Added support for Hunspell - closes #1460

Andrew Kane
1 parent 4e11926e
Showing 4 changed files with 28 additions and 1 deletions Show diff stats
CHANGELOG.md
README.md
lib/searchkick/index_options.rb
test/language_test.rb
 ## 4.4.3 (unreleased)
  
+- Added support for Hunspell
 - Fixed warning about accessing system indices
  
 ## 4.4.2 (2020-11-23)
@@ -322,6 +322,14 @@ See the [list of stemmers](https://www.elastic.co/guide/en/elasticsearch/referen
 - `ukrainian` - [analysis-ukrainian plugin](https://www.elastic.co/guide/en/elasticsearch/plugins/7.4/analysis-ukrainian.html)
 - `vietnamese` - [analysis-vietnamese plugin](https://github.com/duydo/elasticsearch-analysis-vietnamese)
  
+You can also use a Hunspell dictionary for stemming. [master]
+
+```ruby
+class Product < ApplicationRecord
+  searchkick language: {type: "hunspell", locale: "en_US"}
+end
+```
+
 Disable stemming with:
  
 ```ruby
@@ -153,7 +153,11 @@ module Searchkick
         }
       }
  
-      update_language(settings, language)
+      if language.is_a?(Hash) && language[:type] == "hunspell"
+        update_hunspell(settings, language)
+      else
+        update_language(settings, language)
+      end
       update_stemming(settings)
  
       if Searchkick.env == "test"
@@ -196,6 +200,11 @@ module Searchkick
       settings
     end
  
+    # supports all hunspell token filter options
+    def update_hunspell(settings, language)
+      settings[:analysis][:filter][:searchkick_stemmer] = language
+    end
+
     def update_language(settings, language)
       case language
       when "chinese"
@@ -90,6 +90,15 @@ class LanguageTest &lt; Minitest::Test
     end
   end
  
+  def test_hunspell
+    skip if ci?
+
+    with_options({language: {type: "hunspell", locale: "en_US"}}) do
+      store_names ["the foxes jumping quickly"]
+      assert_language_search "fox", ["the foxes jumping quickly"]
+    end
+  end
+
   def assert_language_search(term, expected)
     assert_search term, expected, {misspellings: false}
   end
1	1	## 4.4.3 (unreleased)
2	2
	3	+- Added support for Hunspell
3	4	- Fixed warning about accessing system indices
4	5
5	6	## 4.4.2 (2020-11-23)
...	...
...	...	@@ -322,6 +322,14 @@ See the [list of stemmers](https://www.elastic.co/guide/en/elasticsearch/referen
322	322	- `ukrainian` - [analysis-ukrainian plugin](https://www.elastic.co/guide/en/elasticsearch/plugins/7.4/analysis-ukrainian.html)
323	323	- `vietnamese` - [analysis-vietnamese plugin](https://github.com/duydo/elasticsearch-analysis-vietnamese)
324	324
	325	+You can also use a Hunspell dictionary for stemming. [master]
	326	+
	327	+```ruby
	328	+class Product < ApplicationRecord
	329	+ searchkick language: {type: "hunspell", locale: "en_US"}
	330	+end
	331	+```
	332	+
325	333	Disable stemming with:
326	334
327	335	```ruby
...	...
...	...	@@ -153,7 +153,11 @@ module Searchkick
153	153	}
154	154	}
155	155
156		- update_language(settings, language)
	156	+ if language.is_a?(Hash) && language[:type] == "hunspell"
	157	+ update_hunspell(settings, language)
	158	+ else
	159	+ update_language(settings, language)
	160	+ end
157	161	update_stemming(settings)
158	162
159	163	if Searchkick.env == "test"
...	...	@@ -196,6 +200,11 @@ module Searchkick
196	200	settings
197	201	end
198	202
	203	+ # supports all hunspell token filter options
	204	+ def update_hunspell(settings, language)
	205	+ settings[:analysis][:filter][:searchkick_stemmer] = language
	206	+ end
	207	+
199	208	def update_language(settings, language)
200	209	case language
201	210	when "chinese"
...	...
...	...	@@ -90,6 +90,15 @@ class LanguageTest < Minitest::Test
90	90	end
91	91	end
92	92
	93	+ def test_hunspell
	94	+ skip if ci?
	95	+
	96	+ with_options({language: {type: "hunspell", locale: "en_US"}}) do
	97	+ store_names ["the foxes jumping quickly"]
	98	+ assert_language_search "fox", ["the foxes jumping quickly"]
	99	+ end
	100	+ end
	101	+
93	102	def assert_language_search(term, expected)
94	103	assert_search term, expected, {misspellings: false}
95	104	end
...	...