Natools

Check-in [ef7006737f]
Login
Overview
Comment:tools/smaz: refactor dictionary processing in a dedicated procedure
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: ef7006737f2005f3e52f1e30da1d717a032665a2
User & Date: nat on 2016-12-01 20:10:43
Other Links: manifest | tags
Context
2016-12-02
21:12
tools/smaz: genericize Parallel_Evaluate_Dictionary check-in: 79a36ec957 user: nat tags: trunk
2016-12-01
20:10
tools/smaz: refactor dictionary processing in a dedicated procedure check-in: ef7006737f user: nat tags: trunk
2016-11-30
22:30
natools.gpr: add a profiling mode to the build check-in: 2a24860505 user: nat tags: trunk
Changes

Modified tools/smaz.adb from [b5bd7e07f7] to [d614874f0e].

178
179
180
181
182
183
184






185
186
187
188
189
190
191
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197







+
+
+
+
+
+







      --  print the given dictionary in the given file

   procedure Print_Help
     (Opt : in Getopt.Configuration;
      Output : in Ada.Text_IO.File_Type);
      --  Print the help text to the given file

   procedure Process
     (Handler : in Callback'Class;
      Word_List : in Natools.Smaz_Tools.String_Lists.List;
      Data_List : in Natools.Smaz_Tools.String_Lists.List);
      --  Perform the requested operations

   function To_Dictionary
     (Handler : in Callback'Class;
      Input : in Natools.Smaz_Tools.String_Lists.List)
     return Natools.Smaz_256.Dictionary;
      --  Convert the input into a dictionary given the option in Handler


737
738
739
740
741
742
743
744

745
746
747


748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854

855
856
857
858
859
860
861
862
863

864
865
866
867
868
869
870

871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888

889
890
891
892
893
894
895
743
744
745
746
747
748
749

750
751


752
753
754








































































































755

756
757
758
759
760
761
762
763
764

765
766
767
768
769
770
771

772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789

790
791
792
793
794
795
796
797







-
+

-
-
+
+

-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-

-
+








-
+






-
+

















-
+







               Put_Line (Output, Indent & Indent
                 & "Disable variable-length verbatim in built dictionary");
         end case;
      end loop;
   end Print_Help;


   function To_Dictionary
   procedure Process
     (Handler : in Callback'Class;
      Input : in Natools.Smaz_Tools.String_Lists.List)
     return Natools.Smaz_256.Dictionary
      Word_List : in Natools.Smaz_Tools.String_Lists.List;
      Data_List : in Natools.Smaz_Tools.String_Lists.List)
   is
      use type Natools.Smaz_Tools.String_Count;
      use type Dict_Sources.Enum;
   begin
      case Handler.Dict_Source is
         when Dict_Sources.S_Expression =>
            return Tools_256.To_Dictionary (Input, Handler.Vlen_Verbatim);

         when Dict_Sources.Text_List | Dict_Sources.Unoptimized_Text_List =>
            declare
               Counter : Natools.Smaz_Tools.Word_Counter;
            begin
               for S of Input loop
                  Natools.Smaz_Tools.Add_Substrings
                    (Counter, S, Handler.Min_Sub_Size, Handler.Max_Sub_Size);

                  if Handler.Max_Word_Size > Handler.Max_Sub_Size then
                     Natools.Smaz_Tools.Add_Words
                       (Counter, S,
                        Handler.Max_Sub_Size + 1, Handler.Max_Word_Size);
                  end if;
               end loop;

               if Handler.Filter_Threshold > 0 then
                  Natools.Smaz_Tools.Filter_By_Count
                    (Counter, Handler.Filter_Threshold);
               end if;

               if Handler.Dict_Source = Dict_Sources.Text_List then
                  declare
                     Selected, Pending : Natools.Smaz_Tools.String_Lists.List;
                  begin
                     Natools.Smaz_Tools.Simple_Dictionary_And_Pending
                       (Counter,
                        Handler.Dict_Size,
                        Selected,
                        Pending,
                        Handler.Score_Method,
                        Handler.Max_Pending);

                     return Optimize_Dictionary
                       (Tools_256.To_Dictionary
                          (Selected, Handler.Vlen_Verbatim),
                        Pending,
                        Input,
                        Handler.Job_Count,
                        Handler.Score_Method);
                  end;
               else
                  return Tools_256.To_Dictionary
                    (Natools.Smaz_Tools.Simple_Dictionary
                       (Counter, Handler.Dict_Size, Handler.Score_Method),
                     Handler.Vlen_Verbatim);
               end if;
            end;
      end case;
   end To_Dictionary;


   Opt_Config : constant Getopt.Configuration := Getopt_Config;
   Handler : Callback;
   Input_List, Input_Data : Natools.Smaz_Tools.String_Lists.List;
begin
   Process_Command_Line :
   begin
      Opt_Config.Process (Handler);
   exception
      when Getopt.Option_Error =>
         Print_Help (Opt_Config, Ada.Text_IO.Current_Error);
         Ada.Command_Line.Set_Exit_Status (Ada.Command_Line.Failure);
         return;
   end Process_Command_Line;

   if Handler.Display_Help then
      Print_Help (Opt_Config, Ada.Text_IO.Current_Output);
   end if;

   if not Handler.Need_Dictionary then
      return;
   end if;

   if not (Handler.Stat_Output or Handler.Sx_Output) then
      Handler.Sx_Output := True;
   end if;

