Natools

Diff
Login

Differences From Artifact [78257fe6d3]:

To Artifact [9042103961]:


129
130
131
132
133
134
135






136
137
138
139
140
141
142

   overriding procedure Argument
     (Handler  : in out Callback;
      Argument : in String)
     is null;








   procedure Build_Perfect_Hash
     (Word_List : in Natools.Smaz.Tools.String_Lists.List;
      Package_Name : in String);
      --  Adapter between Smaz_256 generator and retired Smaz types

   procedure Convert
     (Input : in Natools.Smaz_Tools.String_Lists.List;







>
>
>
>
>
>







129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148

   overriding procedure Argument
     (Handler  : in out Callback;
      Argument : in String)
     is null;


   function Activate_Dictionary (Dict : in Natools.Smaz_256.Dictionary)
     return Natools.Smaz_256.Dictionary;
   function Activate_Dictionary (Dict : in Natools.Smaz.Dictionary)
     return Natools.Smaz.Dictionary;
      --  Update Dictionary.Hash so that it can be actually used

   procedure Build_Perfect_Hash
     (Word_List : in Natools.Smaz.Tools.String_Lists.List;
      Package_Name : in String);
      --  Adapter between Smaz_256 generator and retired Smaz types

   procedure Convert
     (Input : in Natools.Smaz_Tools.String_Lists.List;
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189



190
191
192
193
194
195
196
      --  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 Use_Dictionary (Dict : in out Natools.Smaz_256.Dictionary);
   procedure Use_Dictionary (Dict : in out Natools.Smaz.Dictionary);
      --  Update Dictionary.Hash so that it can be actually used



   generic
      type Dictionary (<>) is private;
      type Dictionary_Entry is (<>);
      type Methods is (<>);
      type Score_Value is range <>;
      type String_Count is range <>;
      type Word_Counter is private;

      type Dictionary_Counts is array (Dictionary_Entry) of String_Count;

      with package String_Lists
        is new Ada.Containers.Indefinite_Doubly_Linked_Lists (String);




      with procedure Add_Substrings
        (Counter : in out Word_Counter;
         Phrase : in String;
         Min_Size : in Positive;
         Max_Size : in Positive);








<
<
<
<














>
>
>







171
172
173
174
175
176
177




178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
      --  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







   generic
      type Dictionary (<>) is private;
      type Dictionary_Entry is (<>);
      type Methods is (<>);
      type Score_Value is range <>;
      type String_Count is range <>;
      type Word_Counter is private;

      type Dictionary_Counts is array (Dictionary_Entry) of String_Count;

      with package String_Lists
        is new Ada.Containers.Indefinite_Doubly_Linked_Lists (String);

      with function Activate_Dictionary (Dict : in Dictionary)
        return Dictionary is <>;

      with procedure Add_Substrings
        (Counter : in out Word_Counter;
         Phrase : in String;
         Min_Size : in Positive;
         Max_Size : in Positive);

274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
         Max_Pending_Count : in Ada.Containers.Count_Type);

      with function To_Dictionary
        (List : in String_Lists.List;
         Variable_Length_Verbatim : in Boolean)
        return Dictionary;

      with procedure Use_Dictionary (Dict : in out Dictionary) is <>;

      with function Worst_Element
        (Dict : in Dictionary;
         Counts : in Dictionary_Counts;
         Method : in Methods)
        return Dictionary_Entry;

   package Dictionary_Subprograms is







<
<







279
280
281
282
283
284
285


286
287
288
289
290
291
292
         Max_Pending_Count : in Ada.Containers.Count_Type);

      with function To_Dictionary
        (List : in String_Lists.List;
         Variable_Length_Verbatim : in Boolean)
        return Dictionary;



      with function Worst_Element
        (Dict : in Dictionary;
         Counts : in Dictionary_Counts;
         Method : in Methods)
        return Dictionary_Entry;

   package Dictionary_Subprograms is
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
      procedure Evaluate_Dictionary
        (Job_Count : in Natural;
         Dict : in Dictionary;
         Corpus : in String_Lists.List;
         Compressed_Size : out Ada.Streams.Stream_Element_Count;
         Counts : out Dictionary_Counts)
      is
         Actual_Dict : Dictionary := Dict;
      begin
         Use_Dictionary (Actual_Dict);

         if Job_Count > 0 then
            Parallel_Evaluate_Dictionary (Job_Count,
               Actual_Dict, Corpus, Compressed_Size, Counts);
         else
            Evaluate_Dictionary
              (Actual_Dict, Corpus, Compressed_Size, Counts);
         end if;







|

<
<







368
369
370
371
372
373
374
375
376


377
378
379
380
381
382
383
      procedure Evaluate_Dictionary
        (Job_Count : in Natural;
         Dict : in Dictionary;
         Corpus : in String_Lists.List;
         Compressed_Size : out Ada.Streams.Stream_Element_Count;
         Counts : out Dictionary_Counts)
      is
         Actual_Dict : constant Dictionary := Activate_Dictionary (Dict);
      begin


         if Job_Count > 0 then
            Parallel_Evaluate_Dictionary (Job_Count,
               Actual_Dict, Corpus, Compressed_Size, Counts);
         else
            Evaluate_Dictionary
              (Actual_Dict, Corpus, Compressed_Size, Counts);
         end if;
604
605
606
607
608
609
610

611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627

      procedure Process
        (Handler : in Callback'Class;
         Word_List : in String_Lists.List;
         Data_List : in String_Lists.List;
         Method : in Methods)
      is

