mirror of
https://github.com/elastic/elasticsearch.git
synced 2025-04-24 23:27:25 -04:00
154 lines
3.1 KiB
Text
154 lines
3.1 KiB
Text
[[analysis-simple-analyzer]]
|
|
=== Simple Analyzer
|
|
|
|
The `simple` analyzer breaks text into terms at any non-letter character, such
|
|
as numbers, spaces, hyphens and apostrophes, discards non-letter characters,
|
|
and changes uppercase to lowercase.
|
|
|
|
==== Example
|
|
|
|
[source,js]
|
|
---------------------------
|
|
POST _analyze
|
|
{
|
|
"analyzer": "simple",
|
|
"text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
|
|
}
|
|
---------------------------
|
|
// CONSOLE
|
|
|
|
/////////////////////
|
|
|
|
[source,console-result]
|
|
----------------------------
|
|
{
|
|
"tokens": [
|
|
{
|
|
"token": "the",
|
|
"start_offset": 0,
|
|
"end_offset": 3,
|
|
"type": "word",
|
|
"position": 0
|
|
},
|
|
{
|
|
"token": "quick",
|
|
"start_offset": 6,
|
|
"end_offset": 11,
|
|
"type": "word",
|
|
"position": 1
|
|
},
|
|
{
|
|
"token": "brown",
|
|
"start_offset": 12,
|
|
"end_offset": 17,
|
|
"type": "word",
|
|
"position": 2
|
|
},
|
|
{
|
|
"token": "foxes",
|
|
"start_offset": 18,
|
|
"end_offset": 23,
|
|
"type": "word",
|
|
"position": 3
|
|
},
|
|
{
|
|
"token": "jumped",
|
|
"start_offset": 24,
|
|
"end_offset": 30,
|
|
"type": "word",
|
|
"position": 4
|
|
},
|
|
{
|
|
"token": "over",
|
|
"start_offset": 31,
|
|
"end_offset": 35,
|
|
"type": "word",
|
|
"position": 5
|
|
},
|
|
{
|
|
"token": "the",
|
|
"start_offset": 36,
|
|
"end_offset": 39,
|
|
"type": "word",
|
|
"position": 6
|
|
},
|
|
{
|
|
"token": "lazy",
|
|
"start_offset": 40,
|
|
"end_offset": 44,
|
|
"type": "word",
|
|
"position": 7
|
|
},
|
|
{
|
|
"token": "dog",
|
|
"start_offset": 45,
|
|
"end_offset": 48,
|
|
"type": "word",
|
|
"position": 8
|
|
},
|
|
{
|
|
"token": "s",
|
|
"start_offset": 49,
|
|
"end_offset": 50,
|
|
"type": "word",
|
|
"position": 9
|
|
},
|
|
{
|
|
"token": "bone",
|
|
"start_offset": 51,
|
|
"end_offset": 55,
|
|
"type": "word",
|
|
"position": 10
|
|
}
|
|
]
|
|
}
|
|
----------------------------
|
|
|
|
/////////////////////
|
|
|
|
|
|
The `simple` analyzer parses the sentence and produces the following
|
|
terms:
|
|
|
|
[source,text]
|
|
---------------------------
|
|
[ the, quick, brown, foxes, jumped, over, the, lazy, dog, s, bone ]
|
|
---------------------------
|
|
|
|
==== Configure parameters
|
|
|
|
The `simple` analyzer does not contain configurable parameters.
|
|
|
|
==== Customize
|
|
|
|
The `simple` analyzer is defined by one tokenizer:
|
|
|
|
Tokenizer::
|
|
* <<analysis-lowercase-tokenizer,Lower Case Tokenizer>>
|
|
|
|
To customize the `simple` analyzer, duplicate it to create the basis for
|
|
a `custom` analyzer. The new analyzer can be modified as required, usually by
|
|
adding token filters.
|
|
|
|
===== Example
|
|
|
|
[source,js]
|
|
----------------------------------------------------
|
|
PUT /simple_example
|
|
{
|
|
"settings": {
|
|
"analysis": {
|
|
"analyzer": {
|
|
"rebuilt_simple": {
|
|
"tokenizer": "lowercase",
|
|
"filter": [ <1>
|
|
]
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
----------------------------------------------------
|
|
// CONSOLE
|
|
// TEST[s/\n$/\nstartyaml\n - compare_analyzers: {index: simple_example, first: simple, second: rebuilt_simple}\nendyaml\n/]
|
|
<1> Add token filters here.
|