   Read_Input_List :
   declare
      use type Actions.Enum;

      Input : constant access Ada.Streams.Root_Stream_Type'Class
        := Ada.Text_IO.Text_Streams.Stream (Ada.Text_IO.Current_Input);
      Parser : Natools.S_Expressions.Parsers.Stream_Parser (Input);
   begin
      Parser.Next;
      Natools.Smaz_Tools.Read_List (Input_List, Parser);

      if Handler.Action /= Actions.Nothing then
         Parser.Next;
         Natools.Smaz_Tools.Read_List (Input_Data, Parser);
      end if;
   end Read_Input_List;


   Build_Dictionary :
   declare
      Dictionary : Natools.Smaz_256.Dictionary
        := To_Dictionary (Handler, Input_List);
        := To_Dictionary (Handler, Word_List);
      Sx_Output : Natools.S_Expressions.Printers.Canonical
        (Ada.Text_IO.Text_Streams.Stream (Ada.Text_IO.Current_Output));
      Ada_Dictionary : constant String
        := Ada.Strings.Unbounded.To_String (Handler.Ada_Dictionary);
      Hash_Package : constant String
        := Ada.Strings.Unbounded.To_String (Handler.Hash_Package);
   begin
      Dictionary.Hash := Natools.Smaz_Tools.Linear_Search'Access;
      Natools.Smaz_Tools.List_For_Linear_Search := Input_List;
      Natools.Smaz_Tools.List_For_Linear_Search := Word_List;

      if Ada_Dictionary'Length > 0 then
         Print_Dictionary (Ada_Dictionary, Dictionary, Hash_Package);
      end if;

      if Hash_Package'Length > 0 then
         Natools.Smaz_Tools.GNAT.Build_Perfect_Hash (Input_List, Hash_Package);
         Natools.Smaz_Tools.GNAT.Build_Perfect_Hash (Word_List, Hash_Package);
      end if;

      if Handler.Sx_Dict_Output then
         Sx_Output.Open_List;
         for I in Dictionary.Offsets'Range loop
            Sx_Output.Append_String
              (Natools.Smaz_256.Dict_Entry (Dictionary, I));
         end loop;
         Sx_Output.Close_List;
      end if;

      case Handler.Action is
         when Actions.Nothing => null;

         when Actions.Decode =>
            if Handler.Sx_Output then
               Sx_Output.Open_List;
               for S of Input_Data loop
               for S of Data_List loop
                  Sx_Output.Append_String
                    (Natools.Smaz_256.Decompress (Dictionary, To_SEA (S)));
               end loop;
               Sx_Output.Close_List;
            end if;

            if Handler.Stat_Output then
904
905
906
907
908
909
910
911

912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931

932
933
934
935
936
937
938
806
807
808
809
810
811
812

813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832

833
834
835
836
837
838
839
840







-
+



















-
+







                        & Natural'Image (Output)
                        & Ada.Characters.Latin_1.HT
                        & Float'Image (Float (Original) / Float (Output)));
                  end Print_Line;
                  Original_Total : Natural := 0;
                  Output_Total : Natural := 0;
               begin
                  for S of Input_Data loop
                  for S of Data_List loop
                     declare
                        Original_Size : constant Natural := S'Length;
                        Output_Size : constant Natural
                          := Natools.Smaz_256.Decompress
                             (Dictionary, To_SEA (S))'Length;
                     begin
                        Print_Line (Original_Size, Output_Size);
                        Original_Total := Original_Total + Original_Size;
                        Output_Total := Output_Total + Output_Size;
                     end;
                  end loop;

                  Print_Line (Original_Total, Output_Total);
               end;
            end if;

         when Actions.Encode =>
            if Handler.Sx_Output then
               Sx_Output.Open_List;
               for S of Input_Data loop
               for S of Data_List loop
                  Sx_Output.Append_Atom
                    (Natools.Smaz_256.Compress (Dictionary, S));
               end loop;
               Sx_Output.Close_List;
            end if;

            if Handler.Stat_Output then
952
953
954
955
956
957
958
959

960
961
962
963
964
965
966
854
855
856
857
858
859
860

861
862
863
864
865
866
867
868







-
+







                        & Ada.Characters.Latin_1.HT
                        & Float'Image (Float (Base64) / Float (Original)));
                  end Print_Line;
                  Original_Total : Natural := 0;
                  Output_Total : Natural := 0;
                  Base64_Total : Natural := 0;
               begin
                  for S of Input_Data loop
                  for S of Data_List loop
                     declare
                        Original_Size : constant Natural := S'Length;
                        Output_Size : constant Natural
                          := Natools.Smaz_256.Compress (Dictionary, S)'Length;
                        Base64_Size : constant Natural
                          := ((Output_Size + 2) / 3) * 4;
                     begin
977
978
979
980
981
982
983
984

