我如何告诉 ElasticSearch 多匹配查询我想要存储为字符串的数字字段与数字字符串 return 匹配？

Question

我正在编写一个 Flask 应用程序，我正在使用 elasticsearch。

这里是search.py:

from flask import current_app

def query_object(index, fields, query, page, per_page, fuzziness=0):
    search = current_app.elasticsearch.search(
        index=index,
        body={'query': {'multi_match': {'query': str(query), 'fields': fields, 'fuzziness': fuzziness, 'lenient': True}},
                'from': (page - 1) * per_page, 'size': per_page}
    )

    ids = [int(hit['_id']) for hit in search['hits']['hits']]
    return ids, search['hits']['total']['value']

以下型号已编入索引：

class WishList(db.Model, SearchableMixin):
    __searchable__ = ['first_name', 'gender', 'wants', 'needs', 'wear',
    'read', 'shoe_size_category', 'shoe_type', 'sheet_size', 'additional_comments', 'time_chosen',
    'age', 'shoe_sock_size', 'program_number']

    id = db.Column(db.Integer, primary_key=True)
    program_number = db.Column(db.String(4))
    first_name = db.Column(db.String(20))
    age = db.Column(db.String(10))
    gender = db.Column(db.String(20))
    wants = db.Column(db.String(300))
    needs = db.Column(db.String(300))
    wear = db.Column(db.String(300))
    read = db.Column(db.String(300))
    pant_dress_size = db.Column(db.String(20), default='unspecified')
    shirt_blouse_size = db.Column(db.String(20), default='unspecified')
    jacket_sweater_size = db.Column(db.String(20), default='unspecified')
    shoe_sock_size = db.Column(db.String(20), default='unspecified')
    shoe_size_category = db.Column(db.String(20), default='unspecified')
    shoe_type = db.Column(db.String(50), default='unspecified')
    sheet_size = db.Column(db.String(20), default='unspecified')
    additional_comments = db.Column(db.Text(), nullable=True, default=None)
    time_chosen = db.Column(db.String(40), nullable=True, default=None)
    sponsor_id = db.Column(db.Integer, db.ForeignKey(
        'user.id'), nullable=True, default=None)
    drive_id = db.Column(db.Integer, db.ForeignKey(
        'holiday_cheer_drive.id'), nullable=False, default=None)

通过继承 SearchableMixin class 使该模型可搜索，如下所示：

class SearchableMixin(object):
    @classmethod
    def search_object(cls, fields, expression, page, per_page, fuzziness=0):
        ids, total = query_object(
            cls.__tablename__, fields, expression, page, per_page, fuzziness=fuzziness)
        if total == 0:
            return cls.query.filter_by(id=0), 0
        when = []
        for i in range(len(ids)):
            when.append((ids[i], i))
        return cls.query.filter(cls.id.in_(ids)).order_by(
            db.case(when, value=cls.id)), total

当我当前搜索时，所有字段都是可搜索的并且 return 一个有效的结果，除非我使用数字值进行搜索。

这是一个搜索输出示例，当我告诉 python 将值打印到控制台时，该搜索有效：

Query: bob
Body of search:
{'from': 0,
 'query': {'multi_match': {'fields': ['first_name',
                                      'gender',
                                      'wants',
                                      'needs',
                                      'wear',
                                      'read',
                                      'shoe_size_category',
                                      'shoe_type',
                                      'sheet_size',
                                      'additional_comments',
                                      'time_chosen',
                                      'age',
                                      'shoe_sock_size',
                                      'program_number'],
                           'fuzziness': 0,
                           'lenient': True,
                           'query': 'bob'}},
 'size': 10}
Python elasticsearch object:
{'took': 27, 'timed_out': False, '_shards': {'total': 1, 'successful': 1, 'skipped': 0, 'failed': 0}, 'hits': {'total': {'value': 2, 'relation': 'eq'}, 'max_score': 1.6916759, 'hits': [{'_index': 'wish_list', '_type': '_doc', '_id': '1', '_score': 1.6916759, '_source': {'first_name': 'bob', 'gender': 'male', 'wants': 'bike', 'needs': 'calculator', 'wear': 'hat', 'read': 'book', 'shoe_size_category': "men's", 'shoe_type': 'sneaker', 'sheet_size': 'unspecified', 'additional_comments': 'Likes cheese', 'time_chosen': None, 'age': '5', 'shoe_sock_size': '4', 'program_number': '215', 'mappings': {'properties': {'first_name': {'type': 'text'}, 'gender': {'type':
'text'}, 'wants': {'type': 'text'}, 'needs': {'type': 'text'}, 'wear': {'type': 'text'}, 'read': {'type': 'text'}, 'shoe_size_category': {'type': 'text'}, 'shoe_type': {'type': 'text'}, 'sheet_size': {'type': 'text'}, 'additional_comments': {'type': 'text'}, 'time_chosen': {'type': 'text'}, 'age': {'type': 'text'}, 'shoe_sock_size': {'type': 'text'}, 'program_number': {'type': 'text'}}}}}, {'_index': 'wish_list', '_type': '_doc', '_id': '9', '_score': 1.6916759, '_source': {'first_name': 'bob', 'gender': 'male', 'wants': 'bike', 'needs': 'calculator', 'wear': 'hat', 'read': 'book', 'shoe_size_category': "men's", 'shoe_type': 'sneaker', 'sheet_size': 'unspecified', 'additional_comments': 'Likes cheese', 'time_chosen': None, 'age': 5, 'shoe_sock_size': 4, 'program_number': 215, 'mappings': {'properties': {'first_name': {'type': 'text'}, 'gender': {'type': 'text'}, 'wants': {'type': 'text'}, 'needs': {'type': 'text'}, 'wear': {'type': 'text'}, 'read': {'type': 'text'}, 'shoe_size_category': {'type': 'text'}, 'shoe_type': {'type': 'text'}, 'sheet_size': {'type': 'text'}, 'additional_comments': {'type': 'text'}, 'time_chosen': {'type': 'text'}, 'age': {'type': 'text'}, 'shoe_sock_size': {'type': 'text'}, 'program_number': {'type': 'text'}}}}}]}}

