lib/searchkick/index.rb in searchkick-0.9.0 vs lib/searchkick/index.rb in searchkick-0.9.1

@@ -128,11 +128,12 @@
       end
     end
 
     # reindex
 
-    def create_index
+    def create_index(options = {})
+      index_options = options[:index_options] || self.index_options
       index = Searchkick::Index.new("#{name}_#{Time.now.strftime('%Y%m%d%H%M%S%L')}", @options)
       index.create(index_options)
       index
     end
 
@@ -151,11 +152,11 @@
     def reindex_scope(scope, options = {})
       skip_import = options[:import] == false
 
       clean_indices
 
-      index = create_index
+      index = create_index(index_options: scope.searchkick_index_options)
 
       # check if alias exists
       if alias_exists?
         # import before swap
         index.import_scope(scope) unless skip_import
@@ -215,22 +216,27 @@
                 tokenizer: "keyword",
                 filter: ["lowercase"] + (options[:stem_conversions] == false ? [] : ["searchkick_stemmer"])
               },
               default_index: {
                 type: "custom",
+                # character filters -> tokenizer -> token filters
+                # https://www.elastic.co/guide/en/elasticsearch/guide/current/analysis-intro.html
+                char_filter: ["ampersand"],
                 tokenizer: "standard",
                 # synonym should come last, after stemming and shingle
                 # shingle must come before searchkick_stemmer
                 filter: ["standard", "lowercase", "asciifolding", "searchkick_index_shingle", "searchkick_stemmer"]
               },
               searchkick_search: {
                 type: "custom",
+                char_filter: ["ampersand"],
                 tokenizer: "standard",
                 filter: ["standard", "lowercase", "asciifolding", "searchkick_search_shingle", "searchkick_stemmer"]
               },
               searchkick_search2: {
                 type: "custom",
+                char_filter: ["ampersand"],
                 tokenizer: "standard",
                 filter: ["standard", "lowercase", "asciifolding", "searchkick_stemmer"]
               },
               # https://github.com/leschenko/elasticsearch_autocomplete/blob/master/lib/elasticsearch_autocomplete/analyzers.rb
               searchkick_autocomplete_index: {
@@ -309,11 +315,21 @@
                 type: "nGram",
                 min_gram: 1,
                 max_gram: 50
               },
               searchkick_stemmer: {
-                type: "snowball",
+                # use stemmer if language is lowercase, snowball otherwise
+                # TODO deprecate language option in favor of stemmer
+                type: options[:language] == options[:language].to_s.downcase ? "stemmer" : "snowball",
                 language: options[:language] || "English"
+              }
+            },
+            char_filter: {
+              # https://www.elastic.co/guide/en/elasticsearch/guide/current/custom-analyzers.html
+              # &_to_and
+              ampersand: {
+                type: "mapping",
+                mappings: ["&=> and "]
               }
             },
             tokenizer: {
               searchkick_autocomplete_ngram: {
                 type: "edgeNGram",