#!/usr/bin/env python3
"""
完整报告生成脚本：Excel → 赋分 → 统计 → LLM并行生成 → HTML报告
"""
import sys
import time
import argparse
import logging
from pathlib import Path

sys.path.insert(0, str(Path(__file__).parent.parent / "backend"))

from app.engines.data_engine import DataEngine
from app.engines.scoring_engine import ScoringEngine
from app.engines.stats_engine import StatsEngine
from app.engines.llm_engine import LLMEngine
from app.engines.report_renderer import ReportRenderer

logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s [%(levelname)s] %(message)s",
    datefmt="%H:%M:%S",
)
logger = logging.getLogger(__name__)


def progress_callback(completed, total, segment_id):
    """进度回调"""
    pct = completed / total * 100
    bar = "█" * int(pct / 5) + "░" * (20 - int(pct / 5))
    print(f"\r  [{bar}] {pct:.0f}% ({completed}/{total}) {segment_id:<40}", end="", flush=True)


def main():
    parser = argparse.ArgumentParser(description="生成学校课程实施监测报告")
    parser.add_argument("--school", type=str, default="延安中学", help="学校名称")
    parser.add_argument("--no-cache", action="store_true", help="不使用LLM缓存")
    parser.add_argument("--no-llm", action="store_true", help="跳过LLM生成（仅图表+数据）")
    parser.add_argument("--list-schools", action="store_true", help="列出所有可用学校")
    args = parser.parse_args()

    start_time = time.time()

    # ===== Step 1: 加载数据 =====
    print("=" * 70)
    print("📊 课程实施监测报告生成系统")
    print("=" * 70)

    logger.info("[1/5] 加载Excel数据...")
    data_engine = DataEngine()
    data_engine.load_all()

    if args.list_schools:
        print("\n可用学校:")
        for s in data_engine.schools:
            from app.config import SCHOOL_TYPE_MAP
            info = SCHOOL_TYPE_MAP.get(s, {})
            print(f"  {s} ({info.get('type', '')})")
        return

    school = args.school
    if school not in data_engine.schools:
        print(f"\n❌ 学校 '{school}' 不在数据中。可用学校:")
        for s in data_engine.schools:
            print(f"  - {s}")
        return

    print(f"\n🏫 目标学校: {school}")

    # ===== Step 2: 赋分 =====
    logger.info("[2/5] 全区赋分计算...")
    scoring_engine = ScoringEngine(data_engine)
    raw_scores = scoring_engine.score_all_schools()

    # ===== Step 3: 统计分析 =====
    logger.info("[3/5] PCA合成 + 标准化 + 统计分析...")
    stats_engine = StatsEngine()
    sub_scores = stats_engine.compute_dimension_scores(raw_scores)
    dim_scores = stats_engine.compute_dimension_aggregates(sub_scores)
    report_data = stats_engine.compute_school_report_data(school, sub_scores, dim_scores)

    # ===== Step 4: LLM生成 =====
    if args.no_llm:
        logger.info("[4/5] 跳过LLM生成（--no-llm模式）")
        llm_sections = {}
    else:
        logger.info("[4/5] LLM并行生成报告文字...")
        llm_engine = LLMEngine()
        llm_engine.set_progress_callback(progress_callback)
        llm_sections = llm_engine.generate_report_segments(
            report_data,
            use_cache=not args.no_cache,
        )
        print()  # 换行

    # ===== Step 5: 渲染HTML =====
    logger.info("[5/5] 渲染HTML报告...")
    renderer = ReportRenderer()

    output_dir = Path(__file__).parent.parent / "output"
    output_dir.mkdir(parents=True, exist_ok=True)
    output_path = output_dir / f"{school}_报告.html"

    renderer.render_to_file(report_data, llm_sections, output_path)

    elapsed = time.time() - start_time

    print(f"\n{'=' * 70}")
    print(f"✅ 报告生成完成!")
    print(f"   学校: {school}")
    print(f"   总体得分: {report_data['overall']['score']}分 (区内第{report_data['overall']['rank_in_district']}名)")
    print(f"   LLM段落: {len(llm_sections)}个")
    print(f"   耗时: {elapsed:.1f}秒")
    print(f"   输出: {output_path}")
    print(f"{'=' * 70}")


if __name__ == "__main__":
    main()