Question

我无法弄清楚如何查找带有特殊字符的单词。

例如，我有两个文件：

1）我们正在寻找C ++和C＃开发人员 2）我们正在寻找C开发人员

我只想找到一个包含C++的文档。

创建索引，文档和搜索的代码：

from elasticsearch import Elasticsearch
from elasticsearch.helpers import scan

ELASTIC_SEARCH_NODES = ['http://localhost:9200']

INDEX = 'my_index'
DOC_TYPE = 'material'


def create_index():
    data = {
       "settings": {
          "analysis": {
             "analyzer": {
                "my_analyzer": {
                   "type": "custom",
                   "filter": [
                      "lowercase"
                   ],
                   "tokenizer": "whitespace",
                }
             }
          }
       }
    }

    print es_client.indices.create(index=INDEX, body=data)


def create_doc(body):

    if es_client.exists(INDEX, DOC_TYPE, body['docid']):
        es_client.delete(INDEX, DOC_TYPE, body['docid'])

    print es_client.create(index=INDEX, doc_type=DOC_TYPE, body=body, id=body['docid'])


def find_doc(value):
     results_generator = scan(es_client,
            query={"query": {

                    "match_phrase" : {
                        "text" : value
                    }

            }},
            index=INDEX
        )
     return results_generator


if __name__ == '__main__':
    es_client = Elasticsearch(ELASTIC_SEARCH_NODES, verify_certs=True)

    # create_index()
    doc1 = {"docid": 1, 'text': u"We are looking for C developers"}
    doc2 = {"docid": 2, 'text': u"We are looking for C++ and C# developers"}

    # create_doc(doc1)
    # create_doc(doc2)

    for r in find_doc("C++"):
        print r

搜索结果（如果我escape +（"C\+\+"），结果将是相同的）：

{u'_score': 0.0, u'_type': u'material', u'_id': u'2', u'_source': {u'text': u'We are looking for C++ and C# developers', u'docid': 2}, u'_index': u'my_index'}
{u'_score': 0.0, u'_type': u'material', u'_id': u'1', u'_source': {u'text': u'We are looking for C developers', u'docid': 1}, u'_index': u'my_index'}

似乎获得了这样的结果，因为在划分为+和# not indexed等令牌符号时，事实上，它会查找有符号的文档C：

curl 'http://localhost:9200/my_index/material/_search?pretty=true' -d '{
    "query" : {
        "match_all" : { }
    },
    "script_fields": {
        "terms" : {
            "script": "doc[field].values",
            "params": {
                "field": "text"
            }
        }
    }
}'

结果：

{
  "took" : 3,
  "timed_out" : false,
  "_shards" : {
    "total" : 5,
    "successful" : 5,
    "failed" : 0
  },
  "hits" : {
    "total" : 2,
    "max_score" : 1.0,
    "hits" : [ {
      "_index" : "my_index",
      "_type" : "material",
      "_id" : "2",
      "_score" : 1.0,
      "fields" : {
        "terms" : [ "and", "are", "c", "developers", "for", "looking", "we" ]
      }
    }, {
      "_index" : "my_index",
      "_type" : "material",
      "_id" : "1",
      "_score" : 1.0,
      "fields" : {
        "terms" : [ "are", "c", "developers", "for", "looking", "we" ]
      }
    }]
  }
}

如何解决这个问题？与上一个问题相关的第二个问题是：是否可以仅搜索非%或+等非字母数字字符？

P.S。我使用的是Elastic 2.3.2和elasticsearch = 2.3.0。

Answer 1

谢谢Andrew，我解决了这个问题。问题是标准分析器用于索引，而不是 my_analyzer 。因此，我忘了使用映射。正确的版本：

data = {
   "settings": {
      "analysis": {
         "analyzer": {
            "my_analyzer": {
               "type": "custom",
               "filter": [
                  "lowercase"
               ],
               "tokenizer": "whitespace",
            }
         }
      }
   },
   "mappings": {
       "material": {
           "properties": {
               "docid": {
                   "type": "integer"
               },
               "text": {
                   "type": "string",
                   "analyzer": "my_analyzer"
               }
           }
       }
   }
}

此外，还需要重新创建索引并添加文档。要搜索特殊字符，我使用query_string。代码find_doc功能：

def find_doc(value):
     results_generator = scan(es_client,
            query=
            {
                "query": {
                    "filtered" : {
                        "query" : {
                            "query_string" : {
                                "query": value,
                                "fields" : ["text"],
                                "analyzer": ANALYZER,
                                "default_operator": "AND"
                            },

                        }
                    }

                }
            },
            index=INDEX
        )
     return results_generator

查询示例（现在可以使用wildcard-characters）：

for r in find_doc("*#"):
    print r

for r in find_doc(u"%"):
    print r

for r in find_doc("looking fo*"):
    print r

请求验证分析器（令牌字符串被破坏）：

curl -XPOST "http://localhost:9200/my_index/_analyze?analyzer=my_analyzer&pretty=true" -d 'We are looking for C++ and C# developers'

ElasticSearch和特殊字符

1 个答案: