honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[DOCS] Replace `twitter` dataset in docs APIs (#60521) (#60529)

This commit is contained in:
James Rodewig 2020-07-31 12:40:03 -04:00 committed by GitHub
parent fe1d877b69
commit 9eba7f39b0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
15 changed files with 288 additions and 265 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
docs/reference/docs/delete-by-query.asciidoc
View File

@ -8,16 +8,16 @@ Deletes documents that match the specified query.
[source,console]
--------------------------------------------------
POST /twitter/_delete_by_query
POST /my-index-000001/_delete_by_query
{
"query": {
"match": {
"message": "some message"
"user.id": "elkbee"
}
}
}
--------------------------------------------------
// TEST[setup:big_twitter]
// TEST[setup:my_index_big]
////
@ -250,16 +250,16 @@ include::{docdir}/rest-api/common-parms.asciidoc[tag=wait_for_active_shards]
[source,console]
--------------------------------------------------
POST /twitter/_delete_by_query
POST /my-index-000001/_delete_by_query
{
"query": { <1>
"match": {
"message": "some message"
"user.id": "elkbee"
}
}
}
--------------------------------------------------
// TEST[setup:big_twitter]
// TEST[setup:my_index_big]
//////////////////////////
@ -350,38 +350,38 @@ version conflicts.
[[docs-delete-by-query-api-example]]
==== {api-examples-title}
Delete all tweets from the `twitter` data stream or index:
Delete all documents from the `my-index-000001` data stream or index:
[source,console]
--------------------------------------------------
POST twitter/_delete_by_query?conflicts=proceed
POST my-index-000001/_delete_by_query?conflicts=proceed
{
"query": {
"match_all": {}
}
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
Delete documents from multiple data streams or indices:
[source,console]
--------------------------------------------------
POST /twitter,blog/_delete_by_query
POST /my-index-000001,my-index-000002/_delete_by_query
{
"query": {
"match_all": {}
}
}
--------------------------------------------------
// TEST[s/^/PUT twitter\nPUT blog\n/]
// TEST[s/^/PUT my-index-000001\nPUT my-index-000002\n/]
Limit the delete by query operation to shards that a particular routing
value:
[source,console]
--------------------------------------------------
POST twitter/_delete_by_query?routing=1
POST my-index-000001/_delete_by_query?routing=1
{
"query": {
"range" : {
@ -392,23 +392,23 @@ POST twitter/_delete_by_query?routing=1
}
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
By default `_delete_by_query` uses scroll batches of 1000. You can change the
batch size with the `scroll_size` URL parameter:
[source,console]
--------------------------------------------------
POST twitter/_delete_by_query?scroll_size=5000
POST my-index-000001/_delete_by_query?scroll_size=5000
{
"query": {
"term": {
"user": "kimchy"
"user.id": "kimchy"
}
}
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[discrete]
[[docs-delete-by-query-manual-slice]]
@ -419,7 +419,7 @@ slices:
[source,console]
----------------------------------------------------------------
POST twitter/_delete_by_query
POST my-index-000001/_delete_by_query
{
"slice": {
"id": 0,
@ -427,13 +427,13 @@ POST twitter/_delete_by_query
},
"query": {
"range": {
"likes": {
"lt": 10
"http.response.bytes": {
"lt": 2000000
}
}
}
}
POST twitter/_delete_by_query
POST my-index-000001/_delete_by_query
{
"slice": {
"id": 1,
@ -441,26 +441,26 @@ POST twitter/_delete_by_query
},
"query": {
"range": {
"likes": {
"lt": 10
"http.response.bytes": {
"lt": 2000000
}
}
}
}
----------------------------------------------------------------
// TEST[setup:big_twitter]
// TEST[setup:my_index_big]
Which you can verify works with:
[source,console]
----------------------------------------------------------------
GET _refresh
POST twitter/_search?size=0&filter_path=hits.total
POST my-index-000001/_search?size=0&filter_path=hits.total
{
"query": {
"range": {
"likes": {
"lt": 10
"http.response.bytes": {
"lt": 2000000
}
}
}
@ -492,29 +492,29 @@ the number of slices to use:
[source,console]
----------------------------------------------------------------
POST twitter/_delete_by_query?refresh&slices=5
POST my-index-000001/_delete_by_query?refresh&slices=5
{
"query": {
"range": {
"likes": {
"lt": 10
"http.response.bytes": {
"lt": 2000000
}
}
}
}
----------------------------------------------------------------
// TEST[setup:big_twitter]
// TEST[setup:my_index_big]
Which you also can verify works with:
[source,console]
----------------------------------------------------------------
POST twitter/_search?size=0&filter_path=hits.total
POST my-index-000001/_search?size=0&filter_path=hits.total
{
"query": {
"range": {
"likes": {
"lt": 10
"http.response.bytes": {
"lt": 2000000
}
}
}

18
docs/reference/docs/delete.asciidoc
View File

@ -63,7 +63,7 @@ Example to delete with routing
[source,console]
--------------------------------------------------
PUT /twitter/_doc/1?routing=kimchy
PUT /my-index-000001/_doc/1?routing=kimchy
{
"test": "test"
}
@ -73,11 +73,11 @@ PUT /twitter/_doc/1?routing=kimchy
[source,console]
--------------------------------------------------
DELETE /twitter/_doc/1?routing=kimchy
DELETE /my-index-000001/_doc/1?routing=kimchy
--------------------------------------------------
// TEST[continued]
This request deletes the tweet with id `1`, but it is routed based on the
This request deletes the document with id `1`, but it is routed based on the
user. The document is not deleted if the correct routing is not specified.
[discrete]
@ -129,9 +129,9 @@ to 5 minutes:
[source,console]
--------------------------------------------------
DELETE /twitter/_doc/1?timeout=5m
DELETE /my-index-000001/_doc/1?timeout=5m
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[[docs-delete-api-path-params]]
==== {api-path-parms-title}
@ -166,13 +166,13 @@ include::{es-repo-dir}/rest-api/common-parms.asciidoc[tag=wait_for_active_shards
[[docs-delete-api-example]]
==== {api-examples-title}
Delete the JSON document `1` from the `twitter` index:
Delete the JSON document `1` from the `my-index-000001` index:
[source,console]
--------------------------------------------------
DELETE /twitter/_doc/1
DELETE /my-index-000001/_doc/1
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
The API returns the following result:
@ -184,7 +184,7 @@ The API returns the following result:
"failed": 0,
"successful": 2
},
"_index": "twitter",
"_index": "my-index-000001",
"_type": "_doc",
"_id": "1",
"_version": 2,

86
docs/reference/docs/get.asciidoc
View File

@ -8,9 +8,9 @@ Retrieves the specified JSON document from an index.
[source,console]
--------------------------------------------------
GET twitter/_doc/0
GET my-index-000001/_doc/0
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[[docs-get-api-request]]
==== {api-request-title}
@ -51,9 +51,9 @@ You can turn off `_source` retrieval by using the `_source` parameter:
[source,console]
--------------------------------------------------
GET twitter/_doc/0?_source=false
GET my-index-000001/_doc/0?_source=false
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
If you only need one or two fields from the `_source`, use the `_source_includes`
or `_source_excludes` parameters to include or filter out particular fields.
@ -63,17 +63,17 @@ of fields or wildcard expressions. Example:
[source,console]
--------------------------------------------------
GET twitter/_doc/0?_source_includes=*.id&_source_excludes=entities
GET my-index-000001/_doc/0?_source_includes=*.id&_source_excludes=entities
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
If you only want to specify includes, you can use a shorter notation:
[source,console]
--------------------------------------------------
GET twitter/_doc/0?_source=*.id,retweeted
GET my-index-000001/_doc/0?_source=*.id
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[discrete]
[[get-routing]]
@ -84,11 +84,11 @@ specified to retrieve a document. For example:
[source,console]
--------------------------------------------------
GET twitter/_doc/2?routing=user1
GET my-index-000001/_doc/2?routing=user1
--------------------------------------------------
// TEST[continued]
This request gets the tweet with id `2`, but it is routed based on the
This request gets the document with id `2`, but it is routed based on the
user. The document is not fetched if the correct routing is not specified.
[discrete]
@ -221,34 +221,44 @@ If the `stored_fields` parameter is set to `true` and `found` is
[[docs-get-api-example]]
==== {api-examples-title}
Retrieve the JSON document with the `_id` 0 from the `twitter` index:
Retrieve the JSON document with the `_id` 0 from the `my-index-000001` index:
[source,console]
--------------------------------------------------
GET twitter/_doc/0
GET my-index-000001/_doc/0
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
