make-text-search 0.1 → 0.1.1

data/README.rdoc

@@ -45,14 +45,13 @@ The content added to the index can be filtered. Right now there are two filters:
 
   class Post < ActiveRecord::Base
     has_text_search :title, :filter => :substrings
-    has_text_search :content, :intro :filter => [:strip_html, :substrings]
+    has_text_search :content, :intro, :filter => [:strip_html, :substrings]
   end
 
 You can use several filters using an array. The order is important. If you use both +:substrings+ and +:strip_html+, +:strip_html+ should be the first.
 
 +:substrings+ let you search inside the words. For example, the word +knowledge+ can be found with +owled+ if you filter the content with +:substrings+.
 
-+:strip_html+ elimina las etiquetas HTML y traduce las entities a su versión en UTF-8. Por ejemplo
 +:strip_html+ removes the HTML tags and it translates HTML entities to its equivalent in UTF-8:
 
   Ir a <a href="http://www.google.es">Google Espa&ntilde;a</a>
@@ -61,6 +60,35 @@ will be
 
   Ir a Google España
 
+=== Language
+
+The documents can be parsed using a language. You can set the default language with +config.make_text_search.default_language+. The initial value is nil, which means that the documents are parsed in a agnostic way.
+
+If you want to set the default language add this line to the +config/application.rb+ file.
+
+  config.make_text_search.default_language = "spanish"
+
+If you want to have a different language for every record you have to implement the +text_search_language+ instance method. For example
+
+  class Post < ActiveRecord::Base
+    has_text_search :title, :filter => :substrings
+    has_text_search :content, :intro, :filter => [:strip_html, :substrings]
+
+    def text_search_language
+      case locale
+      when "es" "spanish"
+      when "en" "english"
+      when "de" "german"
+      when "it" "italian"
+      else
+        Rails.application.config.make_text_search.default_language
+      end
+    end
+  end
+
+You can get the available languages of your PostgreSQL server with
+
+  select * from pg_ts_dict;
 
 == Search
 
@@ -71,6 +99,13 @@ To perform search you have to use the scope #search_text
 
   Post.published.search_text("foo & bar").paginate(:page => params[:page])
 
+The query language is the same used by PostgreSQL. See http://www.postgresql.org/docs/8.4/static/datatype-textsearch.html#DATATYPE-TSQUERY
+
+= Resources
+
+* http://www.slideshare.net/billkarwin/full-text-search-in-postgresql
+* http://www.sai.msu.su/~megera/postgres/fts/fts.pdf
+
 == TODO
 
 * Query builder. Add & and | operators

data/lib/make-text-search.rb

@@ -2,7 +2,6 @@ module MakeTextSearch
 
   ActiveSupport.on_load(:active_record) do
     require 'make-text-search/models'
-    require 'make-text-search/query'
     require 'make-text-search/schema'
     require 'make-text-search/filters'
 
@@ -14,7 +13,7 @@ module MakeTextSearch
   class Railtie < ::Rails::Railtie
     config.make_text_search = ActiveSupport::OrderedOptions.new
     config.make_text_search.table_name = "text_search_documents"
-    config.make_text_search.default_language = "english"
+    config.make_text_search.default_language = nil
 
     generators do
       load "generators/migration.rb"

data/lib/make-text-search/adapters/postgresql_ts.rb

@@ -38,15 +38,17 @@ module MakeTextSearch
         table_name = Rails.application.config.make_text_search.table_name
         record_type = quote record_class.name
         record_id = quote record.id
-        language = quote record.text_search_language
+        language = record.text_search_language
 
-        document = "to_tsvector(#{language}, #{quote record.text_search_build_document})"
+        # If language is nil the tsvector will be generated without language
+        document = "to_tsvector(#{language ? quote(language.to_s) + ", " : ""}#{quote record.text_search_build_document})"
 
+        # Reduce the number of operations in the index using SELECT+UPDATE instead of DELETE+INSERT
         if connection.select_value("SELECT count(*) FROM #{table_name} WHERE #{_where_record record}").to_i == 0
           connection.insert(%[INSERT INTO #{table_name}
                               (record_type, record_id, language, document)
                              VALUES
-                              (#{record_type}, #{record_id}, #{language}, #{document})])
+                              (#{record_type}, #{record_id}, #{quote language}, #{document})])
         else
           connection.update(%[UPDATE #{table_name} SET document = #{document} WHERE #{_where_record record}])
         end
@@ -60,6 +62,19 @@ module MakeTextSearch
         "record_type = #{quote record.class.name} AND record_id = #{quote record.id}"
       end
 
+
+      # Query actions
+      def scope_search_text(model, query, language = Rails.application.config.make_text_search.default_language)
+        db_connection = model.connection
+
+        if language
+          query = "to_tsquery(#{db_connection.quote language}, #{db_connection.quote query})"
+        else
+          query = "to_tsquery(#{db_connection.quote query})"
+        end
+        model.where %[#{model.table_name}.id IN (SELECT record_id FROM #{Rails.application.config.make_text_search.table_name} WHERE record_type = #{db_connection.quote model.name} AND document @@ #{query})]
+      end
+
     end
   end
 end

data/lib/make-text-search/models.rb

@@ -26,7 +26,7 @@ module MakeTextSearch
       end
 
       def search_text(query)
-        where MakeTextSearch.build_condition(self, query)
+        connection.text_search_adapter.scope_search_text(self, query)
       end
     end
 

metadata

@@ -1,12 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: make-text-search
 version: !ruby/object:Gem::Version 
-  hash: 9
+  hash: 25
   prerelease: false
   segments: 
   - 0
   - 1
-  version: "0.1"
+  - 1
+  version: 0.1.1
 platform: ruby
 authors: 
 - Ayose Cazorla
@@ -30,10 +31,9 @@ files:
 - lib/make-text-search.rb
 - lib/generators/templates/migration.rb
 - lib/generators/migration.rb
-- lib/make-text-search/query.rb
 - lib/make-text-search/html_entities.dat
-- lib/make-text-search/models.rb
 - lib/make-text-search/filters.rb
+- lib/make-text-search/models.rb
 - lib/make-text-search/adapters/postgresql_ts.rb
 - lib/make-text-search/schema.rb
 - test/schema_test.rb

data/lib/make-text-search/query.rb

@@ -1,8 +0,0 @@
-class <<MakeTextSearch
-  def build_condition(model, query)
-    # TODO use has_text_search_for_postgresql? to implement all the backends
-
-    db_connection =  model.connection
-    %[#{model.table_name}.id IN (SELECT record_id FROM #{Rails.application.config.make_text_search.table_name} WHERE record_type = #{db_connection.quote model.name} AND document @@ to_tsquery(#{db_connection.quote query}))]
-  end
-end