0

我正在尝试从包含多个单词的短语中实现自动完成功能。

我希望能够仅匹配单词的开头（edgeNGram？），但要匹配每个搜索的单词。

例如，如果我搜索“monitor”，我应该收到所有包含单词 monitor 的短语，但如果我搜索“onitor”，我应该没有匹配项（来自下面的数据集）。例如，搜索“mon ap”应该给我“APNEA MONITOR-SCHULTE Vital Signs Monitor”，而“mon rrr”应该没有结果。

所以我的问题是我应该如何去实施它？

简而言之：匹配的短语应该包含以搜索词开头的词。

这是我的映射：

{
    "quicksearch2" : {
        "results" : {
            "properties" : {       
                "phrase" : {
                    "type" : "string",
                    "index_analyzer" : "quicksearch_index_analyzer",
                    "search_analyzer" : "quicksearch_search_analyzer"
                }        
            }
        }
    }
}

这是我的设置：

{
    "quicksearch2" : {
        "settings" : {
            "index.analysis.analyzer.quicksearch_index_analyzer.filter.4" : "left_ngram",
            "index.analysis.analyzer.quicksearch_search_analyzer.filter.3" : "unique",
            "index.analysis.analyzer.quicksearch_index_analyzer.filter.3" : "unique",
            "index.analysis.filter.left_ngram.max_gram" : "20",
            "index.analysis.analyzer.quicksearch_search_analyzer.filter.2" : "asciifolding",
            "index.analysis.analyzer.quicksearch_search_analyzer.tokenizer" : "keyword",
            "index.analysis.analyzer.quicksearch_search_analyzer.filter.1" : "lowercase",
            "index.number_of_replicas" : "0",
            "index.analysis.analyzer.quicksearch_search_analyzer.filter.0" : "trim",
            "index.analysis.filter.left_ngram.type" : "edgeNGram",
            "index.analysis.analyzer.quicksearch_search_analyzer.type" : "custom",
            "index.analysis.analyzer.quicksearch_index_analyzer.filter.0" : "trim",
            "index.analysis.analyzer.quicksearch_index_analyzer.filter.2" : "asciifolding",
            "index.analysis.analyzer.quicksearch_index_analyzer.filter.1" : "lowercase",
            "index.analysis.analyzer.quicksearch_index_analyzer.type" : "custom",
            "index.analysis.filter.left_ngram.side" : "front",
            "index.analysis.analyzer.quicksearch_index_analyzer.tokenizer" : "keyword",
            "index.number_of_shards" : "1",
            "index.version.created" : "900899",
            "index.uuid" : "Lb7vC-eHQB-u_Okm3ERLow"
        }
    }
}

这是我的查询：

query: {
    match: {
        phrase: {
            query: term,
            operator: 'and'
        }
}

一些样本数据：

{
    "took" : 133,
    "timed_out" : false,
    "_shards" : {
        "total" : 1,
        "successful" : 1,
        "failed" : 0
    },
    "hits" : {
        "total" : 6197,
        "max_score" : 1.491863,
        "hits" : [ {
            "_index" : "quicksearch2",
            "_type" : "results",
            "_id" : "emCydgTfQwuKkl4sSZoosQ",
            "_score" : 1.491863,
            "fields" : {
                "phrase" : "APNEA MONITOR- SCHULTE Apnea Monitor"
            }
        }, {
            "_index" : "quicksearch2",
            "_type" : "results",
            "_id" : "AXCO5rUxRwC9SebXcQxXeQ",
            "_score" : 1.491863,
            "fields" : {
                "phrase" : "APNEA MONITOR- SCHULTE Apnea Monitor, Neonatal"
            }
        }, {
            "_index" : "quicksearch2",
            "_type" : "results",
            "_id" : "tjJq3klPTsmP8akOc18Htw",
            "_score" : 1.491863,
            "fields" : {
                "phrase" : "APNEA MONITOR- SCHULTE Apnea Monitor, Recording"
            }
        }, {
            "_index" : "quicksearch2",
            "_type" : "results",
            "_id" : "-FjKWxl9Rm6-byn-wlpoIw",
            "_score" : 1.491863,
            "fields" : {
                "phrase" : "APNEA MONITOR- SCHULTE Cardiorespiratory Monitor"
            }
        }, {
            "_index" : "quicksearch2",
            "_type" : "results",
            "_id" : "Q19k6V6VQ6ulZOLCfESQ6w",
            "_score" : 1.491863,
            "fields" : {
                "phrase" : "APNEA MONITOR- SCHULTE Impedance Pneumograph Bedside Monitor"
            }
        }, {
            "_index" : "quicksearch2",
            "_type" : "results",
            "_id" : "YLI1er3cRjSyGumWNVi0pg",
            "_score" : 1.491863,
            "fields" : {
                "phrase" : "APNEA MONITOR- SCHULTE Impedance Pneumograph Monitor"
            }
        }, {
            "_index" : "quicksearch2",
            "_type" : "results",
            "_id" : "n5j1SaXeS2W6NymaYAYD6A",
            "_score" : 1.491863,
            "fields" : {
                "phrase" : "APNEA MONITOR- SCHULTE Neonatal Monitor"
            }
        }, {
            "_index" : "quicksearch2",
            "_type" : "results",
            "_id" : "U7Q5XrrHRbKOIwfRWO6RTQ",
            "_score" : 1.491863,
            "fields" : {
                "phrase" : "APNEA MONITOR- SCHULTE Pulmonary Function Monitor"
            }
        }, {
            "_index" : "quicksearch2",
            "_type" : "results",
            "_id" : "aF_THiCKRIyzunCbBxJTEg",
            "_score" : 1.491863,
            "fields" : {
                "phrase" : "APNEA MONITOR- SCHULTE Vital Signs Monitor"
            }
        }, {
            "_index" : "quicksearch2",
            "_type" : "results",
            "_id" : "8BAjZfwMQjWmrkqCO7o6gg",
            "_score" : 1.491863,
            "fields" : {
                "phrase" : "P.P.M. - PORTABLE PRECISION MONITOR Gas Monitor, Atmospheric"
            }
        } ]
    }
}
4

