ragflow_python/api/db/services/antique_service.py

#
#  Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
#
#  Licensed under the Apache License, Version 2.0 (the "License");
#  you may not use this file except in compliance with the License.
#  You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
#  Unless required by applicable law or agreed to in writing, software
#  distributed under the License is distributed on an "AS IS" BASIS,
#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#  See the License for the specific language governing permissions and
#  limitations under the License.
#
from datetime import datetime

import peewee
from werkzeug.security import generate_password_hash, check_password_hash

from api.db import UserTenantRole
from api.db.db_models import DB, UserTenant
from api.db.db_models import User, Tenant, MesumAntique
from api.db.services.common_service import CommonService
from api.db.services.brief_service import MesumOverviewService
from api.utils import get_uuid, get_format_time, current_timestamp, datetime_format
from api.db import StatusEnum
import logging

class MesumAntiqueService(CommonService):
    model = MesumAntique

    @classmethod
    @DB.connection_context()
    def get_by_mesum_id(cls, mesum_id):
        objs = cls.query(mesum_id=mesum_id)
        return objs

    @classmethod
    @DB.connection_context()
    def get_all_categories(cls,mesum_id):
        # 查询所有唯一的category
        mesum_antique_categories = []
        try:
            mesum_brief = MesumOverviewService.query(id=mesum_id)
            if mesum_brief:
                categories_text= mesum_brief[0].category
                # 统一替换中文分号为英文分号，并去除末尾分号
                if categories_text:
                    categories_text = categories_text.replace("；", ";").rstrip(";")
                # 分割并清理空格/空值
                mesum_antique_categories = [dynasty.strip() for dynasty in categories_text.split(";") if dynasty.strip()]

        finally:
            pass
        categories = [category.category
                      for category in (
                          cls.model.select(cls.model.category)
                          .where(cls.model.mesum_id==mesum_id)
                          .distinct()
                          .execute()
                      )
                      if category.category
                     ]
        # 下面代码是按照博物馆brief定义的目录顺序调整输出的目录顺序，以便前端能够按照正确顺序显示
        # cyx  20250415
        # 创建字典映射元素到索引，提升查询效率
        mesum_antique_categories_dict = {value: idx for idx, value in enumerate(mesum_antique_categories)}
        # 排序逻辑：通过查字典获取顺序号，不在字典的给极大值（排最后）
        categories_sorted = sorted(
            categories,
            key=lambda item: mesum_antique_categories_dict.get(item, len(mesum_antique_categories))  # 查字典获取顺序号
        )
        return categories_sorted

    @classmethod
    @DB.connection_context()
    def get_all_labels(cls):
        # 查询所有去重后的label
        labels = [label.label for label in cls.model.select(cls.model.label).distinct().execute() if label.label]
        return labels

    @classmethod
    @DB.connection_context()
    def get_labels_ext(cls, mesum_id):
        # 根据mesum_id过滤，并排除空的category
        query = cls.model.select().where(
            (cls.model.mesum_id == mesum_id) &
            (cls.model.category != "")
        ).order_by(cls.model.category)

        # 按category分组并存储结果
        grouped_data = {}
        for obj in query.dicts().execute():
            category = obj['category']
            if category not in grouped_data:
                grouped_data[category] = []
            grouped_data[category].append({
                'id': obj['id'],
                'label': obj['label']
            })

        return grouped_data

    @classmethod
    @DB.connection_context()
    def get_labels_with_id(cls, mesum_id):
        # 根据mesum_id过滤，并排除空的category
        query = cls.model.select().where(
            (cls.model.mesum_id == mesum_id)
        ).order_by(cls.model.id)

        # 将label和关联的id 一并返回
        labels_data = []
        for obj in query.dicts():
            labels_data.append({
                'id': obj['id'],
                'label': obj['label']
            })

        return labels_data

    @classmethod
    @DB.connection_context()
    def get_antique_by_id(cls, mesum_id,antique_id):

        query = cls.model.select().where(
            (cls.model.mesum_id == mesum_id) &
            (cls.model.id == antique_id)
        )

        data = []
        for obj in query.dicts().execute():
            data.append(obj)
        if len(data) > 0:
            data = data[0]
        return data