问题描述
我们自定义拓展词库更改后,原先的索引文档中的数据,由于不是新插入的数据,所以其倒排索引列表还是原先的分词列表数据,导致就算拓展了词库,新增的分词也没有生效。在不重新导入数据的前提下,处理办法如下
处理办法
通过_update_by_query去更新匹配的文档,如果没有指定查询,那么就会在每个文档上执行更新
POST /cloud mall-order/_update_by_query?conflicts=proceed
conflicts:
表示如果更新过程中发生异常冲突时如何处理:
(1)abort:中止(默认)
(2)proceed:继续执行
相关资料
DELETE blogs/
# 写入文档
PUT blogs/_doc/1
{
"content":"Hadoop is cool",
"keyword":"hadoop"
}
# 查看 Mapping
GET blogs/_mapping
# 修改 Mapping,增加子字段,使用英文分词器
PUT blogs/_mapping
{
"properties" : {
"content" : {
"type" : "text",
"fields" : {
"english" : {
"type" : "text",
"analyzer":"english"
}
}
}
}
}
# 写入文档
PUT blogs/_doc/2
{
"content":"Elasticsearch rocks",
"keyword":"elasticsearch"
}
# 查询新写入文档
POST blogs/_search
{
"query": {
"match": {
"content.english": "Elasticsearch"
}
}
}
# 查询 Mapping 变更前写入的文档
POST blogs/_search
{
"query": {
"match": {
"content.english": "Hadoop"
}
}
}
# Update所有文档
POST blogs/_update_by_query
{
}
# 查询之前写入的文档
POST blogs/_search
{
"query": {
"match": {
"content.english": "Hadoop"
}
}
}
# 查询
GET blogs/_mapping
PUT blogs/_mapping
{
"properties" : {
"content" : {
"type" : "text",
"fields" : {
"english" : {
"type" : "text",
"analyzer" : "english"
}
}
},
"keyword" : {
"type" : "keyword"
}
}
}
DELETE blogs_fix
# 创建新的索引并且设定新的Mapping
PUT blogs_fix/
{
"mappings": {
"properties" : {
"content" : {
"type" : "text",
"fields" : {
"english" : {
"type" : "text",
"analyzer" : "english"
}
}
},
"keyword" : {
"type" : "keyword"
}
}
}
}
# Reindx API
POST _reindex
{
"source": {
"index": "blogs"
},
"dest": {
"index": "blogs_fix"
}
}
GET blogs_fix/_doc/1
# 测试 Term Aggregation
POST blogs_fix/_search
{
"size": 0,
"aggs": {
"blog_keyword": {
"terms": {
"field": "keyword",
"size": 10
}
}
}
}
# Reindx API,version Type Internal
POST _reindex
{
"source": {
"index": "blogs"
},
"dest": {
"index": "blogs_fix",
"version_type": "internal"
}
}
# 文档版本号增加
GET blogs_fix/_doc/1
# Reindx API,version Type Internal
POST _reindex
{
"source": {
"index": "blogs"
},
"dest": {
"index": "blogs_fix",
"version_type": "external"
}
}
# Reindx API,version Type Internal
POST _reindex
{
"source": {
"index": "blogs"
},
"dest": {
"index": "blogs_fix",
"version_type": "external"
},
"conflicts": "proceed"
}
# Reindx API,version Type Internal
POST _reindex
{
"source": {
"index": "blogs"
},
"dest": {
"index": "blogs_fix",
"op_type": "create"
}
}
GET _tasks?detailed=true&actions=*reindex