1、默认的分词器
standard
standard tokenizer:以单词边界进行切分
standard token filter:什么都不做
lowercase token filter:将所有字母转换为小写
stop token filer(默认被禁用):移除停用词,比如a the it等等
2、修改分词器的设置
PUT /my_index
{
"settings": {
"analysis": {
"analyzer": {
"es_std": {
"type": "standard",
"stopwords": "_english_"
}
}
}
}
}
3、定制化自己的分词器
PUT /my_index
{
"settings": {
"analysis": {
"char_filter": {
"&_to_and": {
"type": "mapping",
"mappings": [
"&=> and"
]
}
},
"filter": {
"my_stopwords": {
"type": "stop",
"stopwords": [
"the",
"a"
]
}
},
"analyzer": {
"my_analyzer": {
"type": "custom",
"char_filter": [
"html_strip",
"&_to_and"
],
"tokenizer": "standard",
"filter": [
"lowercase",
"my_stopwords"
]
}
}
}
}
}
PUT /my_index/_mapping/my_type
{
"properties": {
"content": {
"type": "text",
"analyzer": "my_analyzer"
}
}
}