The API returns the following result:
[source,console-result]
--------------------------------------------------
{
"_index": "twitter",
"_index": "my-index-000001",
"_type": "_doc",
"_id": "0",
"_version": 1,
"_seq_no": 10,
"_seq_no": 0,
"_primary_term": 1,
"found": true,
"_source": {
"user": "kimchy",
"date": "2009-11-15T14:12:12",
"likes": 0,
"message": "trying out Elasticsearch",
"location": {
"city": "Amsterdam",
"country": "Netherlands"
"@timestamp": "2099-11-15T14:12:12",
"http": {
"request": {
"method": "get"
},
"response": {
"status_code": 200,
"bytes": 1070000
},
"version": "1.1"
},
"source": {
"ip": "127.0.0.1"
},
"message": "GET /search HTTP/1.1 200 1070000",
"user": {
"id": "kimchy"
}
}
}
@ -259,9 +269,9 @@ Check to see if a document with the `_id` 0 exists:
[source,console]
--------------------------------------------------
HEAD twitter/_doc/0
HEAD my-index-000001/_doc/0
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
{es} returns a status code of `200 - OK` if the document exists, or
`404 - Not Found` if it doesn't.
@ -275,7 +285,7 @@ just the `_source` field of a document. For example:
[source,console]
--------------------------------------------------
GET twitter/_source/1
GET my-index-000001/_source/1
--------------------------------------------------
// TEST[continued]
@ -284,7 +294,7 @@ You can use the source filtering parameters to control which parts of the
[source,console]
--------------------------------------------------
GET twitter/_source/1/?_source_includes=*.id&_source_excludes=entities
GET my-index-000001/_source/1/?_source_includes=*.id&_source_excludes=entities
--------------------------------------------------
// TEST[continued]
@ -294,7 +304,7 @@ available if it is disabled in the <<mapping-source-field,mapping>>.
[source,console]
--------------------------------------------------
HEAD twitter/_source/1
HEAD my-index-000001/_source/1
--------------------------------------------------
// TEST[continued]
@ -308,7 +318,7 @@ Consider for instance the following mapping:
[source,console]
--------------------------------------------------
PUT twitter
PUT my-index-000001
{
"mappings": {
"properties": {
@ -329,10 +339,10 @@ Now we can add a document:
[source,console]
--------------------------------------------------
PUT twitter/_doc/1
PUT my-index-000001/_doc/1
{
"counter": 1,
"tags": [ "red" ]
"tags": [ "production" ]
}
--------------------------------------------------
// TEST[continued]
@ -341,7 +351,7 @@ And then try to retrieve it:
[source,console]
--------------------------------------------------
GET twitter/_doc/1?stored_fields=tags,counter
GET my-index-000001/_doc/1?stored_fields=tags,counter
--------------------------------------------------
// TEST[continued]
@ -350,7 +360,7 @@ The API returns the following result:
[source,console-result]
--------------------------------------------------
{
"_index": "twitter",
"_index": "my-index-000001",
"_type": "_doc",
"_id": "1",
"_version": 1,
@ -359,7 +369,7 @@ The API returns the following result:
"found": true,
"fields": {
"tags": [
"red"
"production"
]
}
}
@ -373,17 +383,17 @@ You can also retrieve metadata fields like the `_routing` field:
[source,console]
--------------------------------------------------
PUT twitter/_doc/2?routing=user1
PUT my-index-000001/_doc/2?routing=user1
{
"counter" : 1,
"tags" : ["white"]
"tags" : ["env2"]
}
--------------------------------------------------
// TEST[continued]
[source,console]
--------------------------------------------------
GET twitter/_doc/2?routing=user1&stored_fields=tags,counter
GET my-index-000001/_doc/2?routing=user1&stored_fields=tags,counter
--------------------------------------------------
// TEST[continued]
@ -392,7 +402,7 @@ The API returns the following result:
[source,console-result]
--------------------------------------------------
{
"_index": "twitter",
"_index": "my-index-000001",
"_type": "_doc",
"_id": "2",
"_version": 1,
@ -402,7 +412,7 @@ The API returns the following result:
"found": true,
"fields": {
"tags": [
"white"
"env2"
]
}
}