下面是针对同一对象的完全相同的查询，但使用的是数字字符串：

Query: 215
Body of search:
{'from': 0,
 'query': {'multi_match': {'fields': ['first_name',
                                      'gender',
                                      'wants',
                                      'needs',
                                      'wear',
                                      'read',
                                      'shoe_size_category',
                                      'shoe_type',
                                      'sheet_size',
                                      'additional_comments',
                                      'time_chosen',
                                      'age',
                                      'shoe_sock_size',
                                      'program_number'],
                           'fuzziness': 0,
                           'lenient': True,
                           'query': '215'}},
 'size': 10}
Python elasticsearch object:
{'took': 18, 'timed_out': False, '_shards': {'total': 1, 'successful': 1, 'skipped': 0, 'failed': 0}, 'hits': {'total': {'value': 0, 'relation': 'eq'}, 'max_score': None, 'hits': []}}

正在向函数中传递一个字符串，数据全部保存为字符串，但似乎存在某种类型错误。在我添加 lenient: True 之前，它抛出了一个错误，说 elasticsearch 无法构建查询。

如果我能理解我将如何使用 elasticsearch REST API，那么我可能会弄清楚如何使用 python。

Answer 1

问题是由于在 numeric 数据类型上使用了 fuzziness 参数，然后使用 lenient true 使其工作 removes format-based errors, such as providing a text query value for a numeric field, are ignored. 在 this link.

中提到

以下是您在尝试对数字数据类型使用 fuzziness 时遇到的错误。

reason": "Can only use fuzzy queries on keyword and text fields - not on [age] which is of type [integer]"

当您添加 "lenient" : true 时，会出现上述错误，但不会 return 任何文档。

要让它工作，只需从搜索查询中删除 fuzziness 和 lenient 参数，它应该会工作，因为 Elasticsearch 会自动将有效的 string 转换为 numeric 和反之亦然，如 coerce 文章所述。

使用 REST 展示它的工作示例API

索引定义

{
    "mappings": {
        "properties": {
            "age" :{
                "type" : "integer"
            }
        }
    }
}

索引示例文档

{
  "age" : "25" --> note use of `""`, sending it as string
}

{
  "age" : 28 :- note sending numneric value
}

字符串格式的搜索查询

{
    "query": {
        "bool": {
            "must": [
                {
                    "multi_match": {
                        "query": "28", --> note string format
                        "fields": [
                            "age" --> note you can add more fields
                        ]
                    }
                }
            ]
        }
    }
}

搜索结果

"hits": [
      {
        "_index": "so_numberic",
        "_type": "_doc",
        "_id": "1",
        "_score": 1.0,
        "_source": {
          "program_number": "123456789",
          "age": "28"
        }
      }
    ]

以数字格式搜索查询

{
    "query": {
        "match" : { --> query on single field.
            "age" : {
                "query" : 28 --> note numeric format
            }
        }
    }
}

结果

"hits": [
      {
        "_index": "so_numberic",
        "_type": "_doc",
        "_id": "1",
        "_score": 1.0,
        "_source": {
          "program_number": "123456789",
          "age": "28"
        }
      }
    ]

显示您的 fuzziness 和 lenient 并没有像之前解释的那样带来任何结果。

搜索查询

{
    "query": {
        "match": {
            "age": {
                "query": 28,
                "fuzziness": 2,
                "lenient": true
            }
        }
    }
}

结果

{
    "took": 1,
    "timed_out": false,
    "_shards": {
        "total": 1,
        "successful": 1,
        "skipped": 0,
        "failed": 0
    },
    "hits": { --> note 0 results.
        "total": {
            "value": 0,
            "relation": "eq"
        },
        "max_score": null,
        "hits": []
    }
}

我如何告诉 ElasticSearch 多匹配查询我想要存储为字符串的数字字段与数字字符串 return 匹配？

How do I tell an ElasticSearch multi-match query that I want numeric fields, stored as strings, to return matches with numeric strings?

python

elasticsearch

flask-sqlalchemy

elasticsearch-query