HuiBrain/app/services/page_service.py

"""
知识页面服务
提供知识页面的 CRUD 操作
"""

from __future__ import annotations

import logging
from typing import List, Optional

from sqlalchemy import func, select, text
from sqlalchemy.ext.asyncio import AsyncSession

from app.models.base import KnowledgeChunk, KnowledgePage
from app.schemas.page import PageCreate, PageResponse, PageUpdate

logger = logging.getLogger(__name__)


class PageService:
    """知识页面服务"""

    def __init__(self, db: AsyncSession):
        self.db = db

    async def create_page(self, data: PageCreate) -> KnowledgePage:
        """创建知识页面"""
        page = KnowledgePage(
            title=data.title,
            content=data.content,
            source_file=data.source_file,
            course_name=data.course_name,
            teacher_name=data.teacher_name,
            live_date=data.live_date,
            page_number=data.page_number,
            metadata_json=data.metadata_json,
        )
        self.db.add(page)
        await self.db.flush()
        await self.db.refresh(page)
        return page

    async def get_page(self, page_id: int) -> Optional[KnowledgePage]:
        """根据 ID 获取知识页面"""
        result = await self.db.execute(
            select(KnowledgePage).where(KnowledgePage.id == page_id)
        )
        return result.scalar_one_or_none()

    async def list_pages(
        self,
        page: int = 1,
        page_size: int = 20,
        course_name: Optional[str] = None,
        teacher_name: Optional[str] = None,
        keyword: Optional[str] = None,
    ) -> dict:
        """
        分页查询知识页面列表。

        Args:
            page: 页码（从 1 开始）
            page_size: 每页数量
            course_name: 按课程名称过滤
            teacher_name: 按讲师名称过滤
            keyword: 关键词搜索（标题或内容）

        Returns:
            {"total": int, "page": int, "page_size": int, "items": list}
        """
        query = select(KnowledgePage)
        count_query = select(func.count(KnowledgePage.id))

        # 过滤条件
        if course_name:
            query = query.where(KnowledgePage.course_name == course_name)
            count_query = count_query.where(KnowledgePage.course_name == course_name)
        if teacher_name:
            query = query.where(KnowledgePage.teacher_name == teacher_name)
            count_query = count_query.where(KnowledgePage.teacher_name == teacher_name)
        if keyword:
            like_pattern = f"%{keyword}%"
            query = query.where(
                KnowledgePage.title.ilike(like_pattern)
                | KnowledgePage.content.ilike(like_pattern)
            )
            count_query = count_query.where(
                KnowledgePage.title.ilike(like_pattern)
                | KnowledgePage.content.ilike(like_pattern)
            )

        # 总数
        total_result = await self.db.execute(count_query)
        total = total_result.scalar() or 0

        # 分页
        offset = (page - 1) * page_size
        query = query.order_by(KnowledgePage.created_at.desc()).offset(offset).limit(page_size)
        result = await self.db.execute(query)
        items = result.scalars().all()

        return {
            "total": total,
            "page": page,
            "page_size": page_size,
            "items": items,
        }

    async def update_page(self, page_id: int, data: PageUpdate) -> Optional[KnowledgePage]:
        """更新知识页面"""
        page = await self.get_page(page_id)
        if page is None:
            return None

        update_data = data.model_dump(exclude_unset=True)
        for field, value in update_data.items():
            setattr(page, field, value)

        await self.db.flush()
        await self.db.refresh(page)
        return page

    async def delete_page(self, page_id: int) -> bool:
        """删除知识页面及其关联分块"""
        page = await self.get_page(page_id)
        if page is None:
            return False

        # 先删除关联的分块
        await self.db.execute(
            text("DELETE FROM knowledge_chunks WHERE page_id = :page_id"),
            {"page_id": page_id},
        )
        # 再删除页面
        await self.db.delete(page)
        await self.db.flush()
        return True

    async def get_page_chunks(self, page_id: int) -> List[KnowledgeChunk]:
        """获取知识页面的所有分块"""
        result = await self.db.execute(
            select(KnowledgeChunk)
            .where(KnowledgeChunk.page_id == page_id)
            .order_by(KnowledgeChunk.chunk_index)
        )
        return list(result.scalars().all())

    async def reindex_page(self, page_id: int) -> dict:
        """
        重新索引知识页面：重新分块并生成嵌入向量。
        用于页面内容更新后刷新向量索引。
        """
        page = await self.get_page(page_id)
        if page is None:
            raise ValueError(f"知识页面不存在: {page_id}")

        # 删除旧分块
        await self.db.execute(
            text("DELETE FROM knowledge_chunks WHERE page_id = :page_id"),
            {"page_id": page_id},
        )

        # 重新分块
        from app.services.import_service import ImportService
        chunks = ImportService._chunk_text(page.content)

        if not chunks:
            await self.db.flush()
            return {"page_id": page_id, "chunks": 0}

        # 生成嵌入并插入
        from app.services.embedding_service import EmbeddingService
        try:
            embeddings = await EmbeddingService.embed_batch(chunks)
        except Exception as exc:
            logger.error("重新索引嵌入失败: %s", exc)
            embeddings = [None] * len(chunks)

        for idx, (chunk_text, embedding) in enumerate(zip(chunks, embeddings)):
            embedding_str = None
            if embedding:
                embedding_str = "[" + ",".join(str(x) for x in embedding) + "]"

            await self.db.execute(text("""
                INSERT INTO knowledge_chunks (page_id, chunk_index, content, embedding)
                VALUES (:page_id, :chunk_index, :content, :embedding::vector)
            """), {
                "page_id": page_id,
                "chunk_index": idx,
                "content": chunk_text,
                "embedding": embedding_str,
            })

        # 更新全文搜索向量
        await self.db.execute(text("""
            UPDATE knowledge_chunks
            SET search_vector = to_tsvector('chinese_zh', content)
            WHERE page_id = :page_id
        """), {"page_id": page_id})

        await self.db.flush()
        return {"page_id": page_id, "chunks": len(chunks)}