Phase 7 Task 7: 插件与集成系统

- 创建 plugin_manager.py 模块 - PluginManager: 插件管理主类 - ChromeExtensionHandler: Chrome 插件处理 - BotHandler: 飞书/钉钉/Slack 机器人处理 - WebhookIntegration: Zapier/Make Webhook 集成 - WebDAVSync: WebDAV 同步管理 - 创建完整的 Chrome 扩展代码 - manifest.json, background.js, content.js, content.css - popup.html/js: 弹出窗口界面 - options.html/js: 设置页面 - 支持网页剪藏、选中文本保存、项目选择 - 更新 schema.sql 添加插件相关数据库表 - plugins: 插件配置表 - bot_sessions: 机器人会话表 - webhook_endpoints: Webhook 端点表 - webdav_syncs: WebDAV 同步配置表 - plugin_activity_logs: 插件活动日志表 - 更新 main.py 添加插件相关 API 端点 - GET/POST /api/v1/plugins - 插件管理 - POST /api/v1/plugins/chrome/clip - Chrome 插件保存网页 - POST /api/v1/bots/webhook/{platform} - 接收机器人消息 - GET /api/v1/bots/sessions - 机器人会话列表 - POST /api/v1/webhook-endpoints - 创建 Webhook 端点 - POST /webhook/{type}/{token} - 接收外部 Webhook - POST /api/v1/webdav-syncs - WebDAV 同步配置 - POST /api/v1/webdav-syncs/{id}/test - 测试 WebDAV 连接 - POST /api/v1/webdav-syncs/{id}/sync - 触发 WebDAV 同步 - 更新 requirements.txt 添加插件依赖 - beautifulsoup4: HTML 解析 - webdavclient3: WebDAV 客户端 - 更新 STATUS.md 和 README.md 开发进度
2026-02-23 12:09:15 +08:00
parent 08535e54ba
commit 797ca58e8e
27 changed files with 7350 additions and 11 deletions
--- a/backend/db_manager.py
+++ b/backend/db_manager.py
@@ -878,6 +878,310 @@ class DatabaseManager:
                filtered.append(entity)
        return filtered

+    # ==================== Phase 7: Multimodal Support ====================
+    
+    def create_video(self, video_id: str, project_id: str, filename: str, 
+                     duration: float = 0, fps: float = 0, resolution: Dict = None,
+                     audio_transcript_id: str = None, full_ocr_text: str = "",
+                     extracted_entities: List[Dict] = None, 
+                     extracted_relations: List[Dict] = None) -> str:
+        """创建视频记录"""
+        conn = self.get_conn()
+        now = datetime.now().isoformat()
+        
+        conn.execute(
+            """INSERT INTO videos 
+               (id, project_id, filename, duration, fps, resolution,
+                audio_transcript_id, full_ocr_text, extracted_entities, 
+                extracted_relations, status, created_at, updated_at)
+               VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)""",
+            (video_id, project_id, filename, duration, fps,
+             json.dumps(resolution) if resolution else None,
+             audio_transcript_id, full_ocr_text,
+             json.dumps(extracted_entities or []),
+             json.dumps(extracted_relations or []),
+             'completed', now, now)
+        )
+        conn.commit()
+        conn.close()
+        return video_id
+    
+    def get_video(self, video_id: str) -> Optional[Dict]:
+        """获取视频信息"""
+        conn = self.get_conn()
+        row = conn.execute(
+            "SELECT * FROM videos WHERE id = ?", (video_id,)
+        ).fetchone()
+        conn.close()
+        
+        if row:
+            data = dict(row)
+            data['resolution'] = json.loads(data['resolution']) if data['resolution'] else None
+            data['extracted_entities'] = json.loads(data['extracted_entities']) if data['extracted_entities'] else []
+            data['extracted_relations'] = json.loads(data['extracted_relations']) if data['extracted_relations'] else []
+            return data
+        return None
+    
+    def list_project_videos(self, project_id: str) -> List[Dict]:
+        """获取项目的所有视频"""
+        conn = self.get_conn()
+        rows = conn.execute(
+            "SELECT * FROM videos WHERE project_id = ? ORDER BY created_at DESC",
+            (project_id,)
+        ).fetchall()
+        conn.close()
+        
+        videos = []
+        for row in rows:
+            data = dict(row)
+            data['resolution'] = json.loads(data['resolution']) if data['resolution'] else None
+            data['extracted_entities'] = json.loads(data['extracted_entities']) if data['extracted_entities'] else []
+            data['extracted_relations'] = json.loads(data['extracted_relations']) if data['extracted_relations'] else []
+            videos.append(data)
+        return videos
+    
+    def create_video_frame(self, frame_id: str, video_id: str, frame_number: int,
+                          timestamp: float, image_url: str = None, 
+                          ocr_text: str = None, extracted_entities: List[Dict] = None) -> str:
+        """创建视频帧记录"""
+        conn = self.get_conn()
+        now = datetime.now().isoformat()
+        
+        conn.execute(
+            """INSERT INTO video_frames 
+               (id, video_id, frame_number, timestamp, image_url, ocr_text, extracted_entities, created_at)
+               VALUES (?, ?, ?, ?, ?, ?, ?, ?)""",
+            (frame_id, video_id, frame_number, timestamp, image_url, ocr_text,
+             json.dumps(extracted_entities or []), now)