84
docs/reference/docs/index_.asciidoc
View File

@ -191,7 +191,7 @@ creation of indices. It does not affect the creation of data streams.
PUT _cluster/settings
{
"persistent": {
"action.auto_create_index": "twitter,index10,-index1*,+ind*" <1>
"action.auto_create_index": "my-index-000001,index10,-index1*,+ind*" <1>
}
}
@ -210,7 +210,7 @@ PUT _cluster/settings
}
--------------------------------------------------
<1> Allow auto-creation of indices called `twitter` or `index10`, block the
<1> Allow auto-creation of indices called `my-index-000001` or `index10`, block the
creation of indices that match the pattern `index1*`, and allow creation of
any other indices that match the `ind*` pattern. Patterns are matched in
the order specified.
@ -238,11 +238,13 @@ the document.
[source,console]
--------------------------------------------------
POST twitter/_doc/
POST my-index-000001/_doc/
{
"user" : "kimchy",
"post_date" : "2009-11-15T14:12:12",
"message" : "trying out Elasticsearch"
"@timestamp": "2099-11-15T13:12:00",
"message": "GET /search HTTP/1.1 200 1070000",
"user": {
"id": "kimchy"
}
}
--------------------------------------------------
@ -256,8 +258,8 @@ The API returns the following result:
"failed": 0,
"successful": 2
},
"_index": "twitter",
"_type": "_doc",
"_index": "my-index-000001",
"_type": "_doc",
"_id": "W0tpsmIBdwcYyG50zbta",
"_version": 1,
"_seq_no": 0,
@ -288,11 +290,13 @@ on a per-operation basis using the `routing` parameter. For example:
[source,console]
--------------------------------------------------
POST twitter/_doc?routing=kimchy
POST my-index-000001/_doc?routing=kimchy
{
"user" : "kimchy",
"post_date" : "2009-11-15T14:12:12",
"message" : "trying out Elasticsearch"
"@timestamp": "2099-11-15T13:12:00",
"message": "GET /search HTTP/1.1 200 1070000",
"user": {
"id": "kimchy"
}
}
--------------------------------------------------
@ -413,11 +417,13 @@ to 5 minutes:
[source,console]
--------------------------------------------------
PUT twitter/_doc/1?timeout=5m
PUT my-index-000001/_doc/1?timeout=5m
{
"user" : "kimchy",
"post_date" : "2009-11-15T14:12:12",
"message" : "trying out Elasticsearch"
"@timestamp": "2099-11-15T13:12:00",
"message": "GET /search HTTP/1.1 200 1070000",
"user": {
"id": "kimchy"
}
}
--------------------------------------------------
@ -442,9 +448,11 @@ conflict will occur and the index operation will fail. For example:
[source,console]
--------------------------------------------------
PUT twitter/_doc/1?version=2&version_type=external
PUT my-index-000001/_doc/1?version=2&version_type=external
{
"message" : "elasticsearch now has versioning support, double cool!"
"user": {
"id": "elkbee"
}
}
--------------------------------------------------
// TEST[continued]
@ -496,15 +504,17 @@ primary and replica shards to diverge.
[[docs-index-api-example]]
==== {api-examples-title}
Insert a JSON document into the `twitter` index with an `_id` of 1:
Insert a JSON document into the `my-index-000001` index with an `_id` of 1:
[source,console]
--------------------------------------------------
PUT twitter/_doc/1
PUT my-index-000001/_doc/1
{
"user" : "kimchy",
"post_date" : "2009-11-15T14:12:12",
"message" : "trying out Elasticsearch"
"@timestamp": "2099-11-15T13:12:00",
"message": "GET /search HTTP/1.1 200 1070000",
"user": {
"id": "kimchy"
}
}
--------------------------------------------------
@ -518,8 +528,8 @@ The API returns the following result:
"failed": 0,
"successful": 2
},
"_index": "twitter",
"_type": "_doc",
"_index": "my-index-000001",
"_type": "_doc",
"_id": "1",
"_version": 1,
"_seq_no": 0,
@ -529,28 +539,32 @@ The API returns the following result:
--------------------------------------------------
// TESTRESPONSE[s/"successful": 2/"successful": 1/]
Use the `_create` resource to index a document into the `twitter` index if
Use the `_create` resource to index a document into the `my-index-000001` index if
no document with that ID exists:
[source,console]
--------------------------------------------------
PUT twitter/_create/1
PUT my-index-000001/_create/1
{
"user" : "kimchy",
"post_date" : "2009-11-15T14:12:12",
"message" : "trying out Elasticsearch"
"@timestamp": "2099-11-15T13:12:00",
"message": "GET /search HTTP/1.1 200 1070000",
"user": {
"id": "kimchy"
}
}
--------------------------------------------------
Set the `op_type` parameter to _create_ to index a document into the `twitter`
Set the `op_type` parameter to _create_ to index a document into the `my-index-000001`
index if no document with that ID exists:
[source,console]
--------------------------------------------------
PUT twitter/_doc/1?op_type=create
PUT my-index-000001/_doc/1?op_type=create
{
"user" : "kimchy",
"post_date" : "2009-11-15T14:12:12",
"message" : "trying out Elasticsearch"
"@timestamp": "2099-11-15T13:12:00",
"message": "GET /search HTTP/1.1 200 1070000",
"user": {
"id": "kimchy"
}
}
--------------------------------------------------

14
docs/reference/docs/multi-get.asciidoc
View File

@ -12,17 +12,17 @@ GET /_mget
{
"docs": [
{
"_index": "twitter",
"_index": "my-index-000001",
"_id": "1"
},
{
"_index": "twitter",
"_index": "my-index-000001",
"_id": "2"
}
]
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[[docs-multi-get-api-request]]
==== {api-request-title}
@ -128,7 +128,7 @@ If you specify an index in the request URI, only the document IDs are required i
[source,console]
--------------------------------------------------
GET /twitter/_mget
GET /my-index-000001/_mget
{
"docs": [
{
@ -159,18 +159,18 @@ GET /test/_doc/_mget
]
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
You can use the `ids` element to simplify the request:
[source,console]
--------------------------------------------------
GET /twitter/_mget
GET /my-index-000001/_mget
{
"ids" : ["1", "2"]
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[[mget-source-filtering]]
===== Filter source fields

