ES支持中文&&全拼&&拼音首字母搜索_es使用首字母和全拼混合搜索-CSDN博客

这篇博客介绍了如何在Elasticsearch环境中设置搜索模板，新建索引，并实现中文、全拼和拼音首字母的搜索功能。通过设置filter实现结果过滤，结合ID倒序展示。同时，分享了部分相关Java代码片段，尽管遇到一些问题，但博主提供了参考资料以供解决。

环境

Ubuntu18.04
ES 6.6.1

搜索模板

新建模板，便于后续创建索引，直接使用模板，省事方便

PUT _template/goods
{
  "index_patterns":"goods*",
  "settings": {
    "index.number_of_replicas": "1",
    "index.number_of_shards": "5",
    "index.translog.flush_threshold_size": "512mb",
    "index.translog.sync_interval": "60s",
    "index.codec": "best_compression",
    "analysis": {
      "filter": {
        "edge_ngram_filter": {
          "type": "edge_ngram",
          "min_gram": 1,
          "max_gram": 50
        },
        "simple_pinyin_filter": {
          "type": "pinyin",
          "keep_first_letter": true,
          "keep_separate_first_letter": false,
          "keep_full_pinyin": false,
          "keep_original": false,
          "limit_first_letter_length": 50,
          "lowercase": true
        },
        "full_pinyin_filter": {
          "type": "pinyin",
          "keep_first_letter": false,
          "keep_separate_first_letter": false,
          "keep_full_pinyin": true,
          "none_chinese_pinyin_tokenize": true,
          "keep_original": false,
          "limit_first_letter_length": 50,
          "lowercase": true
        }
      },
      "char_filter": {
        "charconvert": {
          "type": "mapping",
          "mappings_path": "char_filter_text.txt"
        }
      },
      "tokenizer": {
        "ik_max_word": {
          "type": "ik_max_word",
          "use_smart": true
        }
      },
      "analyzer": {
        "ngramIndexAnalyzer": {
          "type": "custom",
          "tokenizer": "keyword",
          "filter": [
            "edge_ngram_filter",
            "lowercase"
          ],
          "char_filter": [
            "charconvert"
          ]
        },
        "ngramSearchAnalyzer": {
          "type": "custom",
          "tokenizer": "keyword",
          "filter": [
            "lowercase"
          ],
          "char_filter": [
            "charconvert"
          ]
        },
        "ikIndexAnalyzer": {
          "type": "custom",
          "tokenizer": "ik_max_word",
          "char_filter": [
            "charconvert"
          ]
        },
        "ikSearchAnalyzer": {
          "type": "custom",
          "tokenizer": "ik_max_word",
          "char_filter": [
            "charconvert"
          ]
        },
        "simplePinyinIndexAnalyzer": {
          "tokenizer": "keyword",
          "filter": [
            "simple_pinyin_filter",
            "edge_ngram_filter",
            "lowercase"
          ]
        },
        "simplePinyinSearchAnalyzer": {
          "tokenizer": "keyword",
          "filter": [
            "simple_pinyin_filter",
            "lowercase"
          ]
        },
        "fullPinyinIndexAnalyzer": {
          "tokenizer": "keyword",
          "filter": [
            "full_pinyin_filter",
            "edge_ngram_filter",
            "lowercase"
          ]
        },
        "fullPinyinSearchAnalyzer": {
          "tokenizer": "keyword",
          "filter": [
            "full_pinyin_filter",
            "lowercase"
          ]
        }
      }
    }
  }
}

新建 char_filter_text.txt 存于 ES_HOME/config 目录下。可以把相关部分删除。

新建索引

goods_v1 将使用上述模板（goods*），可直接使用模板中定义的 analyzer

DELETE goods_v1

PUT /goods_v1
{
  "mappings": {
    "doc":{
      "properties" : {
        "id":{
          "type":"long"
        },
        "name" : {
          "type": "text", 
          "analyzer": "ikIndexAnalyzer",
          "fields": {
            "ngram": {
              "type": "text", 
              "analyzer": "ngramIndexAnalyzer"
            },
            "SPY": {
              "type": "text", 
              "analyzer": "simplePinyinIndexAnalyzer"
            },
            "FPY": {
              "type": "text", 
              "analyzer": "fullPinyinIndexAnalyzer"
            }
          }
        },
        "update_time" : {
          "type":"date"
        },
        "deleted" : {
          "type":"boolean"
        }
      }
    }
  }
}

PUT /goods_v1/_alias/goods
{ 
  "is_write_index":true
}

filter&&结果id倒序

本搜索只做简单过滤，并且按id倒序返回，不需要计算相似度

GET goods/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "bool": {
          "filter": [
            {
              "term": {
                "deleted": {
                  "value": false,
                  "boost": 1
                }
              }
            },
            {
              "bool": {
                "should": [
                  {
                    "match": {
                      "name.ngram": {
                        "query": "水果",
                        "operator": "OR",
                        "analyzer": "ngramSearchAnalyzer",
                        "prefix_length": 0,
                        "max_expansions": 50,
                        "fuzzy_transpositions": true,
                        "lenient": false,
                        "zero_terms_query": "NONE",
                        "auto_generate_synonyms_phrase_query": true,
                        "boost": 5
                      }
                    }
                  },
                  {
                    "term": {
                      "name.SPY": {
                        "value": "水果",
                        "boost": 1
                      }
                    }
                  },
                  {
                    "wildcard": {
                      "name.SPY": {
                        "wildcard": "*水果*",
                        "boost": 0.8