leocrm/app/plugins/builtins/unified_search/providers/wiki_provider.py

"""Wiki search provider — searches wiki articles via FTS and vector."""

from __future__ import annotations

import logging
import uuid
from typing import Any

from sqlalchemy import text
from sqlalchemy.ext.asyncio import AsyncSession

from app.plugins.builtins.unified_search.base_provider import BaseSearchProvider

logger = logging.getLogger(__name__)


class WikiSearchProvider(BaseSearchProvider):
    """Search provider for WikiArticle entities."""

    entity_type = "wiki_article"

    async def _search_fts_filtered(
        self,
        db: AsyncSession,
        tsquery: str,
        tenant_id: uuid.UUID,
        limit: int,
        visible_ids: set[uuid.UUID] | None,
    ) -> list[dict[str, Any]]:
        """Full-text search on wiki_articles title + content."""
        if visible_ids is not None:
            sql = text(
                """
                SELECT a.id, a.title, a.slug, a.summary, a.content, a.status,
                       a.category_id, a.tenant_id,
                       ts_rank(
                           to_tsvector('pg_catalog.german',
                               coalesce(a.title, '') || ' ' ||
                               coalesce(a.content, '') || ' ' ||
                               coalesce(a.summary, '')
                           ),
                           to_tsquery('pg_catalog.german', :q)
                       ) AS rank
                FROM wiki_articles a
                WHERE a.tenant_id = :tid
                  AND a.deleted_at IS NULL
                  AND a.status = 'published'
                  AND to_tsvector('pg_catalog.german',
                      coalesce(a.title, '') || ' ' ||
                      coalesce(a.content, '') || ' ' ||
                      coalesce(a.summary, '')
                  ) @@ to_tsquery('pg_catalog.german', :q)
                  AND a.id = ANY(:visible_ids)
                ORDER BY rank DESC
                LIMIT :lim
                """
            )
            result = await db.execute(
                sql,
                {"q": tsquery, "tid": tenant_id, "lim": limit, "visible_ids": list(visible_ids)},
            )
        else:
            sql = text(
                """
                SELECT a.id, a.title, a.slug, a.summary, a.content, a.status,
                       a.category_id, a.tenant_id,
                       ts_rank(
                           to_tsvector('pg_catalog.german',
                               coalesce(a.title, '') || ' ' ||
                               coalesce(a.content, '') || ' ' ||
                               coalesce(a.summary, '')
                           ),
                           to_tsquery('pg_catalog.german', :q)
                       ) AS rank
                FROM wiki_articles a
                WHERE a.tenant_id = :tid
                  AND a.deleted_at IS NULL
                  AND a.status = 'published'
                  AND to_tsvector('pg_catalog.german',
                      coalesce(a.title, '') || ' ' ||
                      coalesce(a.content, '') || ' ' ||
                      coalesce(a.summary, '')
                  ) @@ to_tsquery('pg_catalog.german', :q)
                ORDER BY rank DESC
                LIMIT :lim
                """
            )
            result = await db.execute(
                sql,
                {"q": tsquery, "tid": tenant_id, "lim": limit},
            )
        rows = result.mappings().all()
        return [dict(r) for r in rows]

    async def _search_vector_filtered(
        self,
        db: AsyncSession,
        embedding: list[float],
        tenant_id: uuid.UUID,
        limit: int,
        visible_ids: set[uuid.UUID] | None,
    ) -> list[dict[str, Any]]:
        """Semantic vector search on wiki_articles.embedding."""
        emb_str = f"[{','.join(str(x) for x in embedding)}]"
        if visible_ids is not None:
            sql = text(
                """
                SELECT a.id, a.title, a.slug, a.summary, a.content, a.status,
                       a.category_id, a.tenant_id,
                       1 - (a.embedding <=> cast(:emb AS vector)) AS similarity
                FROM wiki_articles a
                WHERE a.tenant_id = :tid
                  AND a.deleted_at IS NULL
                  AND a.status = 'published'
                  AND a.embedding IS NOT NULL
                  AND a.id = ANY(:visible_ids)
                ORDER BY a.embedding <=> cast(:emb AS vector)
                LIMIT :lim
                """
            )
            result = await db.execute(
                sql,
                {"emb": emb_str, "tid": tenant_id, "lim": limit, "visible_ids": list(visible_ids)},
            )
        else:
            sql = text(
                """
                SELECT a.id, a.title, a.slug, a.summary, a.content, a.status,
                       a.category_id, a.tenant_id,
                       1 - (a.embedding <=> cast(:emb AS vector)) AS similarity
                FROM wiki_articles a
                WHERE a.tenant_id = :tid
                  AND a.deleted_at IS NULL
                  AND a.status = 'published'
                  AND a.embedding IS NOT NULL
                ORDER BY a.embedding <=> cast(:emb AS vector)
                LIMIT :lim
                """
            )
            result = await db.execute(
                sql,
                {"emb": emb_str, "tid": tenant_id, "lim": limit},
            )
        rows = result.mappings().all()
        return [dict(r) for r in rows]

    def to_search_result(self, entity: dict) -> dict[str, Any]:
        """Convert a wiki article dict to a search result."""
        return {
            "entity_type": "wiki_article",
            "entity_id": str(entity.get("id", "")),
            "title": entity.get("title", ""),
            "description": entity.get("summary", "") or (entity.get("content", "")[:200] if entity.get("content") else ""),
            "url": f"/wiki?article={entity.get('slug', '')}",
            "tenant_id": str(entity.get("tenant_id", "")),
        }