Natools

Check-in [966f7e5239]
Login
Overview
Comment:tools/smaz: partially genericize Print_Dictionary
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: 966f7e5239cc144e888b17e2f67de1cebbd3b0c8
User & Date: nat on 2016-12-07 21:36:23
Other Links: manifest | tags
Context
2016-12-08
22:29
tools/smaz: genericize Process check-in: cfdc0a7979 user: nat tags: trunk
2016-12-07
21:36
tools/smaz: partially genericize Print_Dictionary check-in: 966f7e5239 user: nat tags: trunk
2016-12-06
22:40
tools/smaz: refactor dictionary holder inside the generic package check-in: 1eac1c8b76 user: nat tags: trunk
Changes

Modified tools/smaz.adb from [acdde2a761] to [c5aac94447].

127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144

   function Last_Code (Dict : in Natools.Smaz_256.Dictionary)
     return Ada.Streams.Stream_Element
     is (Dict.Last_Code);
      --  Return the last valid entry

   procedure Print_Dictionary
     (Filename : in String;
      Dictionary : in Natools.Smaz_256.Dictionary;
      Hash_Package_Name : in String := "");
   procedure Print_Dictionary
     (Output : in Ada.Text_IO.File_Type;
      Dictionary : in Natools.Smaz_256.Dictionary;
      Hash_Package_Name : in String := "");
      --  print the given dictionary in the given file

   procedure Print_Help
     (Opt : in Getopt.Configuration;







<
<
<
<







127
128
129
130
131
132
133




134
135
136
137
138
139
140

   function Last_Code (Dict : in Natools.Smaz_256.Dictionary)
     return Ada.Streams.Stream_Element
     is (Dict.Last_Code);
      --  Return the last valid entry

   procedure Print_Dictionary




     (Output : in Ada.Text_IO.File_Type;
      Dictionary : in Natools.Smaz_256.Dictionary;
      Hash_Package_Name : in String := "");
      --  print the given dictionary in the given file

   procedure Print_Help
     (Opt : in Getopt.Configuration;
203
204
205
206
207
208
209






210
211
212
213
214
215
216
         Counts : in out Dictionary_Counts);

      with procedure Filter_By_Count
        (Counter : in out Word_Counter;
         Threshold_Count : in String_Count);

      with function Last_Code (Dict : in Dictionary) return Dictionary_Entry;







      with function Remove_Element
        (Dict : in Dictionary;
         Element : in Dictionary_Entry)
        return Dictionary;

      with function Simple_Dictionary







>
>
>
>
>
>







199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
         Counts : in out Dictionary_Counts);

      with procedure Filter_By_Count
        (Counter : in out Word_Counter;
         Threshold_Count : in String_Count);

      with function Last_Code (Dict : in Dictionary) return Dictionary_Entry;

      with procedure Print_Dictionary
        (Output : in Ada.Text_IO.File_Type;
         Dict : in Dictionary;
         Hash_Package_Name : in String := "")
        is <>;

      with function Remove_Element
        (Dict : in Dictionary;
         Element : in Dictionary_Entry)
        return Dictionary;

      with function Simple_Dictionary
280
281
282
283
284
285
286






287
288
289
290
291
292
293
         Dict : in Dictionary;
         Corpus : in String_Lists.List;
         Compressed_Size : out Ada.Streams.Stream_Element_Count;
         Counts : out Dictionary_Counts);
         --  Return the same results as Natools.Smaz.Tools.Evaluate_Dictionary,
         --  but hopefully more quickly, using Job_Count tasks.







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








>
>
>
>
>
>







282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
         Dict : in Dictionary;
         Corpus : in String_Lists.List;
         Compressed_Size : out Ada.Streams.Stream_Element_Count;
         Counts : out Dictionary_Counts);
         --  Return the same results as Natools.Smaz.Tools.Evaluate_Dictionary,
         --  but hopefully more quickly, using Job_Count tasks.

      procedure Print_Dictionary
        (Filename : in String;
         Dict : in Dictionary;
         Hash_Package_Name : in String := "");
         --  print the given dictionary in the given file