26
docs/reference/docs/multi-termvectors.asciidoc
View File

@ -12,12 +12,12 @@ POST /_mtermvectors
{
"docs": [
{
"_index": "twitter",
"_index": "my-index-000001",
"_id": "2",
"term_statistics": true
},
{
"_index": "twitter",
"_index": "my-index-000001",
"_id": "1",
"fields": [
"message"
@ -26,7 +26,7 @@ POST /_mtermvectors
]
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[[docs-multi-termvectors-api-request]]
==== {api-request-title}
@ -89,7 +89,7 @@ in the request body:
[source,console]
--------------------------------------------------
POST /twitter/_mtermvectors
POST /my-index-000001/_mtermvectors
{
"docs": [
{
@ -105,14 +105,14 @@ POST /twitter/_mtermvectors
]
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
If all requested documents are in same index and the parameters are the same, you can use the
following simplified syntax:
[source,console]
--------------------------------------------------
POST /twitter/_mtermvectors
POST /my-index-000001/_mtermvectors
{
"ids": [ "1", "2" ],
"parameters": {
@ -123,7 +123,7 @@ POST /twitter/_mtermvectors
}
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[[docs-multi-termvectors-artificial-doc]]
===== Artificial documents
@ -137,20 +137,18 @@ POST /_mtermvectors
{
"docs": [
{
"_index": "twitter",
"_index": "my-index-000001",
"doc" : {
"user" : "John Doe",
"message" : "twitter test test test"
"message" : "test test test"
}
},
{
"_index": "twitter",
"_index": "my-index-000001",
"doc" : {
"user" : "Jane Doe",
"message" : "Another twitter test ..."
"message" : "Another test ..."
}
}
]
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]

94
docs/reference/docs/reindex.asciidoc
View File

@ -26,14 +26,14 @@ Mappings, shard counts, replicas, and so on must be configured ahead of time.
POST _reindex
{
"source": {
"index": "twitter"
"index": "my-index-000001"
},
"dest": {
"index": "new_twitter"
"index": "my-new-index-000001"
}
}
--------------------------------------------------
// TEST[setup:big_twitter]
// TEST[setup:my_index_big]
////
@ -205,38 +205,38 @@ slices to each request:
POST _reindex
{
"source": {
"index": "twitter",
"index": "my-index-000001",
"slice": {
"id": 0,
"max": 2
}
},
"dest": {
"index": "new_twitter"
"index": "my-new-index-000001"
}
}
POST _reindex
{
"source": {
"index": "twitter",
"index": "my-index-000001",
"slice": {
"id": 1,
"max": 2
}
},
"dest": {
"index": "new_twitter"
"index": "my-new-index-000001"
}
}
----------------------------------------------------------------
// TEST[setup:big_twitter]
// TEST[setup:my_index_big]
You can verify this works by:
[source,console]
----------------------------------------------------------------
GET _refresh
POST new_twitter/_search?size=0&filter_path=hits.total
POST my-new-index-000001/_search?size=0&filter_path=hits.total
----------------------------------------------------------------
// TEST[continued]
@ -265,20 +265,20 @@ slice on `_id`. Use `slices` to specify the number of slices to use:
POST _reindex?slices=5&refresh
{
"source": {
"index": "twitter"
"index": "my-index-000001"
},
"dest": {
"index": "new_twitter"
"index": "my-new-index-000001"
}
}
----------------------------------------------------------------
// TEST[setup:big_twitter]
// TEST[setup:my_index_big]
You can also this verify works by:
[source,console]
----------------------------------------------------------------
POST new_twitter/_search?size=0&filter_path=hits.total
POST my-new-index-000001/_search?size=0&filter_path=hits.total
----------------------------------------------------------------
// TEST[continued]
@ -617,33 +617,33 @@ the `conflicts` option to prevent reindex from aborting on version conflicts.
===== Reindex select documents with a query
You can limit the documents by adding a query to the `source`.
For example, the following request only copies tweets made by `kimchy` into `new_twitter`:
For example, the following request only copies documents with a `user.id` of `kimchy` into `my-new-index-000001`:
[source,console]
--------------------------------------------------
POST _reindex
{
"source": {
"index": "twitter",
"index": "my-index-000001",
"query": {
"term": {
"user": "kimchy"
"user.id": "kimchy"
}
}
},
"dest": {
"index": "new_twitter"
"index": "my-new-index-000001"
}
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[[docs-reindex-select-max-docs]]
===== Reindex select documents with `max_docs`
You can limit the number of processed documents by setting `max_docs`.
For example, this request copies a single document from `twitter` to
