feat: 数据源统一与前端预览修复

=== 后端核心 ===
- db_helper: 统一数据库访问抽象层
- system.py API:
  * 参数绑定修复: 使用 Body(embed=True) 接收 JSON
  * 添加请求日志记录
- sync.py: 仅导出 DB→JSON（备份）

=== 合规与流水线 ===
- compliance_checker: 标签检测优化（仅检查容器，避免正文误判）
- 所有脚本（creator/collector/writer/outline/research等）统一使用数据库

=== 前端改版 ===
- topics.html:
  * 创作/优化 API 路径修正
  * 预览弹窗重设计：多平台并行加载、富文本显示、单复制按钮
  * 状态中文映射（getStatusLabel）
  * 认证检查
- 所有 HTML 静态资源路径修复（移除 /static 前缀）

=== 数据一致性 ===
- 数据库状态统一为英文（pending/review/ready/published）
- 前端显示中文化映射

已测试 A03 流水线完整通过。

platform/backend/app/api/system.py

@@ -1,63 +1,65 @@
-from fastapi import APIRouter, HTTPException, Depends
+import logging
+from fastapi import APIRouter, HTTPException, Depends, Body
 from sqlalchemy.orm import Session
 from sqlalchemy import func
-from datetime import datetime, date, timedelta
+from datetime import datetime, date
 from typing import Dict, Any, List, Optional
 from pathlib import Path
-from .auth import get_current_user
 import os
 import json
 from ..database import get_db
 from ..models import Topic, Article
-from ..schemas import SystemStatus
 from ..core.generator import run_creator
 from ..core.optimizer import run_optimizer
 from ..core.sync import sync_all_topics
 from ..core.scheduler import scheduler
+from .auth import get_current_user
 
 PROJECT_ROOT = Path(__file__).resolve().parents[4]
 if os.getenv('PROJECT_ROOT'):
     PROJECT_ROOT = Path(os.getenv('PROJECT_ROOT'))
 LOGS_DIR = PROJECT_ROOT / "automation" / "logs"
-DATA_DIR = PROJECT_ROOT / "automation" / "data"
 
+logger = logging.getLogger(__name__)
 router = APIRouter(prefix="/api/system", tags=["system"])
 
+def _aggregate_status_counts(db: Session):
+    """聚合状态计数，兼容中英文状态值"""
+    raw = db.query(Topic.status, func.count()).group_by(Topic.status).all()
+    mapping = {
+        'pending': ['pending', '待处理'],
+        'review': ['review', '待审查'],
+        'ready': ['ready', '待发布'],
+        'published': ['published', '已发布']
+    }
+    counts = {'pending': 0, 'review': 0, 'ready': 0, 'published': 0}
+    for status_val, cnt in raw:
+        for key, aliases in mapping.items():
+            if status_val in aliases:
+                counts[key] += cnt
+                break
+    return counts
+
 @router.get("/status")
 def get_status(db: Session = Depends(get_db)):
-    """系统状态概览 - 返回前端兼容格式"""
     total = db.query(Topic).count()
-    by_status_result = db.query(Topic.status, func.count()).group_by(Topic.status).all()
-    by_status = {status: count for status, count in by_status_result}
-    
-    # 确保返回所有状态（数据库存中文，返回前端需要英文）
-    status_map = {
-        'pending': by_status.get('待处理', 0),
-        'review': by_status.get('待审查', 0),
-        'ready': by_status.get('待发布', 0),
-        'published': by_status.get('已发布', 0)
-    }
-    
-    # 计算今日新增
+    counts = _aggregate_status_counts(db)
     today = date.today()
-    today_count = db.query(Topic).filter(
-        func.date(Topic.created_at) == today
-    ).count()
-    
+    today_count = db.query(Topic).filter(func.date(Topic.created_at) == today).count()
     return {
         "stats": {
             "total": total,
-            "pending": status_map['pending'],
-            "review": status_map['review'],
-            "ready": status_map['ready'],
-            "published": status_map['published'],
+            "pending": counts['pending'],
+            "review": counts['review'],
+            "ready": counts['ready'],
+            "published": counts['published'],
             "today": today_count
         }
     }
 
