client.rb in ultrasphinx-1.11

- old
+ new

@@ -24,19 +24,21 @@
   #   client.filters << Riddle::Client::Filter.new("birthday",
   #     Time.at(1975, 1, 1).to_i..Time.at(1985, 1, 1).to_i, false)
   #
   class Client
     Commands = {
-      :search  => 0, # SEARCHD_COMMAND_SEARCH
-      :excerpt => 1, # SEARCHD_COMMAND_EXCERPT
-      :update  => 2  # SEARCHD_COMMAND_UPDATE
+      :search   => 0, # SEARCHD_COMMAND_SEARCH
+      :excerpt  => 1, # SEARCHD_COMMAND_EXCERPT
+      :update   => 2, # SEARCHD_COMMAND_UPDATE
+      :keywords => 3  # SEARCHD_COMMAND_KEYWORDS
     }
     
     Versions = {
-      :search  => 0x112, # VER_COMMAND_SEARCH
-      :excerpt => 0x100, # VER_COMMAND_EXCERPT
-      :update  => 0x101  # VER_COMMAND_UPDATE
+      :search   => 0x113, # VER_COMMAND_SEARCH
+      :excerpt  => 0x100, # VER_COMMAND_EXCERPT
+      :update   => 0x101, # VER_COMMAND_UPDATE
+      :keywords => 0x100  # VER_COMMAND_KEYWORDS
     }
     
     Statuses = {
       :ok      => 0, # SEARCHD_OK
       :error   => 1, # SEARCHD_ERROR
@@ -48,11 +50,11 @@
       :all        => 0, # SPH_MATCH_ALL
       :any        => 1, # SPH_MATCH_ANY
       :phrase     => 2, # SPH_MATCH_PHRASE
       :boolean    => 3, # SPH_MATCH_BOOLEAN
       :extended   => 4, # SPH_MATCH_EXTENDED
-      :fullsacn   => 5, # SPH_MATCH_FULLSCAN
+      :fullscan   => 5, # SPH_MATCH_FULLSCAN
       :extended2  => 6  # SPH_MATCH_EXTENDED2
     }
     
     RankModes = {
       :proximity_bm25 => 0, # SPH_RANK_PROXIMITY_BM25
@@ -156,12 +158,12 @@
       }
     end
     
     # Append a query to the queue. This uses the same parameters as the query
     # method.
-    def append_query(search, index = '*')
-      @queue << query_message(search, index)
+    def append_query(search, index = '*', comments = '')
+      @queue << query_message(search, index, comments)
     end
     
     # Run all the queries currently in the queue. This will return an array of
     # results hashes.
     def run
@@ -202,18 +204,13 @@
           doc = is_64_bit > 0 ? response.next_64bit_int : response.next_int
           weight = response.next_int
 
           result[:matches] << {:doc => doc, :weight => weight, :index => i, :attributes => {}}
           result[:attribute_names].each do |attr|
-            case result[:attributes][attr]
-            when AttributeTypes[:float]
-              result[:matches].last[:attributes][attr] = response.next_float
-            when AttributeTypes[:multi]
-              result[:matches].last[:attributes][attr] = response.next_int_array
-            else
-              result[:matches].last[:attributes][attr] = response.next_int
-            end
+            result[:matches].last[:attributes][attr] = attribute_from_type(
+              result[:attributes][attr], response
+            )
           end
         end
 
         result[:total] = response.next_int.to_i || 0
         result[:total_found] = response.next_int.to_i || 0
@@ -273,12 +270,12 @@
     # 
     # <tt>:status</tt> is the error code for the query - and if there was a
     # related warning, it will be under the <tt>:warning</tt> key. Fatal errors
     # will be described under <tt>:error</tt>.
     #
-    def query(search, index = '*')      
-      @queue << query_message(search, index)
+    def query(search, index = '*', comments = '')
+      @queue << query_message(search, index, comments)
       self.run.first
     end
     
     # Build excerpts from search terms (the +words+) and the text of documents. Excerpts are bodies of text that have the +words+ highlighted.
     # They may also be abbreviated to fit within a word limit.
@@ -356,10 +353,34 @@
       )
       
       response.next_int
     end
     
+    # Generates a keyword list for a given query. Each keyword is represented
+    # by a hash, with keys :tokenised and :normalised. If return_hits is set to
+    # true it will also report on the number of hits and documents for each
+    # keyword (see :hits and :docs keys respectively).
+    def keywords(query, index, return_hits = false)
+      response = Response.new request(
+        :keywords,
+        keywords_message(query, index, return_hits)
+      )
+      
+      (0...response.next_int).collect do
+        hash = {}
+        hash[:tokenised]  = response.next
+        hash[:normalised] = response.next
+        
+        if return_hits
+          hash[:docs] = response.next_int
+          hash[:hits] = response.next_int
+        end
+        
+        hash
+      end
+    end
+    
     private
     
     # Connects to the Sphinx daemon, and yields a socket to use. The socket is
     # closed at the end of the block.
     def connect(&block)
@@ -437,11 +458,11 @@
         raise ResponseError, "Unknown searchd error (status: #{status})"
       end
     end
     
     # Generation of the message to send to Sphinx for a search.
-    def query_message(search, index)
+    def query_message(search, index, comments = '')
       message = Message.new
       
       # Mode, Limits, Sort Mode
       message.append_ints @offset, @limit, MatchModes[@match_mode],
         RankModes[@rank_mode], SortModes[@sort_mode]
@@ -498,10 +519,12 @@
       @field_weights.each do |key,val|
         message.append_string key
         message.append_int val
       end
       
+      message.append_string comments
+      
       message.to_s
     end
     
     # Generation of the message to send to Sphinx for an excerpts request.
     def excerpts_message(options)
@@ -541,8 +564,30 @@
         message.append_64bit_int key # document ID
         message.append_ints *values # array of new values (integers)
       end
       
       message.to_s
+    end
+    
+    # Generates the simple message to send to the daemon for a keywords request.
+    def keywords_message(query, index, return_hits)
+      message = Message.new
+      
+      message.append_string query
+      message.append_string index
+      message.append_int return_hits ? 1 : 0
+      
+      message.to_s
+    end
+    
+    def attribute_from_type(type, response)
+      type -= AttributeTypes[:multi] if is_multi = type > AttributeTypes[:multi]
+      
+      case type
+      when AttributeTypes[:float]
+        is_multi ? response.next_float_array : response.next_float
+      else
+        is_multi ? response.next_int_array   : response.next_int
+      end
     end
   end
 end