`new_twitter`:
For example, this request copies a single document from `my-index-000001` to
`my-new-index-000001`:
[source,console]
--------------------------------------------------
@ -651,36 +651,36 @@ POST _reindex
{
"max_docs": 1,
"source": {
"index": "twitter"
"index": "my-index-000001"
},
"dest": {
"index": "new_twitter"
"index": "my-new-index-000001"
}
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[[docs-reindex-multiple-sources]]
===== Reindex from multiple sources
The `index` attribute in `source` can be a list, allowing you to copy from lots
of sources in one request. This will copy documents from the
`twitter` and `blog` indices:
`my-index-000001` and `my-index-000002` indices:
[source,console]
--------------------------------------------------
POST _reindex
{
"source": {
"index": ["twitter", "blog"]
"index": ["my-index-000001", "my-index-000002"]
},
"dest": {
"index": "all_together"
"index": "my-new-index-000002"
}
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[s/^/PUT blog\/post\/post1?refresh\n{"test": "foo"}\n/]
// TEST[setup:my_index]
// TEST[s/^/PUT my-index-000002\/_doc\/post1?refresh\n{"test": "foo"}\n/]
NOTE: The Reindex API makes no effort to handle ID collisions so the last
document written will "win" but the order isn't usually predictable so it is
@ -691,22 +691,22 @@ using a script.
===== Reindex select fields with a source filter
You can use source filtering to reindex a subset of the fields in the original documents.
For example, the following request only reindexes the `user` and `_doc` fields of each document:
For example, the following request only reindexes the `user.id` and `_doc` fields of each document:
[source,console]
--------------------------------------------------
POST _reindex
{
"source": {
"index": "twitter",
"_source": ["user", "_doc"]
"index": "my-index-000001",
"_source": ["user.id", "_doc"]
},
"dest": {
"index": "new_twitter"
"index": "my-new-index-000001"
}
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[[docs-reindex-change-name]]
===== Reindex to change the name of a field
@ -716,7 +716,7 @@ create an index containing documents that look like this:
[source,console]
--------------------------------------------------
POST test/_doc/1?refresh
POST my-index-000001/_doc/1?refresh
{
"text": "words words",
"flag": "foo"
@ -731,10 +731,10 @@ but you don't like the name `flag` and want to replace it with `tag`.
POST _reindex
{
"source": {
"index": "test"
"index": "my-index-000001"
},
"dest": {
"index": "test2"
"index": "my-new-index-000001"
},
"script": {
"source": "ctx._source.tag = ctx._source.remove(\"flag\")"
@ -747,7 +747,7 @@ Now you can get the new document:
[source,console]
--------------------------------------------------
GET test2/_doc/1
GET my-new-index-000001/_doc/1
--------------------------------------------------
// TEST[continued]
@ -758,7 +758,7 @@ which will return:
{
"found": true,
"_id": "1",
"_index": "test2",
"_index": "my-new-index-000001",
"_type": "_doc",
"_version": 1,
"_seq_no": 44,
@ -836,7 +836,7 @@ POST _reindex
{
"max_docs": 10,
"source": {
"index": "twitter",
"index": "my-index-000001",
"query": {
"function_score" : {
"random_score" : {},
@ -845,11 +845,11 @@ POST _reindex
}
},
"dest": {
"index": "random_twitter"
"index": "my-new-index-000001"
}
}
----------------------------------------------------------------
// TEST[setup:big_twitter]
// TEST[setup:my_index_big]
<1> You may need to adjust the `min_score` depending on the relative amount of
data extracted from source.
@ -866,10 +866,10 @@ document's metadata. This example bumps the version of the source document:
POST _reindex
{
"source": {
"index": "twitter"
"index": "my-index-000001"
},
"dest": {
"index": "new_twitter",
"index": "my-new-index-000001",
"version_type": "external"
},
"script": {
@ -878,7 +878,7 @@ POST _reindex
}
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
Just as in `_update_by_query`, you can set `ctx.op` to change the
operation that is executed on the destination:
@ -926,7 +926,7 @@ POST _reindex
"username": "user",
"password": "pass"
},
"index": "source",
"index": "my-index-000001",
"query": {
"match": {
"test": "data"
@ -934,12 +934,12 @@ POST _reindex
}
},
"dest": {
"index": "dest"
"index": "my-new-index-000001"
}
}
--------------------------------------------------
// TEST[setup:host]
// TEST[s/^/PUT source\n/]
// TEST[s/^/PUT my-index-000001\n/]
// TEST[s/otherhost:9200",/\${host}"/]
// TEST[s/"username": "user",//]
// TEST[s/"password": "pass"//]

