查看不同的analyzer的效果
#Simple Analyzer – 按照非字母切分(符号被过滤),小写处理
#Stop Analyzer – 小写处理,停用词过滤(the,a,is)
#Whitespace Analyzer – 按照空格切分,不转小写
#Keyword Analyzer – 不分词,直接将输入当作输出
#Patter Analyzer – 正则表达式,默认 \W+ (非字符分隔)
#Language – 提供了30多种常见语言的分词器
#2 running Quick brown-foxes leap over lazy dogs in the summer evening
#查看不同的analyzer的效果
#standard
GET _analyze
{
"analyzer": "standard",
"text": "2 running Quick brown-foxes leap over lazy dogs in the summer evening."
}
#simpe
GET _analyze
{
"analyzer": "simple",
"text": "2 running Quick brown-foxes leap over lazy dogs in the summer evening."
}
#stop
GET _analyze
{
"analyzer": "stop",
"text": "2 running Quick brown-foxes leap over lazy dogs in the summer evening."
}
#whitespace
GET _analyze
{
"analyzer": "whitespace",
"text": "2 running Quick brown-foxes leap over lazy dogs in the summer evening."
}
#keyword
GET _analyze
{
"analyzer": "keyword",
"text": "2 running Quick brown-foxes leap over lazy dogs in the summer evening."
}
GET _analyze
{
"analyzer": "pattern",
"text": "2 running Quick brown-foxes leap over lazy dogs in the summer evening."
}
#english
GET _analyze
{
"analyzer": "english",
"text": "2 running Quick brown-foxes leap over lazy dogs in the summer evening."
}
POST _analyze
{
"analyzer": "icu_analyzer",
"text": "他说的确实在理”"
}
POST _analyze
{
"analyzer": "standard",
"text": "他说的确实在理”"
}
POST _analyze
{
"analyzer": "icu_analyzer",
"text": "这个苹果不大好吃"
}
PUT logs/_doc/1
{"level":"DEBUG"}
GET /logs/_mapping
POST _analyze
{
"tokenizer":"keyword",
"char_filter":["html_strip"],
"text": "<b>hello world</b>"
}
POST _analyze
{
"tokenizer":"path_hierarchy",
"text":"/user/ymruan/a/b/c/d/e"
}
#使用char filter进行替换
POST _analyze
{
"tokenizer": "standard",
"char_filter": [
{
"type" : "mapping",
"mappings" : [ "- => _"]
}
],
"text": "123-456, I-test! test-990 650-555-1234"
}
# char filter 替换表情符号
POST _analyze
{
"tokenizer": "standard",
"char_filter": [
{
"type" : "mapping",
"mappings" : [ ":) => happy", ":( => sad"]
}
],
"text": ["I am felling :)", "Feeling :( today"]
}
# white space and snowball
GET _analyze
{
"tokenizer": "whitespace",
"filter": ["stop","snowball"],
"text": ["The gilrs in China are playing this game!"]
}
# whitespace与stop
GET _analyze
{
"tokenizer": "whitespace",
"filter": ["stop","snowball"],
"text": ["The rain in Spain falls mainly on the plain."]
}
# remove 加入lowercase后,The被当成 stopword删除
GET _analyze
{
"tokenizer": "whitespace",
"filter": ["lowercase","stop","snowball"],
"text": ["The gilrs in China are playing this game!"]
}
# 正则表达式
GET _analyze
{
"tokenizer": "standard",
"char_filter": [
{
"type" : "pattern_replace",
"pattern" : "http://(.*)",
"replacement" : "$1"
}
],
"text" : "http://www.elastic.co"
}
DELETE logs