 @router.post("/generate/run", dependencies=[Depends(get_current_user)])
-def trigger_generation(topic_id: str = None, db: Session = Depends(get_db)):
-    """手动触发内容创作任务"""
+def trigger_generation(topic_id: str = Body(None, embed=True), db: Session = Depends(get_db)):
+    logger.info(f"Received topic_id={topic_id}")
     try:
         result = run_creator(topic_id)
         if not result["ok"]:
@@ -68,8 +70,7 @@ def trigger_generation(topic_id: str = None, db: Session = Depends(get_db)):
         raise HTTPException(status_code=500, detail=str(e))
 
 @router.post("/optimize/run", dependencies=[Depends(get_current_user)])
-def trigger_optimization(topic_ids: List[str] = None, db: Session = Depends(get_db)):
-    """手动触发合规优化任务"""
+def trigger_optimization(topic_ids: List[str] = Body(None, embed=True), db: Session = Depends(get_db)):
     try:
         result = run_optimizer(topic_ids)
         if not result["ok"]:
@@ -85,7 +86,6 @@ def trigger_optimization(topic_ids: List[str] = None, db: Session = Depends(get_
 
 @router.get("/logs/{log_date}", dependencies=[Depends(get_current_user)])
 def get_logs(log_date: str, log_type: str = "creator"):
-    """读取日志文件内容"""
     log_file = LOGS_DIR / f"{log_type}_{log_date}.log"
     if not log_file.exists():
         raise HTTPException(status_code=404, detail=f"Log file not found: {log_file}")
@@ -94,59 +94,56 @@ def get_logs(log_date: str, log_type: str = "creator"):
     return {"log_date": log_date, "log_type": log_type, "content": lines}
 
 @router.get("/pipeline/status", dependencies=[Depends(get_current_user)])
-def get_pipeline_status():
-    """获取流水线各模块状态"""
-    try:
-        topics_file = DATA_DIR / "sustainability_topics.json"
-        topics = []
-        if topics_file.exists():
-            topics = json.loads(topics_file.read_text(encoding='utf-8'))
-        status_counts = {}
-        for t in topics:
-            s = t.get('status', 'unknown')
-            status_counts[s] = status_counts.get(s, 0) + 1
-        log_files = {
-            "collector": LOGS_DIR / f"collector_{date.today().isoformat()}.log",
-            "creator": LOGS_DIR / f"creator_{date.today().isoformat()}.log",
-            "optimizer": LOGS_DIR / f"optimizer_{date.today().isoformat()}.log",
-        }
-        pipeline_status = {}
-        for name, log_file in log_files.items():
-            if log_file.exists():
-                mtime = datetime.fromtimestamp(log_file.stat().st_mtime)
-                pipeline_status[name] = {"last_run": mtime.isoformat(), "exists": True}
-            else:
-                pipeline_status[name] = {"exists": False, "last_run": None}
-        return {"topics_count": len(topics), "status_distribution": status_counts, "pipeline_modules": pipeline_status}
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
+def get_pipeline_status(db: Session = Depends(get_db)):
+    total = db.query(Topic).count()
+    counts = _aggregate_status_counts(db)
+    log_files = {
+        "collector": LOGS_DIR / f"collector_{date.today().isoformat()}.log",
+        "creator": LOGS_DIR / f"creator_{date.today().isoformat()}.log",
+        "optimizer": LOGS_DIR / f"optimizer_{date.today().isoformat()}.log",
+    }
+    pipeline_status = {}
+    for name, log_file in log_files.items():
+        if log_file.exists():
+            mtime = datetime.fromtimestamp(log_file.stat().st_mtime)
+            pipeline_status[name] = {"last_run": mtime.isoformat(), "exists": True}
+        else:
+            pipeline_status[name] = {"exists": False, "last_run": None}
+    return {"topics_count": total, "status_distribution": counts, "pipeline_modules": pipeline_status}
 
