in ov3:
                rev1 = ov3["reversal_info"][model1]
                rev2 = ov3["reversal_info"][model2]
                rev_j = "✅ " + (m2_tag if rev2["percentage"] < rev1["percentage"] else m1_tag) + "优"
                if abs(rev1["percentage"] - rev2["percentage"]) < 0.5:
                    rev_j = "⚖️ 持平"
                lines.append(
                    f"| **Reversal Cases** | {rev1['count']:,} ({rev1['percentage']:.2f}%) "
                    f"| {rev2['count']:,} ({rev2['percentage']:.2f}%) | - | - | {rev_j} |"
                )
            lines.append("")

            # ── 纵向区间对比 ──────────────────────────────────────────────
            def _long_sort_key(k):
                stripped = k[len("long_"):].replace("m", "")
                m = re.search(r'(?<=\d)-', stripped)
                if m:
                    try:
                        return float(stripped[:m.start()])
                    except ValueError:
                        pass
                return float('inf')

            long_keys = sorted(
                [k for k in cd.keys() if k.startswith("long_")],
                key=_long_sort_key
            )
            if long_keys:
                lines.append(f"#### 纵向区间对比")
                lines.append("")
                lines.append(
                    f"| 区间 | 样本数 "
                    f"| Lat ({m1_tag}) | Lat ({m2_tag}) | Lat Δ% "
                    f"| Long ({m1_tag}) | Long ({m2_tag}) | Long Δ% "
                    f"| LongRel ({m1_tag}) | LongRel ({m2_tag}) | LongRel Δ% "
                    f"| Head ({m1_tag}) | Head ({m2_tag}) | Head Δ% |"
                )
                lines.append("|------|" + "---|" * 13)
                for rk in long_keys:
                    rb = cd[rk]
                    if not rb:
                        continue

                    def _rv(metric, model):
                        d = rb.get(metric, {})
                        if model in d:
                            return fmt(d[model]["mean"])
                        return "-"

                    def _rd(metric):
                        d = rb.get(metric, {})
                        rel = d.get("relative_change_%")
                        if rel is None:
                            return "-"
                        return fmt_pct(rel)

                    # sample count from any available metric
                    n_range = "-"
                    for _mk in ("lateral_error", "longitudinal_error", "heading_error"):
                        _md = rb.get(_mk, {})
                        if model1 in _md and "samples" in _md[model1]:
                            n_range = f"{_md[model1]['samples']:,}"
                            break

                    # range label: strip prefix and trailing 'm'
                    rl = rk[len("long_"):]

                    lines.append(
                        f"| **{rl}** | {n_range} "
                        f"| {_rv('lateral_error', model1)} | {_rv('lateral_error', model2)} | {_rd('lateral_error')} "
                        f"| {_rv('longitudinal_error', model1)} | {_rv('longitudinal_error', model2)} | {_rd('longitudinal_error')} "
                        f"| {_rv('longitudinal_relative_error', model1)} | {_rv('longitudinal_relative_error', model2)} | {_rd('longitudinal_relative_error')} "
                        f"| {_rv('heading_error', model1)} | {_rv('heading_error', model2)} | {_rd('heading_error')} |"
                    )
                lines.append("")

        lines.append("---")
        lines.append("")

    # ── Match Statistics ──────────────────────────────────────────────────────
    if stats:
        lines.append("## 📊 样本匹配统计")
        lines.append("")
        lines.append("### 整体匹配情况")
        lines.append("")
        lines.append("| 模型 | 总样本数 | 公共样本 | 独有样本 | 公共占比 |")
        lines.append("|------|----------|----------|----------|---------|")
        m1_pct = stats.get("common_percentage_of_model1", 0)
        m2_pct = stats.get("common_percentage_of_model2", 0)
        m1_uniq = stats.get("model1_unique", 0)
        m2_uniq = stats.get("model2_unique", 0)
        lines.append(f"| **{model1}** | {m1_total:,} | {total_common:,} | {m1_uniq:,} | {m1_pct:.2f}% |")
        lines.append(f"| **{model2}** | {m2_total:,} | {total_common:,} | {m2_uniq:,} | {m2_pct:.2f}% |")
        lines.append("")

        per_cls_stats = stats.get("per_class", {})
        if per_cls_stats:
            lines.append("### 各类别匹配情况 (3D)")
            lines.append("")
            lines.append(f"| 类别 | {m1_tag}总数 | {m2_tag}总数 | 公共样本 | {m1_tag}占比 | {m2_tag}占比 |")
            lines.append("|------|" + "---|" * 5)
            for cls, cs in per_cls_stats.items():
                lines.append(
                    f"| **{cls}** | {cs['model1_total']:,} | {cs['model2_total']:,} "
                    f"| {cs['common']:,} | {cs['common_percentage_of_model1']:.2f}% "
                    f"| {cs['common_percentage_of_model2']:.2f}% |"
                )
            lines.append("")

        lines.append("---")
        lines.append("")

