# app/utils/search.py
import re

def highlight_excerpt(text: str, query: str, max_length: int = 300) -> str:
    """
    从文本中截取包含搜索词的片段并高亮
    :param text: 原始文本（这里传入纯文本，已移除 Markdown/HTML 标签）
    :param query: 搜索关键词
    :param max_length: 无匹配时的最大截断长度
    :return: 带 <mark> 高亮的 HTML 片段
    """
    if not text or not query:
        return text[:max_length] if text else ""

    # 不区分大小写搜索
    pattern = re.compile(re.escape(query), re.IGNORECASE)
    match = pattern.search(text)

    if match:
        # 关键词前后各保留 max_length//2 的上下文
        context_length = max_length // 2
        start = max(0, match.start() - context_length)
        end = min(len(text), match.end() + context_length)
        excerpt = text[start:end]

        # 片段截断提示
        if start > 0:
            excerpt = "..." + excerpt
        if end < len(text):
            excerpt += "..."
    else:
        excerpt = text[:max_length]
        if len(text) > max_length:
            excerpt += "..."

    # 高亮：保留原文大小写，用 <mark> 标签包裹
    highlighted = pattern.sub(lambda m: f'<mark class="search-highlight">{m.group()}</mark>', excerpt)
    return highlighted

# app/articles/routes.py（替换原 search 函数，注意引入必要的模型和模块）
from datetime import datetime, timedelta
from app.articles.models import Category  # 假设已有 Category 模型

@articles_bp.route("/search")
def search():
    query = request.args.get("q", "").strip()
    category_id = request.args.get("category", type=int)
    date_from = request.args.get("from", type=str)
    recent_days = request.args.get("recent", type=int)
    page = request.args.get("page", 1, type=int)

    # 获取所有已发布文章的分类（用于下拉框）
    categories = Category.query.join(Category.posts).filter(Post.is_published.is_(True)).distinct().all()

    base_query = Post.query.filter(Post.is_published.is_(True))

    # 关键词过滤
    if query:
        search_pattern = f"%{query}%"
        base_query = base_query.filter(
            or_(
                Post.title.ilike(search_pattern),
                Post.summary.ilike(search_pattern),
                Post.content.ilike(search_pattern),
            )
        )

    # 分类过滤
    if category_id:
        base_query = base_query.filter_by(category_id=category_id)

    # 时间过滤：优先用指定日期，其次用“近 N 天”
    if date_from:
        try:
            start_date = datetime.fromisoformat(date_from)
            base_query = base_query.filter(Post.created_at >= start_date)
        except ValueError:
            pass  # 无效日期直接忽略
    elif recent_days:
        start_date = datetime.utcnow() - timedelta(days=recent_days)
        base_query = base_query.filter(Post.created_at >= start_date)

    pagination = (
        base_query
        .order_by(Post.created_at.desc())
        .paginate(page=page, per_page=20, error_out=False)
    )

    return render_template(
        "articles/search.html",
        results=pagination.items,
        query=query,
        categories=categories,
        selected_category=category_id,
        selected_from=date_from,
        selected_recent=recent_days,
        pagination=pagination,
        total=pagination.total,
    )

# 在搜索路由中替换关键词过滤的部分
from sqlalchemy import func

@articles_bp.route("/search")
def search():
    # ... 前面的参数获取、时间/分类过滤、分页逻辑保持不变 ...

    if query:
        # 构建搜索向量：将标题和正文合并成一个中文搜索向量（|| 是向量合并符）
        search_vector = (
            func.to_tsvector("chinese", Post.title)
            .op("||")(func.to_tsvector("chinese", Post.content))
        )
        # 构建查询：plainto_tsquery 会自动把用户输入的空格转换成“且”逻辑
        ts_query = func.plainto_tsquery("chinese", query)
        # 过滤并按相关性降序
        base_query = (
            base_query
            .filter(search_vector.op("@@")(ts_query))  # @@ 是全文匹配操作符
            .order_by(func.ts_rank(search_vector, ts_query).desc())
        )

    # ... 分页与渲染 ...

# app/articles/models.py
from app import db

class Post(db.Model):
    # ... 原有字段 ...
    # 添加搜索向量列（PostgreSQL 12+ 支持计算列）
    search_vector = db.Column(
        db.TSVECTOR,
        db.Computed(
            "to_tsvector('chinese', coalesce(title, '') || ' ' || coalesce(content, ''))",
            persisted=True,
        ),
    )
    # 创建 GIN 索引
    __table_args__ = (db.Index("idx_post_search_vector", search_vector, postgresql_using="gin"),)

# 修改 computed 列的定义
db.Computed(
    "setweight(to_tsvector('chinese', coalesce(title, '')), 'A') || "
    "setweight(to_tsvector('chinese', coalesce(summary, '')), 'B') || "
    "setweight(to_tsvector('chinese', coalesce(content, '')), 'D')",
    persisted=True,
)