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

"""User search provider — queries users table via user_tenants for tenant scope."""

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 UserSearchProvider(BaseSearchProvider):
    """Search provider for User entities.

    Users are global entities (no tenant_id on users table).
    Tenant membership is resolved via user_tenants join.
    """

    entity_type = "user"

    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 users fields, filtered by tenant membership."""
        if visible_ids is not None:
            sql = text(
                """
                SELECT u.*, ts_rank(
                    to_tsvector('pg_catalog.german',
                        coalesce(u.name, '') || ' ' ||
                        coalesce(u.first_name, '') || ' ' ||
                        coalesce(u.last_name, '') || ' ' ||
                        coalesce(u.email, '')
                    ),
                    to_tsquery('pg_catalog.german', :q)
                ) AS rank
                FROM users u
                JOIN user_tenants ut ON ut.user_id = u.id
                WHERE ut.tenant_id = :tid
                  AND u.deleted_at IS NULL
                  AND u.is_active = true
                  AND to_tsvector('pg_catalog.german',
                      coalesce(u.name, '') || ' ' ||
                      coalesce(u.first_name, '') || ' ' ||
                      coalesce(u.last_name, '') || ' ' ||
                      coalesce(u.email, '')
                  ) @@ to_tsquery('pg_catalog.german', :q)
                  AND u.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 u.*, ts_rank(
                    to_tsvector('pg_catalog.german',
                        coalesce(u.name, '') || ' ' ||
                        coalesce(u.first_name, '') || ' ' ||
                        coalesce(u.last_name, '') || ' ' ||
                        coalesce(u.email, '')
                    ),
                    to_tsquery('pg_catalog.german', :q)
                ) AS rank
                FROM users u
                JOIN user_tenants ut ON ut.user_id = u.id
                WHERE ut.tenant_id = :tid
                  AND u.deleted_at IS NULL
                  AND u.is_active = true
                  AND to_tsvector('pg_catalog.german',
                      coalesce(u.name, '') || ' ' ||
                      coalesce(u.first_name, '') || ' ' ||
                      coalesce(u.last_name, '') || ' ' ||
                      coalesce(u.email, '')
                  ) @@ 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 search — users table has no embedding column yet."""
        return []

    async def get_embedding_text(
        self, db: AsyncSession, entity_id: uuid.UUID, tenant_id: uuid.UUID
    ) -> str:
        """Get text for embedding generation."""
        sql = text(
            """
            SELECT name, first_name, last_name, email
            FROM users
            WHERE id = :eid
            """
        )
        result = await db.execute(sql, {"eid": entity_id})
        row = result.mappings().first()
        if not row:
            return ""
        parts = [
            row.get("name", ""),
            row.get("first_name", ""),
            row.get("last_name", ""),
            row.get("email", ""),
        ]
        return " ".join(str(p) for p in parts if p)

    def to_search_result(self, entity: object) -> dict[str, Any]:
        """Convert user to search result dict."""
        if isinstance(entity, dict):
            name = entity.get("name", "")
            email = entity.get("email", "") or ""
            entity_id = str(entity.get("id", ""))
            first_name = entity.get("first_name", "") or ""
            last_name = entity.get("last_name", "") or ""
        else:
            name = getattr(entity, "name", "")
            email = getattr(entity, "email", "") or ""
            entity_id = str(getattr(entity, "id", ""))
            first_name = getattr(entity, "first_name", "") or ""
            last_name = getattr(entity, "last_name", "") or ""
        display_name = f"{first_name} {last_name}".strip() or name
        return {
            "entity_type": self.entity_type,
            "entity_id": entity_id,
            "title": display_name,
            "snippet": email[:200],
            "score": 0.0,
            "data": {"email": email},
        }