|
@@ -4,7 +4,147 @@
|
|
|
<titleabbrev>Unique</titleabbrev>
|
|
|
++++
|
|
|
|
|
|
-The `unique` token filter can be used to only index unique tokens during
|
|
|
-analysis. By default it is applied on all the token stream. If
|
|
|
-`only_on_same_position` is set to `true`, it will only remove duplicate
|
|
|
-tokens on the same position.
|
|
|
+Removes duplicate tokens from a stream. For example, you can use the `unique`
|
|
|
+filter to change `the lazy lazy dog` to `the lazy dog`.
|
|
|
+
|
|
|
+If the `only_on_same_position` parameter is set to `true`, the `unique` filter
|
|
|
+removes only duplicate tokens _in the same position_.
|
|
|
+
|
|
|
+[NOTE]
|
|
|
+====
|
|
|
+When `only_on_same_position` is `true`, the `unique` filter works the same as
|
|
|
+<<analysis-remove-duplicates-tokenfilter,`remove_duplicates`>> filter.
|
|
|
+====
|
|
|
+
|
|
|
+[[analysis-unique-tokenfilter-analyze-ex]]
|
|
|
+==== Example
|
|
|
+
|
|
|
+The following <<indices-analyze,analyze API>> request uses the `unique` filter
|
|
|
+to remove duplicate tokens from `the quick fox jumps the lazy fox`:
|
|
|
+
|
|
|
+[source,console]
|
|
|
+--------------------------------------------------
|
|
|
+GET _analyze
|
|
|
+{
|
|
|
+ "tokenizer" : "whitespace",
|
|
|
+ "filter" : ["unique"],
|
|
|
+ "text" : "the quick fox jumps the lazy fox"
|
|
|
+}
|
|
|
+--------------------------------------------------
|
|
|
+
|
|
|
+The filter removes duplicated tokens for `the` and `fox`, producing the
|
|
|
+following output:
|
|
|
+
|
|
|
+[source,text]
|
|
|
+--------------------------------------------------
|
|
|
+[ the, quick, fox, jumps, lazy ]
|
|
|
+--------------------------------------------------
|
|
|
+
|
|
|
+/////////////////////
|
|
|
+[source,console-result]
|
|
|
+--------------------------------------------------
|
|
|
+{
|
|
|
+ "tokens" : [
|
|
|
+ {
|
|
|
+ "token" : "the",
|
|
|
+ "start_offset" : 0,
|
|
|
+ "end_offset" : 3,
|
|
|
+ "type" : "word",
|
|
|
+ "position" : 0
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "token" : "quick",
|
|
|
+ "start_offset" : 4,
|
|
|
+ "end_offset" : 9,
|
|
|
+ "type" : "word",
|
|
|
+ "position" : 1
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "token" : "fox",
|
|
|
+ "start_offset" : 10,
|
|
|
+ "end_offset" : 13,
|
|
|
+ "type" : "word",
|
|
|
+ "position" : 2
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "token" : "jumps",
|
|
|
+ "start_offset" : 14,
|
|
|
+ "end_offset" : 19,
|
|
|
+ "type" : "word",
|
|
|
+ "position" : 3
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "token" : "lazy",
|
|
|
+ "start_offset" : 24,
|
|
|
+ "end_offset" : 28,
|
|
|
+ "type" : "word",
|
|
|
+ "position" : 4
|
|
|
+ }
|
|
|
+ ]
|
|
|
+}
|
|
|
+--------------------------------------------------
|
|
|
+/////////////////////
|
|
|
+
|
|
|
+[[analysis-unique-tokenfilter-analyzer-ex]]
|
|
|
+==== Add to an analyzer
|
|
|
+
|
|
|
+The following <<indices-create-index,create index API>> request uses the
|
|
|
+`unique` filter to configure a new <<analysis-custom-analyzer,custom analyzer>>.
|
|
|
+
|
|
|
+[source,console]
|
|
|
+--------------------------------------------------
|
|
|
+PUT custom_unique_example
|
|
|
+{
|
|
|
+ "settings" : {
|
|
|
+ "analysis" : {
|
|
|
+ "analyzer" : {
|
|
|
+ "standard_truncate" : {
|
|
|
+ "tokenizer" : "standard",
|
|
|
+ "filter" : ["unique"]
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+}
|
|
|
+--------------------------------------------------
|
|
|
+
|
|
|
+[[analysis-unique-tokenfilter-configure-parms]]
|
|
|
+==== Configurable parameters
|
|
|
+
|
|
|
+`only_on_same_position`::
|
|
|
+(Optional, boolean)
|
|
|
+If `true`, only remove duplicate tokens in the same position.
|
|
|
+Defaults to `false`.
|
|
|
+
|
|
|
+[[analysis-unique-tokenfilter-customize]]
|
|
|
+==== Customize
|
|
|
+
|
|
|
+To customize the `unique` filter, duplicate it to create the basis
|
|
|
+for a new custom token filter. You can modify the filter using its configurable
|
|
|
+parameters.
|
|
|
+
|
|
|
+For example, the following request creates a custom `unique` filter with
|
|
|
+`only_on_same_position` set to `true`.
|
|
|
+
|
|
|
+[source,console]
|
|
|
+--------------------------------------------------
|
|
|
+PUT letter_unique_pos_example
|
|
|
+{
|
|
|
+ "settings": {
|
|
|
+ "analysis": {
|
|
|
+ "analyzer": {
|
|
|
+ "letter_unique_pos": {
|
|
|
+ "tokenizer": "letter",
|
|
|
+ "filter": [ "unique_pos" ]
|
|
|
+ }
|
|
|
+ },
|
|
|
+ "filter": {
|
|
|
+ "unique_pos": {
|
|
|
+ "type": "unique",
|
|
|
+ "only_on_same_position": true
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+}
|
|
|
+--------------------------------------------------
|