+        )
+        conn.commit()
+        conn.close()
+        return frame_id
+    
+    def get_video_frames(self, video_id: str) -> List[Dict]:
+        """获取视频的所有帧"""
+        conn = self.get_conn()
+        rows = conn.execute(
+            """SELECT * FROM video_frames WHERE video_id = ? ORDER BY timestamp""",
+            (video_id,)
+        ).fetchall()
+        conn.close()
+        
+        frames = []
+        for row in rows:
+            data = dict(row)
+            data['extracted_entities'] = json.loads(data['extracted_entities']) if data['extracted_entities'] else []
+            frames.append(data)
+        return frames
+    
+    def create_image(self, image_id: str, project_id: str, filename: str,
+                     ocr_text: str = "", description: str = "",
+                     extracted_entities: List[Dict] = None,
+                     extracted_relations: List[Dict] = None) -> str:
+        """创建图片记录"""
+        conn = self.get_conn()
+        now = datetime.now().isoformat()
+        
+        conn.execute(
+            """INSERT INTO images 
+               (id, project_id, filename, ocr_text, description,
+                extracted_entities, extracted_relations, status, created_at, updated_at)
+               VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)""",
+            (image_id, project_id, filename, ocr_text, description,
+             json.dumps(extracted_entities or []),
+             json.dumps(extracted_relations or []),
+             'completed', now, now)
+        )
+        conn.commit()
+        conn.close()
+        return image_id
+    
+    def get_image(self, image_id: str) -> Optional[Dict]:
+        """获取图片信息"""
+        conn = self.get_conn()
+        row = conn.execute(
+            "SELECT * FROM images WHERE id = ?", (image_id,)
+        ).fetchone()
+        conn.close()
+        
+        if row:
+            data = dict(row)
+            data['extracted_entities'] = json.loads(data['extracted_entities']) if data['extracted_entities'] else []
+            data['extracted_relations'] = json.loads(data['extracted_relations']) if data['extracted_relations'] else []
+            return data
+        return None
+    
+    def list_project_images(self, project_id: str) -> List[Dict]:
+        """获取项目的所有图片"""
+        conn = self.get_conn()
+        rows = conn.execute(
+            "SELECT * FROM images WHERE project_id = ? ORDER BY created_at DESC",
+            (project_id,)
+        ).fetchall()
+        conn.close()
+        
+        images = []
+        for row in rows:
+            data = dict(row)
+            data['extracted_entities'] = json.loads(data['extracted_entities']) if data['extracted_entities'] else []
+            data['extracted_relations'] = json.loads(data['extracted_relations']) if data['extracted_relations'] else []
+            images.append(data)
+        return images
+    
+    def create_multimodal_mention(self, mention_id: str, project_id: str, 
+                                  entity_id: str, modality: str, source_id: str,
+                                  source_type: str, text_snippet: str = "",
+                                  confidence: float = 1.0) -> str:
+        """创建多模态实体提及记录"""
+        conn = self.get_conn()
+        now = datetime.now().isoformat()
+        
+        conn.execute(
+            """INSERT OR REPLACE INTO multimodal_mentions 
+               (id, project_id, entity_id, modality, source_id, source_type, 
+                text_snippet, confidence, created_at)
+               VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)""",
+            (mention_id, project_id, entity_id, modality, source_id, 
+             source_type, text_snippet, confidence, now)
+        )
+        conn.commit()
+        conn.close()
+        return mention_id
+    
+    def get_entity_multimodal_mentions(self, entity_id: str) -> List[Dict]:
+        """获取实体的多模态提及"""
+        conn = self.get_conn()
+        rows = conn.execute(
+            """SELECT m.*, e.name as entity_name
+               FROM multimodal_mentions m
+               JOIN entities e ON m.entity_id = e.id
+               WHERE m.entity_id = ? ORDER BY m.created_at DESC""",
+            (entity_id,)
+        ).fetchall()
+        conn.close()
+        return [dict(r) for r in rows]
+    
+    def get_project_multimodal_mentions(self, project_id: str, 
+                                        modality: str = None) -> List[Dict]:
+        """获取项目的多模态提及"""
+        conn = self.get_conn()
+        
+        if modality:
+            rows = conn.execute(
+                """SELECT m.*, e.name as entity_name
+                   FROM multimodal_mentions m
+                   JOIN entities e ON m.entity_id = e.id
+                   WHERE m.project_id = ? AND m.modality = ?