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

503
504
505
506
507
508
509




















510
511
512
513
514
515
516
         Cursor : String_Lists.Cursor := String_Lists.First (Corpus);
      begin
         Compressed_Size := 0;
         Counts := (others => 0);
         Parallel_Run (Cursor, Job_Count);
      end Parallel_Evaluate_Dictionary;






















      function To_Dictionary
        (Handler : in Callback'Class;
         Input : in String_Lists.List;
         Method : in Methods)
        return Dictionary
      is







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
         Cursor : String_Lists.Cursor := String_Lists.First (Corpus);
      begin
         Compressed_Size := 0;
         Counts := (others => 0);
         Parallel_Run (Cursor, Job_Count);
      end Parallel_Evaluate_Dictionary;


      procedure Print_Dictionary
        (Filename : in String;
         Dict : in Dictionary;
         Hash_Package_Name : in String := "") is
      begin
         if Filename = "-" then
            Print_Dictionary
              (Ada.Text_IO.Current_Output, Dict, Hash_Package_Name);
         elsif Filename'Length > 0 then
            declare
               File : Ada.Text_IO.File_Type;
            begin
               Ada.Text_IO.Create (File, Name => Filename);
               Print_Dictionary (File, Dict, Hash_Package_Name);
               Ada.Text_IO.Close (File);
            end;
         end if;
      end Print_Dictionary;


      function To_Dictionary
        (Handler : in Callback'Class;
         Input : in String_Lists.List;
         Method : in Methods)
        return Dictionary
      is
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
      R.Add_Option ("no-vlen-verbatim",   No_Argument,       No_Vlen_Verbatim);
      R.Add_Option ("score-method",       Required_Argument, Score_Method);
      R.Add_Option ("vlen-verbatim",      No_Argument,       Vlen_Verbatim);

      return R;
   end Getopt_Config;


   procedure Print_Dictionary
     (Filename : in String;
      Dictionary : in Natools.Smaz_256.Dictionary;
      Hash_Package_Name : in String := "") is
   begin
      if Filename = "-" then
         Print_Dictionary
           (Ada.Text_IO.Current_Output, Dictionary, Hash_Package_Name);
      elsif Filename'Length > 0 then
         declare
            File : Ada.Text_IO.File_Type;
         begin
            Ada.Text_IO.Create (File, Name => Filename);
            Print_Dictionary (File, Dictionary, Hash_Package_Name);
            Ada.Text_IO.Close (File);
         end;
      end if;
   end Print_Dictionary;


   procedure Print_Dictionary
     (Output : in Ada.Text_IO.File_Type;
      Dictionary : in Natools.Smaz_256.Dictionary;
      Hash_Package_Name : in String := "")
   is
      procedure Put_Line (Line : in String);







<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<







752
753
754
755
756
757
758




















759
760
761
762
763
764
765
      R.Add_Option ("no-vlen-verbatim",   No_Argument,       No_Vlen_Verbatim);
      R.Add_Option ("score-method",       Required_Argument, Score_Method);
      R.Add_Option ("vlen-verbatim",      No_Argument,       Vlen_Verbatim);

      return R;
   end Getopt_Config;






















   procedure Print_Dictionary
     (Output : in Ada.Text_IO.File_Type;
      Dictionary : in Natools.Smaz_256.Dictionary;
      Hash_Package_Name : in String := "")
   is
      procedure Put_Line (Line : in String);
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
      Hash_Package : constant String
        := Ada.Strings.Unbounded.To_String (Handler.Hash_Package);
   begin
      Natools.Smaz_Tools.Set_Dictionary_For_Trie_Search (Word_List);
      Dictionary.Hash := Natools.Smaz_Tools.Trie_Search'Access;

      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 (Word_List, Hash_Package);
      end if;

      if Handler.Sx_Dict_Output then







|







943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
      Hash_Package : constant String
        := Ada.Strings.Unbounded.To_String (Handler.Hash_Package);
   begin
      Natools.Smaz_Tools.Set_Dictionary_For_Trie_Search (Word_List);
      Dictionary.Hash := Natools.Smaz_Tools.Trie_Search'Access;

      if Ada_Dictionary'Length > 0 then
         Dict_256.Print_Dictionary (Ada_Dictionary, Dictionary, Hash_Package);
      end if;

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

      if Handler.Sx_Dict_Output then