Added language option - closes #115

Andrew Kane
1 parent 17ed24fd
Showing 3 changed files with 22 additions and 5 deletions Show diff stats
CHANGELOG.md
README.md
lib/searchkick/reindex.rb
 ## 0.5.1 [unreleased]
 - Replaced stop words with common terms query
+- Added language option
 - Fixed bug with empty array in where clause
 ## 0.5.0
@@ -176,6 +176,18 @@ Available options are:
 :text_end
 ```
+### Language [master]
+
+Searchkick defaults to English for stemming.  To change this, use:
+
+```ruby
+class Product < ActiveRecord::Base
+  searchkick language: "German"
+end
+```
+
+[See the list of languages](http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/analysis-snowball-tokenfilter.html)
+
 ### Synonyms
 ```ruby
@@ -94,24 +94,24 @@ module Searchkick
               searchkick_keyword: {
                 type: "custom",
                 tokenizer: "keyword",
-                filter: ["lowercase", "snowball"]
+                filter: ["lowercase", "searchkick_stemmer"]
               },
               default_index: {
                 type: "custom",
                 tokenizer: "standard",
                 # synonym should come last, after stemming and shingle
-                # shingle must come before snowball
-                filter: ["standard", "lowercase", "asciifolding", "searchkick_index_shingle", "snowball"]
+                # shingle must come before searchkick_stemmer
+                filter: ["standard", "lowercase", "asciifolding", "searchkick_index_shingle", "searchkick_stemmer"]
               },
               searchkick_search: {
                 type: "custom",
                 tokenizer: "standard",
-                filter: ["standard", "lowercase", "asciifolding", "searchkick_search_shingle", "snowball"]
+                filter: ["standard", "lowercase", "asciifolding", "searchkick_search_shingle", "searchkick_stemmer"]
               },
               searchkick_search2: {
                 type: "custom",
                 tokenizer: "standard",
-                filter: ["standard", "lowercase", "asciifolding", "snowball"]
+                filter: ["standard", "lowercase", "asciifolding", "searchkick_stemmer"]
               },
               # https://github.com/leschenko/elasticsearch_autocomplete/blob/master/lib/elasticsearch_autocomplete/analyzers.rb
               searchkick_autocomplete_index: {
@@ -190,6 +190,10 @@ module Searchkick
                 type: "nGram",
                 min_gram: 1,
                 max_gram: 50
+              },
+              searchkick_stemmer: {
+                type: "snowball",
+                language: options[:language] || "English"
               }
             },
             tokenizer: {
1	## 0.5.1 [unreleased]	1	## 0.5.1 [unreleased]
2		2
3	- Replaced stop words with common terms query	3	- Replaced stop words with common terms query
		4	+- Added language option
4	- Fixed bug with empty array in where clause	5	- Fixed bug with empty array in where clause
5		6
6	## 0.5.0	7	## 0.5.0
	@@ -176,6 +176,18 @@ Available options are:		@@ -176,6 +176,18 @@ Available options are:
176	:text_end	176	:text_end
177	```	177	```
178		178
		179	+### Language [master]
		180	+
		181	+Searchkick defaults to English for stemming. To change this, use:
		182	+
		183	+```ruby
		184	+class Product < ActiveRecord::Base
		185	+ searchkick language: "German"
		186	+end
		187	+```
		188	+
		189	+[See the list of languages](http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/analysis-snowball-tokenfilter.html)
		190	+
179	### Synonyms	191	### Synonyms
180		192
181	```ruby	193	```ruby