 @router.post("/sync/run")
 def run_sync():
-    """手动触发数据同步"""
     try:
         sync_all_topics()
-        return {"message": "Sync completed"}
+        return {"message": "Sync completed (DB → JSON backup)"}
     except Exception as e:
         raise HTTPException(status_code=500, detail=str(e))
 
 @router.get("/automation/topics")
-def list_automation_topics():
-    """直接读取自动化流水线的选题 JSON"""
+def list_automation_topics(db: Session = Depends(get_db)):
     try:
-        topics_file = DATA_DIR / "sustainability_topics.json"
-        if not topics_file.exists():
-            raise HTTPException(status_code=404, detail="Topics JSON not found")
-        topics = json.loads(topics_file.read_text(encoding='utf-8'))
-        return {"count": len(topics), "topics": topics[-50:]}
-    except json.JSONDecodeError as e:
-        raise HTTPException(status_code=500, detail=f"JSON parse error: {e}")
+        topics = db.query(Topic).order_by(Topic.created_at.desc()).limit(100).all()
+        result = []
+        for t in topics:
+            result.append({
+                "id": t.id,
+                "title": t.title,
+                "field": t.field,
+                "status": t.status,
+                "priority": t.priority,
+                "priority_score": t.priority_score,
+                "total_score": t.total_score,
+                "created_at": t.created_at.isoformat() if t.created_at else None,
+                "updated_at": t.updated_at.isoformat() if t.updated_at else None,
+                "ready_at": t.ready_at.isoformat() if t.ready_at else None,
+                "compliance_score": t.compliance_score
+            })
+        return {"count": len(result), "topics": result[:50]}
     except Exception as e:
         raise HTTPException(status_code=500, detail=str(e))
 
 @router.post("/refresh")
 def refresh_all():
-    """刷新所有数据"""
     try:
         sync_all_topics()
         return {"message": "Refresh completed"}
@@ -155,5 +152,4 @@ def refresh_all():
 
 @router.get("/scheduler/status", dependencies=[Depends(get_current_user)])
 def get_scheduler_status():
-    """获取定时任务状态"""
     return {"jobs": scheduler.get_jobs()}

platform/backend/app/core/sync.py

@@ -13,52 +13,96 @@ if os.getenv('PROJECT_ROOT'):
 TOPICS_FILE = PROJECT_ROOT / "automation" / "data" / "sustainability_topics.json"
 