87
docs/reference/docs/termvectors.asciidoc
View File

@ -8,9 +8,9 @@ Retrieves information and statistics for terms in the fields of a particular doc
[source,console]
--------------------------------------------------
GET /twitter/_termvectors/1
GET /my-index-000001/_termvectors/1
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[[docs-termvectors-api-request]]
==== {api-request-title}
@ -28,9 +28,9 @@ or by adding the fields to the request body.
[source,console]
--------------------------------------------------
GET /twitter/_termvectors/1?fields=message
GET /my-index-000001/_termvectors/1?fields=message
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
Fields can be specified using wildcards, similar to the <<query-dsl-multi-match-query,multi match query>>.
@ -169,7 +169,7 @@ First, we create an index that stores term vectors, payloads etc. :
[source,console]
--------------------------------------------------
PUT /twitter
PUT /my-index-000001
{ "mappings": {
"properties": {
"text": {
@ -210,16 +210,16 @@ Second, we add some documents:
[source,console]
--------------------------------------------------
PUT /twitter/_doc/1
PUT /my-index-000001/_doc/1
{
"fullname" : "John Doe",
"text" : "twitter test test test "
"text" : "test test test "
}
PUT /twitter/_doc/2?refresh=wait_for
PUT /my-index-000001/_doc/2?refresh=wait_for
{
"fullname" : "Jane Doe",
"text" : "Another twitter test ..."
"text" : "Another test ..."
}
--------------------------------------------------
// TEST[continued]
@ -229,7 +229,7 @@ The following request returns all information and statistics for field
[source,console]
--------------------------------------------------
GET /twitter/_termvectors/1
GET /my-index-000001/_termvectors/1
{
"fields" : ["text"],
"offsets" : true,
@ -246,57 +246,44 @@ Response:
[source,console-result]
--------------------------------------------------
{
"_index": "my-index-000001",
"_type": "_doc",
"_id": "1",
"_index": "twitter",
"_type": "_doc",
"_version": 1,
"found": true,
"took": 6,
"term_vectors": {
"text": {
"field_statistics": {
"sum_doc_freq": 4,
"doc_count": 2,
"sum_doc_freq": 6,
"sum_ttf": 8
"sum_ttf": 6
},
"terms": {
"test": {
"doc_freq": 2,
"ttf": 4,
"term_freq": 3,
"tokens": [
{
"end_offset": 12,
"payload": "d29yZA==",
"position": 1,
"start_offset": 8
},
{
"end_offset": 17,
"payload": "d29yZA==",
"position": 2,
"start_offset": 13
},
{
"end_offset": 22,
"payload": "d29yZA==",
"position": 3,
"start_offset": 18
}
],
"ttf": 4
},
"twitter": {
"doc_freq": 2,
"term_freq": 1,
"tokens": [
{
"end_offset": 7,
"payload": "d29yZA==",
"position": 0,
"start_offset": 0
"start_offset": 0,
"end_offset": 4,
"payload": "d29yZA=="
},
{
"position": 1,
"start_offset": 5,
"end_offset": 9,
"payload": "d29yZA=="
},
{
"position": 2,
"start_offset": 10,
"end_offset": 14,
"payload": "d29yZA=="
}
],
"ttf": 2
]
}
}
}
@ -316,7 +303,7 @@ Note that for the field `text`, the terms are not re-generated.
[source,console]
--------------------------------------------------
GET /twitter/_termvectors/1
GET /my-index-000001/_termvectors/1
{
"fields" : ["text", "some_field_without_term_vectors"],
"offsets" : true,
@ -339,11 +326,11 @@ mapping will be dynamically created.*
[source,console]
--------------------------------------------------
GET /twitter/_termvectors
GET /my-index-000001/_termvectors
{
"doc" : {
"fullname" : "John Doe",
"text" : "twitter test test test"
"text" : "test test test"
}
}
--------------------------------------------------
@ -360,11 +347,11 @@ vectors, the term vectors will be re-generated.
[source,console]
--------------------------------------------------
GET /twitter/_termvectors
GET /my-index-000001/_termvectors
{
"doc" : {
"fullname" : "John Doe",
"text" : "twitter test test test"
"text" : "test test test"
},
"fields": ["fullname"],
"per_field_analyzer" : {
@ -379,7 +366,7 @@ Response:
[source,console-result]
--------------------------------------------------
{
"_index": "twitter",
"_index": "my-index-000001",
"_type": "_doc",
"_version": 0,
"found": true,