    # ── Summary / Conclusions ─────────────────────────────────────────────────
    lines.append("## 🎯 结论与建议")
    lines.append("")
    lines.append("### 2D检测汇总")
    lines.append("")

    sum2d = summary.get("2d", {})
    ap_w = sum2d.get("ap", {}).get("wins", 0)
    ap_l = sum2d.get("ap", {}).get("losses", 0)
    ap_t = sum2d.get("ap", {}).get("ties", 0)
    f1_w = sum2d.get("f1_score", {}).get("wins", 0)
    f1_l = sum2d.get("f1_score", {}).get("losses", 0)
    f1_t = sum2d.get("f1_score", {}).get("ties", 0)

    lines.append(f"- **AP 类别统计**: {m2_tag}赢{ap_w}类 / {m1_tag}赢{ap_l}类 / 平局{ap_t}类")
    lines.append(f"- **F1 类别统计**: {m2_tag}赢{f1_w}类 / {m1_tag}赢{f1_l}类 / 平局{f1_t}类")
    lines.append(f"- **整体mAP**: {model1}={fmt(ov['map'][model1])} vs {model2}={fmt(ov['map'][model2])} ({fmt_pct(ov['map']['relative_change_%'])})")
    lines.append("")

    if m3d:
        sum3d = summary.get("3d", {})
        lat_w = sum3d.get("lateral", {}).get("wins", 0)
        lat_l = sum3d.get("lateral", {}).get("losses", 0)
        lon_w = sum3d.get("longitudinal", {}).get("wins", 0)
        lon_l = sum3d.get("longitudinal", {}).get("losses", 0)
        hd_w  = sum3d.get("heading", {}).get("wins", 0)
        hd_l  = sum3d.get("heading", {}).get("losses", 0)

        lines.append("### 3D检测汇总")
        lines.append("")
        lines.append(f"- **横向误差 (Lateral)**: {m2_tag}优{lat_w}类 / {m1_tag}优{lat_l}类")
        lines.append(f"- **纵向误差 (Longitudinal)**: {m2_tag}优{lon_w}类 / {m1_tag}优{lon_l}类")
        lines.append(f"- **航向误差 (Heading)**: {m2_tag}优{hd_w}类 / {m1_tag}优{hd_l}类")
        lines.append("")

    lines.append("### 综合建议")
    lines.append("")
    # 自动判断整体赢家
    map_rel = ov["map"]["relative_change_%"]
    if map_rel > 2:
        overall_winner = model2
    elif map_rel < -2:
        overall_winner = model1
    else:
        overall_winner = None

    if overall_winner:
        lines.append(f"- 🏆 **综合mAP**: {overall_winner} 整体占优（{fmt_pct(abs(map_rel))}）")
    else:
        lines.append(f"- ⚖️ **综合mAP**: 两模型基本持平（差距{fmt_pct(abs(map_rel))}）")

    adv_summary_m2 = [(c, r) for c, *_, r in adv_m2]
    adv_summary_m1 = [(c, r) for c, *_, r in adv_m1]
    if adv_summary_m2:
        cls_str = "、".join(c for c, _ in adv_summary_m2)
        lines.append(f"- ✅ **{model2} 改善**: {cls_str} 类别AP有所提升")
    if adv_summary_m1:
        cls_str = "、".join(c for c, _ in adv_summary_m1)
        lines.append(f"- ⚠️ **{model2} 退化**: {cls_str} 类别AP有所下降")

    lines.append("")

    return "\n".join(lines)


def main():
    parser = argparse.ArgumentParser(
        description="将 comparison_report.json 转换为中文 Markdown 评测报告"
    )
    parser.add_argument("json_path", help="comparison_report.json 的路径")
    parser.add_argument("--output", "-o", default=None,
                        help="输出 Markdown 文件路径（默认与 JSON 同目录，文件名 COMPARISON_REPORT.md）")
    parser.add_argument("--title", default=None,
                        help="自定义报告标题")
    parser.add_argument("--background", default=None,
                        help="背景说明文字")
    parser.add_argument("--date", default=str(date.today()),
                        help="评测日期 (默认今天，格式 YYYY-MM-DD)")
    args = parser.parse_args()

    json_path = Path(args.json_path)
    if not json_path.exists():
        print(f"错误: 文件不存在: {json_path}", file=sys.stderr)
        sys.exit(1)

    with open(json_path, "r", encoding="utf-8") as f:
        data = json.load(f)

    # 自动从 JSON 中读取模型名称
    models = list(data["2d_metrics"]["overall"]["precision"].keys())
    # 过滤掉 diff / relative_change_% 等非模型 key
    skip = {"diff", "relative_change_%"}
    models = [m for m in models if m not in skip]
    if len(models) < 2:
        print("错误: 无法从 JSON 中自动识别模型名称，请检查文件格式。", file=sys.stderr)
        sys.exit(1)
    model1, model2 = models[0], models[1]
    print(f"模型1: {model1}")
    print(f"模型2: {model2}")

    report = build_report(data, model1, model2,
                          report_date=args.date,
                          title=args.title,
                          background=args.background)

    # 输出路径
    if args.output:
        out_path = Path(args.output)
    else:
        out_path = json_path.parent / "COMPARISON_REPORT.md"

    out_path.write_text(report, encoding="utf-8")
    print(f"报告已生成: {out_path}")


if __name__ == "__main__":
    main()