2 回答 2

1

我不太确定为什么您正在做的事情不起作用，但是这里有一种方法似乎可以满足您的要求。

我用这些设置创建了一个索引：

curl -XPUT "http://localhost:9200/test_index " -d'
{
   "settings": {
      "analysis": {
         "filter": {
            "my_edge_ngram_filter": {
               "type": "edgeNGram",
               "min_gram": 2,
               "max_gram": 20,
               "token_chars": [
                  "letter",
                  "digit"
               ]
            }
         },
         "analyzer": {
            "my_ngram_analyzer": {
               "type": "custom",
               "tokenizer": "whitespace",
               "filter": [
                  "lowercase",
                  "asciifolding",
                  "my_edge_ngram_filter"
               ]
            },
            "my_whitespace_analyzer": {
               "type": "custom",
               "tokenizer": "whitespace",
               "filter": [
                  "lowercase",
                  "asciifolding"
               ]
            }
         }
      }
   },
   "mappings": {
      "docs": {
         "properties": {
            "phrase": {
               "type": "string",
               "index_analyzer": "my_ngram_analyzer",
               "search_analyzer": "my_whitespace_analyzer"
            }
         }
      }
   }
}'

然后添加您列出的文档：

curl -XPOST "http://localhost:9200/test_index/_bulk " -d'
{ "index" : { "_index" : "test_index", "_type" : "docs", "_id" : "1" } }
{ "phrase" : "APNEA MONITOR- SCHULTE Apnea Monitor" }
{ "index" : { "_index" : "test_index", "_type" : "docs", "_id" : "2" } }
{ "phrase" : "APNEA MONITOR- SCHULTE Apnea Monitor, Neonatal" }
{ "index" : { "_index" : "test_index", "_type" : "docs", "_id" : "3" } }
{ "phrase" : "APNEA MONITOR- SCHULTE Apnea Monitor, Recording" }
{ "index" : { "_index" : "test_index", "_type" : "docs", "_id" : "4" } }
{ "phrase" : "APNEA MONITOR- SCHULTE Cardiorespiratory Monitor" }
{ "index" : { "_index" : "test_index", "_type" : "docs", "_id" : "5" } }
{ "phrase" : "APNEA MONITOR- SCHULTE Impedance Pneumograph Bedside Monitor" }
{ "index" : { "_index" : "test_index", "_type" : "docs", "_id" : "6" } }
{ "phrase" : "APNEA MONITOR- SCHULTE Impedance Pneumograph Monitor" }
{ "index" : { "_index" : "test_index", "_type" : "docs", "_id" : "7" } }
{ "phrase" : "APNEA MONITOR- SCHULTE Neonatal Monitor" }
{ "index" : { "_index" : "test_index", "_type" : "docs", "_id" : "8" } }
{ "phrase" : "APNEA MONITOR- SCHULTE Pulmonary Function Monitor" }
{ "index" : { "_index" : "test_index", "_type" : "docs", "_id" : "9" } }
{ "phrase" : "APNEA MONITOR- SCHULTE Vital Signs Monitor" }
{ "index" : { "_index" : "test_index", "_type" : "docs", "_id" : "10" } }
{ "phrase" : "P.P.M. - PORTABLE PRECISION MONITOR Gas Monitor, Atmospheric" }
'

以下搜索似乎返回了您期望的结果：

curl -XPOST "http://localhost:9200/test_index/_search" -d'
{
    "query": {
        "match": {
           "phrase" : {
               "query": "monitor",
               "operator": "and"
           }
        }
    }
}'

返回所有文档，

curl -XPOST "http://localhost:9200/test_index/_search" -d'
{
    "query": {
        "match": {
           "phrase" : {
               "query": "onitor",
               "operator": "and"
           }
        }
    }
}'

不返回任何内容，并且

curl -XPOST "http://localhost:9200/test_index/_search" -d'
{
    "query": {
        "match": {
           "phrase" : {
               "query": "mon ap",
               "operator": "and"
           }
        }
    }
}'

返回除 document 之外的所有内容"10"。

这是一个您可以使用的可运行示例（您需要在 localhost:9200 安装和运行 ES，或提供另一个端点）：http ://sense.qbox.io/gist/19fdcdb20c24436c64b7656c3b8002fe78667b12

于 2014-01-09T18:14:27.903 回答
0

将标记器（索引和搜索）从关键字更改为标准似乎已经成功了。

于 2014-01-13T06:24:12.337 回答