diff --git a/docs/reference/analysis/analyzers/stop-analyzer-language-support.asciidoc b/docs/reference/analysis/analyzers/stop-analyzer-language-support.asciidoc new file mode 100644 index 0000000000000..410f97be5cb79 --- /dev/null +++ b/docs/reference/analysis/analyzers/stop-analyzer-language-support.asciidoc @@ -0,0 +1,114 @@ +[[analysis-stop-analyzer-language-support]] +=== Stop Analyzer Language Support + +The `stop` analyzer supports the following languages: + +[width="100%"] +|======= +|Language |Source + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/ArabicAnalyzerProvider.java[Arabic] +| link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java#L57[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/ArmenianAnalyzerProvider.java[Armenian] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/hy/ArmenianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/BasqueAnalyzerProvider.java[Basque] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/eu/BasqueAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/BengaliAnalyzerProvider.java[Bengali] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/bn/BengaliAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/BrazilianAnalyzerProvider.java[Brazilian] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/BulgarianAnalyzerProvider.java[Bulgarian] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/CatalanAnalyzerProvider.java[Catalan] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/CjkAnalyzerProvider.java[CJK] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/CzechAnalyzerProvider.java[Czech] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/DanishAnalyzerProvider.java[Danish] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/da/DanishAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/DutchAnalyzerProvider.java[Dutch] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/da/DanishAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/EnglishAnalyzerProvider.java[English] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/en/EnglishAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/FinnishAnalyzerProvider.java[Finnish] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/fi/FinnishAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/FrenchAnalyzerProvider.java[French] +|link:https://github.com/apache/lucene-solr/tree/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/fr[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/GalicianAnalyzerProvider.java[Galician] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/GermanAnalyzerProvider.java[German] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/de/GermanAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/GreekAnalyzerProvider.java[Greek] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/HindiAnalyzerProvider.java[Hindi] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/HungarianAnalyzerProvider.java[Hungarian] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/hu/HungarianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/IndonesianAnalyzerProvider.java[Indonesian] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/id/IndonesianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/IrishAnalyzerProvider.java[Irish] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/ga/IrishAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/ItalianAnalyzerProvider.java[Italian] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/LatvianAnalyzerProvider.java[Latvian] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/lv/LatvianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/LithuanianAnalyzerProvider.java[Lithuanian] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/lt/LithuanianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/NorwegianAnalyzerProvider.java[Norwegian] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/no/NorwegianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/PersianAnalyzerProvider.java[Persian] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/PortugueseAnalyzerProvider.java[Portuguese] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/RomanianAnalyzerProvider.java[Romanian] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/ro/RomanianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/RussianAnalyzerProvider.java[Russian] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/SoraniAnalyzerProvider.java[Sorani] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/ckb/SoraniAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/SpanishAnalyzerProvider.java[Spanish] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/es/SpanishAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/SwedishAnalyzerProvider.java[Swedish] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/sv/SwedishAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/ThaiAnalyzerProvider.java[Thai] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java[Lucene] + +|link:https://github.com/elastic/elasticsearch/blob/master/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/TurkishAnalyzerProvider.java[Turkish] +|link:https://github.com/apache/lucene-solr/blob/2e1a470c90e9293a42160280c5c39afb33bb5db0/lucene/analysis/common/src/java/org/apache/lucene/analysis/tr/TurkishAnalyzer.java[Lucene] +|======= + + +See the link:https://github.com/elastic/elasticsearch/blob/master/docs/reference/analysis/analyzers/stop-analyzer.asciidoc#analysis-stop-tokenfilter[Stop Analyzer Documentaton] for more information about the stop word configuration. diff --git a/docs/reference/analysis/analyzers/stop-analyzer.asciidoc b/docs/reference/analysis/analyzers/stop-analyzer.asciidoc index 517233d93b7f6..e3b2c5437dae1 100644 --- a/docs/reference/analysis/analyzers/stop-analyzer.asciidoc +++ b/docs/reference/analysis/analyzers/stop-analyzer.asciidoc @@ -1,273 +1,276 @@ -[[analysis-stop-analyzer]] -=== Stop Analyzer - -The `stop` analyzer is the same as the <> -but adds support for removing stop words. It defaults to using the -`_english_` stop words. - -[float] -=== Example output - -[source,console] ---------------------------- -POST _analyze -{ - "analyzer": "stop", - "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone." -} ---------------------------- - -///////////////////// - -[source,console-result] ----------------------------- -{ - "tokens": [ - { - "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": "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 above sentence would produce the following terms: - -[source,text] ---------------------------- -[ quick, brown, foxes, jumped, over, lazy, dog, s, bone ] ---------------------------- - -[float] -=== Configuration - -The `stop` analyzer accepts the following parameters: - -[horizontal] -`stopwords`:: - - A pre-defined stop words list like `_english_` or an array containing a - list of stop words. Defaults to `_english_`. - -`stopwords_path`:: - - The path to a file containing stop words. This path is relative to the - Elasticsearch `config` directory. - - -See the <> for more information -about stop word configuration. - -[float] -=== Example configuration - -In this example, we configure the `stop` analyzer to use a specified list of -words as stop words: - -[source,console] ----------------------------- -PUT my_index -{ - "settings": { - "analysis": { - "analyzer": { - "my_stop_analyzer": { - "type": "stop", - "stopwords": ["the", "over"] - } - } - } - } -} - -POST my_index/_analyze -{ - "analyzer": "my_stop_analyzer", - "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone." -} ----------------------------- - -///////////////////// - -[source,console-result] ----------------------------- -{ - "tokens": [ - { - "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": "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 above example produces the following terms: - -[source,text] ---------------------------- -[ quick, brown, foxes, jumped, lazy, dog, s, bone ] ---------------------------- - -[float] -=== Definition - -It consists of: - -Tokenizer:: -* <> - -Token filters:: -* <> - -If you need to customize the `stop` analyzer beyond the configuration -parameters then you need to recreate it as a `custom` analyzer and modify -it, usually by adding token filters. This would recreate the built-in -`stop` analyzer and you can use it as a starting point for further -customization: - -[source,console] ----------------------------------------------------- -PUT /stop_example -{ - "settings": { - "analysis": { - "filter": { - "english_stop": { - "type": "stop", - "stopwords": "_english_" <1> - } - }, - "analyzer": { - "rebuilt_stop": { - "tokenizer": "lowercase", - "filter": [ - "english_stop" <2> - ] - } - } - } - } -} ----------------------------------------------------- -// TEST[s/\n$/\nstartyaml\n - compare_analyzers: {index: stop_example, first: stop, second: rebuilt_stop}\nendyaml\n/] - -<1> The default stopwords can be overridden with the `stopwords` - or `stopwords_path` parameters. -<2> You'd add any token filters after `english_stop`. +[[analysis-stop-analyzer]] +=== Stop Analyzer + +The `stop` analyzer is the same as the <> +but adds support for removing stop words. It defaults to using the +`_english_` stop words. + +See the link:https://github.com/elastic/elasticsearch/blob/master/docs/reference/analysis/analyzers/stop-analyzer-language-support.asciidoc[Stop Analyzer Language Support] for more information about supported stop word languages + + +[float] +=== Example output + +[source,console] +--------------------------- +POST _analyze +{ + "analyzer": "stop", + "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone." +} +--------------------------- + +///////////////////// + +[source,console-result] +---------------------------- +{ + "tokens": [ + { + "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": "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 above sentence would produce the following terms: + +[source,text] +--------------------------- +[ quick, brown, foxes, jumped, over, lazy, dog, s, bone ] +--------------------------- + +[float] +=== Configuration + +The `stop` analyzer accepts the following parameters: + +[horizontal] +`stopwords`:: + + A pre-defined stop words list like `_english_` or an array containing a + list of stop words. Defaults to `_english_`. + +`stopwords_path`:: + + The path to a file containing stop words. This path is relative to the + Elasticsearch `config` directory. + + +See the <> for more information +about stop word configuration. + +[float] +=== Example configuration + +In this example, we configure the `stop` analyzer to use a specified list of +words as stop words: + +[source,console] +---------------------------- +PUT my_index +{ + "settings": { + "analysis": { + "analyzer": { + "my_stop_analyzer": { + "type": "stop", + "stopwords": ["the", "over"] + } + } + } + } +} + +POST my_index/_analyze +{ + "analyzer": "my_stop_analyzer", + "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone." +} +---------------------------- + +///////////////////// + +[source,console-result] +---------------------------- +{ + "tokens": [ + { + "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": "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 above example produces the following terms: + +[source,text] +--------------------------- +[ quick, brown, foxes, jumped, lazy, dog, s, bone ] +--------------------------- + +[float] +=== Definition + +It consists of: + +Tokenizer:: +* <> + +Token filters:: +* <> + +If you need to customize the `stop` analyzer beyond the configuration +parameters then you need to recreate it as a `custom` analyzer and modify +it, usually by adding token filters. This would recreate the built-in +`stop` analyzer and you can use it as a starting point for further +customization: + +[source,console] +---------------------------------------------------- +PUT /stop_example +{ + "settings": { + "analysis": { + "filter": { + "english_stop": { + "type": "stop", + "stopwords": "_english_" <1> + } + }, + "analyzer": { + "rebuilt_stop": { + "tokenizer": "lowercase", + "filter": [ + "english_stop" <2> + ] + } + } + } + } +} +---------------------------------------------------- +// TEST[s/\n$/\nstartyaml\n - compare_analyzers: {index: stop_example, first: stop, second: rebuilt_stop}\nendyaml\n/] + +<1> The default stopwords can be overridden with the `stopwords` + or `stopwords_path` parameters. +<2> You'd add any token filters after `english_stop`.