985
986
987
988
989
990
991
879
880
881
882
883
884
885

886
887
888
889
890
891
892
893







-
+








         when Actions.Evaluate =>
            declare
               Total_Size : Ada.Streams.Stream_Element_Count;
               Counts : Tools_256.Dictionary_Counts;
            begin
               Evaluate_Dictionary (Handler.Job_Count,
                  Dictionary, Input_Data, Total_Size, Counts);
                  Dictionary, Data_List, Total_Size, Counts);

               if Handler.Sx_Output then
                  Sx_Output.Open_List;
                  Sx_Output.Append_String (Ada.Strings.Fixed.Trim
                    (Ada.Streams.Stream_Element_Count'Image (Total_Size),
                     Ada.Strings.Both));

1114
1115
1116
1117
1118
1119
1120































































1121
















































1122
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085

1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134







+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

                       Tools_256.Score_Frequency'Access);
                     Print_Min_Max ("gain",
                       Tools_256.Score_Gain'Access);
                  end;
               end if;
            end;
      end case;
   end Process;


   function To_Dictionary
     (Handler : in Callback'Class;
      Input : in Natools.Smaz_Tools.String_Lists.List)
     return Natools.Smaz_256.Dictionary
   is
      use type Natools.Smaz_Tools.String_Count;
      use type Dict_Sources.Enum;
   begin
      case Handler.Dict_Source is
         when Dict_Sources.S_Expression =>
            return Tools_256.To_Dictionary (Input, Handler.Vlen_Verbatim);

         when Dict_Sources.Text_List | Dict_Sources.Unoptimized_Text_List =>
            declare
               Counter : Natools.Smaz_Tools.Word_Counter;
            begin
               for S of Input loop
                  Natools.Smaz_Tools.Add_Substrings
                    (Counter, S, Handler.Min_Sub_Size, Handler.Max_Sub_Size);

                  if Handler.Max_Word_Size > Handler.Max_Sub_Size then
                     Natools.Smaz_Tools.Add_Words
                       (Counter, S,
                        Handler.Max_Sub_Size + 1, Handler.Max_Word_Size);
                  end if;
               end loop;

               if Handler.Filter_Threshold > 0 then
                  Natools.Smaz_Tools.Filter_By_Count
                    (Counter, Handler.Filter_Threshold);
               end if;

               if Handler.Dict_Source = Dict_Sources.Text_List then
                  declare
                     Selected, Pending : Natools.Smaz_Tools.String_Lists.List;
                  begin
                     Natools.Smaz_Tools.Simple_Dictionary_And_Pending
                       (Counter,
                        Handler.Dict_Size,
                        Selected,
                        Pending,
                        Handler.Score_Method,
                        Handler.Max_Pending);

                     return Optimize_Dictionary
                       (Tools_256.To_Dictionary
                          (Selected, Handler.Vlen_Verbatim),
                        Pending,
                        Input,
                        Handler.Job_Count,
                        Handler.Score_Method);
                  end;
               else
                  return Tools_256.To_Dictionary
                    (Natools.Smaz_Tools.Simple_Dictionary
                       (Counter, Handler.Dict_Size, Handler.Score_Method),
                     Handler.Vlen_Verbatim);
               end if;
            end;
      end case;
   end Build_Dictionary;
   end To_Dictionary;


   Opt_Config : constant Getopt.Configuration := Getopt_Config;
   Handler : Callback;
   Input_List, Input_Data : Natools.Smaz_Tools.String_Lists.List;
begin
   Process_Command_Line :
   begin
      Opt_Config.Process (Handler);
   exception
      when Getopt.Option_Error =>
         Print_Help (Opt_Config, Ada.Text_IO.Current_Error);
         Ada.Command_Line.Set_Exit_Status (Ada.Command_Line.Failure);
         return;
   end Process_Command_Line;

   if Handler.Display_Help then
      Print_Help (Opt_Config, Ada.Text_IO.Current_Output);
   end if;

   if not Handler.Need_Dictionary then
      return;
   end if;

   if not (Handler.Stat_Output or Handler.Sx_Output) then
      Handler.Sx_Output := True;
   end if;

   Read_Input_List :
   declare
      use type Actions.Enum;

      Input : constant access Ada.Streams.Root_Stream_Type'Class
        := Ada.Text_IO.Text_Streams.Stream (Ada.Text_IO.Current_Input);
      Parser : Natools.S_Expressions.Parsers.Stream_Parser (Input);
   begin
      Parser.Next;
      Natools.Smaz_Tools.Read_List (Input_List, Parser);

      if Handler.Action /= Actions.Nothing then
         Parser.Next;
         Natools.Smaz_Tools.Read_List (Input_Data, Parser);
      end if;
   end Read_Input_List;

   Process (Handler, Input_List, Input_Data);

end Smaz;