64
docs/reference/docs/update-by-query.asciidoc
View File

@ -10,9 +10,9 @@ modifying the source, which is useful for picking up mapping changes.
[source,console]
--------------------------------------------------
POST twitter/_update_by_query?conflicts=proceed
POST my-index-000001/_update_by_query?conflicts=proceed
--------------------------------------------------
// TEST[setup:big_twitter]
// TEST[setup:my_index_big]
////
@ -305,16 +305,16 @@ To update selected documents, specify a query in the request body:
[source,console]
--------------------------------------------------
POST twitter/_update_by_query?conflicts=proceed
POST my-index-000001/_update_by_query?conflicts=proceed
{
"query": { <1>
"term": {
"user": "kimchy"
"user.id": "kimchy"
}
}
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
<1> The query must be passed as a value to the `query` key, in the same
way as the <<search-search,Search API>>. You can also use the `q`
@ -324,49 +324,63 @@ Update documents in multiple data streams or indices:
[source,console]
--------------------------------------------------
POST twitter,blog/_update_by_query
POST my-index-000001,my-index-000002/_update_by_query
--------------------------------------------------
// TEST[s/^/PUT twitter\nPUT blog\n/]
// TEST[s/^/PUT my-index-000001\nPUT my-index-000002\n/]
Limit the update by query operation to shards that a particular routing value:
[source,console]
--------------------------------------------------
POST twitter/_update_by_query?routing=1
POST my-index-000001/_update_by_query?routing=1
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
By default update by query uses scroll batches of 1000.
You can change the batch size with the `scroll_size` parameter:
[source,console]
--------------------------------------------------
POST twitter/_update_by_query?scroll_size=100
POST my-index-000001/_update_by_query?scroll_size=100
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[[docs-update-by-query-api-source]]
===== Update the document source
Update by query supports scripts to update the document source.
For example, the following request increments the likes field for all of kimchy’s tweets:
For example, the following request increments the `count` field for all
documents with a `user.id` of `kimchy` in `my-index-000001`:
////
[source,console]
----
PUT my-index-000001/_create/1
{
"user": {
"id": "kimchy"
},
"count": 1
}
----
////
[source,console]
--------------------------------------------------
POST twitter/_update_by_query
POST my-index-000001/_update_by_query
{
"script": {
"source": "ctx._source.likes++",
"source": "ctx._source.count++",
"lang": "painless"
},
"query": {
"term": {
"user": "kimchy"
"user.id": "kimchy"
}
}
}
--------------------------------------------------
// TEST[setup:twitter]
// TEST[continued]
Note that `conflicts=proceed` is not specified in this example. In this case, a
version conflict should halt the process so you can handle the failure.
@ -404,9 +418,9 @@ PUT _ingest/pipeline/set-foo
}
} ]
}
POST twitter/_update_by_query?pipeline=set-foo
POST my-index-000001/_update_by_query?pipeline=set-foo
--------------------------------------------------
// TEST[setup:twitter]
// TEST[setup:my_index]
[discrete]
@ -535,7 +549,7 @@ slices to each request:
[source,console]
----------------------------------------------------------------
POST twitter/_update_by_query
POST my-index-000001/_update_by_query
{
"slice": {
"id": 0,
@ -545,7 +559,7 @@ POST twitter/_update_by_query
"source": "ctx._source['extra'] = 'test'"
}
}
POST twitter/_update_by_query
POST my-index-000001/_update_by_query
{
"slice": {
"id": 1,
@ -556,14 +570,14 @@ POST twitter/_update_by_query
}
}
----------------------------------------------------------------
// TEST[setup:big_twitter]
// TEST[setup:my_index_big]
Which you can verify works with:
[source,console]
----------------------------------------------------------------
GET _refresh
POST twitter/_search?size=0&q=extra:test&filter_path=hits.total
POST my-index-000001/_search?size=0&q=extra:test&filter_path=hits.total
----------------------------------------------------------------
// TEST[continued]
@ -591,20 +605,20 @@ slices to use:
[source,console]
----------------------------------------------------------------
POST twitter/_update_by_query?refresh&slices=5
POST my-index-000001/_update_by_query?refresh&slices=5
{
"script": {
"source": "ctx._source['extra'] = 'test'"
}
}
----------------------------------------------------------------
// TEST[setup:big_twitter]
// TEST[setup:my_index_big]
Which you also can verify works with:
[source,console]
----------------------------------------------------------------
POST twitter/_search?size=0&q=extra:test&filter_path=hits.total
POST my-index-000001/_search?size=0&q=extra:test&filter_path=hits.total
----------------------------------------------------------------
// TEST[continued]

4
docs/reference/indices/aliases.asciidoc
View File

@ -325,7 +325,7 @@ POST /_aliases
"add": {
"index": "test1",
"alias": "alias2",
"filter": { "term": { "user": "kimchy" } }
"filter": { "term": { "user.id": "kimchy" } }
}
}
]
@ -392,7 +392,7 @@ routing value:
[source,console]
--------------------------------------------------
GET /alias2/_search?q=user:kimchy&routing=2,3
GET /alias2/_search?q=user.id:kimchy&routing=2,3
--------------------------------------------------
// TEST[continued]

2
docs/reference/indices/component-templates.asciidoc
View File

@ -139,7 +139,7 @@ PUT _component_template/template_1
"alias1" : {},
"alias2" : {
"filter" : {
"term" : {"user" : "kimchy" }
"term" : {"user.id" : "kimchy" }
},
"routing" : "kimchy"
},

2
docs/reference/indices/create-index.asciidoc
View File

@ -153,7 +153,7 @@ PUT /test
"alias_1": {},
"alias_2": {
"filter": {
"term": { "user": "kimchy" }
"term": { "user.id": "kimchy" }
},
"routing": "kimchy"
}

2
docs/reference/indices/put-component-template.asciidoc
View File

@ -136,7 +136,7 @@ PUT _component_template/template_1
"alias1" : {},
"alias2" : {
"filter" : {
"term" : {"user" : "kimchy" }
"term" : {"user.id" : "kimchy" }
},
"routing" : "kimchy"
},

2
docs/reference/indices/put-index-template-v1.asciidoc
View File

@ -150,7 +150,7 @@ PUT _template/template_1
"alias1" : {},
"alias2" : {
"filter" : {
"term" : {"user" : "kimchy" }
"term" : {"user.id" : "kimchy" }
},
"routing" : "kimchy"
},

2
docs/reference/indices/put-index-template.asciidoc
View File

@ -153,7 +153,7 @@ PUT _index_template/template_1
"alias1" : {},
"alias2" : {
"filter" : {
"term" : {"user" : "kimchy" }
"term" : {"user.id" : "kimchy" }
},
"routing" : "kimchy"
},