elasticsearch 分词器变换全角和半角以及数字串模糊匹配

最新推荐文章于 2025-02-13 15:21:11 发布

会发paper的学渣

最新推荐文章于 2025-02-13 15:21:11 发布

阅读量1.8k

点赞数

分类专栏： elasticsearch

本文链接：https://blog.youkuaiyun.com/sslfk/article/details/121768547

版权

elasticsearch 大数据 big data 搜索引擎全文检索

elasticsearch 专栏收录该内容

16 篇文章

订阅专栏

本文探讨了信息技术中最新的代码分词技术，通过实例展示如何使用code_split_ngram_analyzer进行高效分析，以及其在提高代码理解与搜索引擎优化中的应用。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

{
    "mappings": {
        "properties": {
            "cellphone": {
                "type": "text",
                "analyzer": "code_split_ngram_analyzer"
            },
            "tag": {
                "type": "text",
                "analyzer": "char_standard_analyzer",
                "fields": {
                    "keyword": {
                        "type": "keyword",
                        "normalizer": "my_normalizer",
                        "ignore_above": 256
                    }
                }
            }
        }
    },
    "settings": {
        "index": {
            "max_ngram_diff": "5",
            "refresh_interval": "1m",
            "number_of_shards": "2",
            "analysis": {
                "normalizer": {
                    "my_normalizer": {
                        "type": "custom",
                        "filter": [
                            "lowercase",
                            "asciifolding"
                        ]
                    }
                },
                "analyzer": {
                    "code_split_ngram_analyzer": {
                        "filter": [
                            "lowercase"
                        ],
                        "type": "custom",
                        "tokenizer": "code_split_ngram_tokenizer"
                    },
                    "char_standard_analyzer": {
                        "filter": [
                            "lowercase",
                            "asciifolding"
                        ],
                        "tokenizer": "standard"
                    }
                },
                "tokenizer": {
                    "code_split_ngram_tokenizer": {
                        "token_chars": [
                            "letter",
                            "digit"
                        ],
                        "min_gram": "3",
                        "type": "ngram",
                        "max_gram": "6"
                    }
                }
            }
        }
    }
}