+                   ORDER BY m.created_at DESC""",
+                (project_id, modality)
+            ).fetchall()
+        else:
+            rows = conn.execute(
+                """SELECT m.*, e.name as entity_name
+                   FROM multimodal_mentions m
+                   JOIN entities e ON m.entity_id = e.id
+                   WHERE m.project_id = ? ORDER BY m.created_at DESC""",
+                (project_id,)
+            ).fetchall()
+        
+        conn.close()
+        return [dict(r) for r in rows]
+    
+    def create_multimodal_entity_link(self, link_id: str, entity_id: str,
+                                      linked_entity_id: str, link_type: str,
+                                      confidence: float = 1.0, 
+                                      evidence: str = "",
+                                      modalities: List[str] = None) -> str:
+        """创建多模态实体关联"""
+        conn = self.get_conn()
+        now = datetime.now().isoformat()
+        
+        conn.execute(
+            """INSERT OR REPLACE INTO multimodal_entity_links 
+               (id, entity_id, linked_entity_id, link_type, confidence, 
+                evidence, modalities, created_at)
+               VALUES (?, ?, ?, ?, ?, ?, ?, ?)""",
+            (link_id, entity_id, linked_entity_id, link_type, confidence,
+             evidence, json.dumps(modalities or []), now)
+        )
+        conn.commit()
+        conn.close()
+        return link_id
+    
+    def get_entity_multimodal_links(self, entity_id: str) -> List[Dict]:
+        """获取实体的多模态关联"""
+        conn = self.get_conn()
+        rows = conn.execute(
+            """SELECT l.*, e1.name as entity_name, e2.name as linked_entity_name
+               FROM multimodal_entity_links l
+               JOIN entities e1 ON l.entity_id = e1.id
+               JOIN entities e2 ON l.linked_entity_id = e2.id
+               WHERE l.entity_id = ? OR l.linked_entity_id = ?""",
+            (entity_id, entity_id)
+        ).fetchall()
+        conn.close()
+        
+        links = []
+        for row in rows:
+            data = dict(row)
+            data['modalities'] = json.loads(data['modalities']) if data['modalities'] else []
+            links.append(data)
+        return links
+    
+    def get_project_multimodal_stats(self, project_id: str) -> Dict:
+        """获取项目多模态统计信息"""
+        conn = self.get_conn()
+        
+        stats = {
+            'video_count': 0,
+            'image_count': 0,
+            'multimodal_entity_count': 0,
+            'cross_modal_links': 0,
+            'modality_distribution': {}
+        }
+        
+        # 视频数量
+        row = conn.execute(
+            "SELECT COUNT(*) as count FROM videos WHERE project_id = ?",
+            (project_id,)
+        ).fetchone()
+        stats['video_count'] = row['count']
+        
+        # 图片数量
+        row = conn.execute(
+            "SELECT COUNT(*) as count FROM images WHERE project_id = ?",
+            (project_id,)
+        ).fetchone()
+        stats['image_count'] = row['count']
+        
+        # 多模态实体数量
+        row = conn.execute(
+            """SELECT COUNT(DISTINCT entity_id) as count 
+               FROM multimodal_mentions WHERE project_id = ?""",
+            (project_id,)
+        ).fetchone()
+        stats['multimodal_entity_count'] = row['count']
+        
+        # 跨模态关联数量
+        row = conn.execute(
+            """SELECT COUNT(*) as count FROM multimodal_entity_links 
+               WHERE entity_id IN (SELECT id FROM entities WHERE project_id = ?)""",
+            (project_id,)
+        ).fetchone()
+        stats['cross_modal_links'] = row['count']
+        
+        # 模态分布
+        for modality in ['audio', 'video', 'image', 'document']:
+            row = conn.execute(
+                """SELECT COUNT(*) as count FROM multimodal_mentions 
+                   WHERE project_id = ? AND modality = ?""",
+                (project_id, modality)
+            ).fetchone()
+            stats['modality_distribution'][modality] = row['count']
+        
+        conn.close()
+        return stats
+

 # Singleton instance
 _db_manager = None