 def sync_topic_to_db(topic_id: str, db: Session = None) -> Topic:
-    topics = json.loads(TOPICS_FILE.read_text(encoding='utf-8'))
-    topic_data = next((t for t in topics if t['id'] == topic_id), None)
-    if not topic_data:
-        raise ValueError(f"Topic {topic_id} not found in file")
-    
+    """注意：此函数原用于将JSON单个选题同步到数据库。现已不需要，保留用于兼容。当前方向相反（DB为主），此处仅从数据库导出到JSON（如果需要）"""
+    # 为了不破坏旧调用，我们改为从数据库读取并写入 JSON 文件（单条更新）
     close_db = False
     if db is None:
         db = SessionLocal()
         close_db = True
     try:
-        db_topic = db.query(Topic).filter(Topic.id == topic_id).first()
-        if db_topic is None:
-            db_topic = Topic(
-                id=topic_data['id'],
-                title=topic_data['title'],
-                field=topic_data['field'],
-                format=topic_data.get('format'),
-                core_concept=topic_data.get('core_concept'),
-                audience_pain=topic_data.get('audience_pain'),
-                unique_angle=topic_data.get('unique_angle'),
-                priority=topic_data.get('priority'),
-                priority_score=topic_data.get('priority_score', 0),
-                total_score=topic_data.get('total_score')
-            )
-            db.add(db_topic)
-        db_topic.status = topic_data.get('status', db_topic.status)
-        db_topic.ready_at = datetime.strptime(topic_data['ready_at'], '%Y-%m-%d').date() if topic_data.get('ready_at') else None
-        db_topic.published_at = datetime.strptime(topic_data['published_at'], '%Y-%m-%d').date() if topic_data.get('published_at') else None
-        db_topic.compliance_score = topic_data.get('compliance_score', db_topic.compliance_score)
-        db_topic.platform_urls = topic_data.get('platform_urls', {})
-        db_topic.generated_at = datetime.now() if db_topic.generated_at is None and topic_data.get("status") in ["ready", "published"] else db_topic.generated_at
-        db_topic.updated_at = datetime.now()
-        db.commit()
-        db.refresh(db_topic)
-        return db_topic
+        topic = db.query(Topic).filter(Topic.id == topic_id).first()
+        if not topic:
+            raise ValueError(f"Topic {topic_id} not found in DB")
+        # 写入 JSON 文件（作为备份）
+        try:
+            if TOPICS_FILE.exists():
+                with open(TOPICS_FILE, 'r', encoding='utf-8') as f:
+                    topics = json.load(f)
+            else:
+                topics = []
+            # 转为字典
+            tdict = {
+                'id': topic.id,
+                'title': topic.title,
+                'field': topic.field,
+                'format': topic.format,
+                'core_concept': topic.core_concept,
+                'audience_pain': topic.audience_pain,
+                'unique_angle': topic.unique_angle,
+                'priority': topic.priority,
+                'priority_score': topic.priority_score,
+                'total_score': topic.total_score,
+                'status': topic.status,
+                'cases': topic.cases or [],
+                'source_file': topic.source_file,
+                'created_at': topic.created_at.isoformat() if topic.created_at else None,
+                'updated_at': topic.updated_at.isoformat() if topic.updated_at else None,
+                'ready_at': topic.ready_at.isoformat() if topic.ready_at else None,
+                'published_at': topic.published_at.isoformat() if topic.published_at else None,
+                'compliance_score': topic.compliance_score,
+                'platform_urls': topic.platform_urls or {}
+            }
+            # 更新或追加
+            found = False
+            for i, t in enumerate(topics):
+                if t['id'] == topic_id:
+                    topics[i] = tdict
+                    found = True
+                    break
+            if not found:
+                topics.append(tdict)
+            with open(TOPICS_FILE, 'w', encoding='utf-8') as f:
+                json.dump(topics, f, ensure_ascii=False, indent=2)
+        except Exception as e:
+            print(f"[Warning] JSON backup failed: {e}")
+        return topic
     finally:
         if close_db:
             db.close()
 
 def sync_all_topics():
+    """导出所有选题到 JSON 文件（用于备份或兼容）"""
     db = SessionLocal()
     try:
-        topics = json.loads(TOPICS_FILE.read_text(encoding='utf-8'))
+        topics = db.query(Topic).order_by(Topic.created_at).all()
+        topic_list = []
         for t in topics:
-            sync_topic_to_db(t['id'], db)
-        print(f"✅ 同步 {len(topics)} 个选题到数据库")
+            tdict = {
+                'id': t.id,
+                'title': t.title,
+                'field': t.field,
+                'format': t.format,
+                'core_concept': t.core_concept,
+                'audience_pain': t.audience_pain,
+                'unique_angle': t.unique_angle,
+                'priority': t.priority,
+                'priority_score': t.priority_score,
+                'total_score': t.total_score,
+                'status': t.status,
+                'cases': t.cases or [],
+                'source_file': t.source_file,
+                'created_at': t.created_at.isoformat() if t.created_at else None,
+                'updated_at': t.updated_at.isoformat() if t.updated_at else None,
+                'ready_at': t.ready_at.isoformat() if t.ready_at else None,
+                'published_at': t.published_at.isoformat() if t.published_at else None,
+                'compliance_score': t.compliance_score,
+                'platform_urls': t.platform_urls or {}
+            }
+            topic_list.append(tdict)
+        TOPICS_FILE.parent.mkdir(parents=True, exist_ok=True)
+        with open(TOPICS_FILE, 'w', encoding='utf-8') as f:
+            json.dump(topic_list, f, ensure_ascii=False, indent=2)
+        print(f"✅ 导出 {len(topic_list)} 个选题到 JSON (兼容模式)")
     finally:
         db.close()