         Dict : Dictionary := To_Dictionary (Handler, Word_List, Method);
         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
         Use_Dictionary (Dict);

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

         if Hash_Package'Length > 0 then
            Build_Perfect_Hash (Word_List, Hash_Package);
         end if;







>
|







<
<







605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620


621
622
623
624
625
626
627

      procedure Process
        (Handler : in Callback'Class;
         Word_List : in String_Lists.List;
         Data_List : in String_Lists.List;
         Method : in Methods)
      is
         Dict : constant Dictionary := Activate_Dictionary
           (To_Dictionary (Handler, Word_List, Method));
         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


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

         if Hash_Package'Length > 0 then
            Build_Perfect_Hash (Word_List, Hash_Package);
         end if;
1096
1097
1098
1099
1100
1101
1102





















































1103
1104
1105
1106
1107
1108
1109
            Handler.Algorithm := Algorithms.Base_256;

         when Options.Base_256_Retired =>
            Handler.Algorithm := Algorithms.Base_256_Retired;
      end case;
   end Option;























































   procedure Build_Perfect_Hash
     (Word_List : in Natools.Smaz.Tools.String_Lists.List;
      Package_Name : in String)
   is
      Other_Word_List : Natools.Smaz_Tools.String_Lists.List;
   begin







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







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
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
            Handler.Algorithm := Algorithms.Base_256;

         when Options.Base_256_Retired =>
            Handler.Algorithm := Algorithms.Base_256_Retired;
      end case;
   end Option;


   function Activate_Dictionary (Dict : in Natools.Smaz_256.Dictionary)
     return Natools.Smaz_256.Dictionary
   is
      Result : Natools.Smaz_256.Dictionary := Dict;
   begin
      Natools.Smaz_Tools.Set_Dictionary_For_Trie_Search
        (Tools_256.To_String_List (Result));
      Result.Hash := Natools.Smaz_Tools.Trie_Search'Access;

      for I in Result.Offsets'Range loop
         if Natools.Smaz_Tools.Trie_Search (Natools.Smaz_256.Dict_Entry
           (Result, I)) /= Natural (I)
         then
            Ada.Text_IO.Put_Line
              (Ada.Text_IO.Current_Error,
               "Fail at" & Ada.Streams.Stream_Element'Image (I)
               & " -> " & Natools.String_Escapes.C_Escape_Hex
                  (Natools.Smaz_256.Dict_Entry (Result, I), True)
               & " ->" & Natural'Image (Natools.Smaz_Tools.Trie_Search
                  (Natools.Smaz_256.Dict_Entry (Result, I))));
         end if;
      end loop;

      return Result;
   end Activate_Dictionary;


   function Activate_Dictionary (Dict : in Natools.Smaz.Dictionary)
     return Natools.Smaz.Dictionary
   is
      Result : Natools.Smaz.Dictionary := Dict;
   begin
      Natools.Smaz.Tools.Set_Dictionary_For_Trie_Search (Result);
      Result.Hash := Natools.Smaz.Tools.Trie_Search'Access;

      for I in Result.Offsets'Range loop
         if Natools.Smaz_Tools.Trie_Search (Natools.Smaz.Dict_Entry
           (Result, I)) /= Natural (I)
         then
            Ada.Text_IO.Put_Line
              (Ada.Text_IO.Current_Error,
               "Fail at" & Ada.Streams.Stream_Element'Image (I)
               & " -> " & Natools.String_Escapes.C_Escape_Hex
                  (Natools.Smaz.Dict_Entry (Result, I), True)
               & " ->" & Natural'Image (Natools.Smaz.Tools.Trie_Search
                  (Natools.Smaz.Dict_Entry (Result, I))));
         end if;
      end loop;

      return Result;
   end Activate_Dictionary;


   procedure Build_Perfect_Hash
     (Word_List : in Natools.Smaz.Tools.String_Lists.List;
      Package_Name : in String)
   is
      Other_Word_List : Natools.Smaz_Tools.String_Lists.List;
   begin
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
               New_Line (Output);
               Put_Line (Output, Indent & Indent
                 & "Use retired base-256 implementation");
         end case;
      end loop;
   end Print_Help;


   procedure Use_Dictionary (Dict : in out Natools.Smaz_256.Dictionary) is
   begin
      Natools.Smaz_Tools.Set_Dictionary_For_Trie_Search
        (Tools_256.To_String_List (Dict));
      Dict.Hash := Natools.Smaz_Tools.Trie_Search'Access;

      for I in Dict.Offsets'Range loop
         if Natools.Smaz_Tools.Trie_Search (Natools.Smaz_256.Dict_Entry
           (Dict, I)) /= Natural (I)
         then
            Ada.Text_IO.Put_Line
              (Ada.Text_IO.Current_Error,
               "Fail at" & Ada.Streams.Stream_Element'Image (I)
               & " -> " & Natools.String_Escapes.C_Escape_Hex
                  (Natools.Smaz_256.Dict_Entry (Dict, I), True)
               & " ->" & Natural'Image (Natools.Smaz_Tools.Trie_Search
                  (Natools.Smaz_256.Dict_Entry (Dict, I))));
         end if;
      end loop;
   end Use_Dictionary;


   procedure Use_Dictionary (Dict : in out Natools.Smaz.Dictionary) is
   begin
      Natools.Smaz.Tools.Set_Dictionary_For_Trie_Search (Dict);
      Dict.Hash := Natools.Smaz.Tools.Trie_Search'Access;

      for I in Dict.Offsets'Range loop
         if Natools.Smaz_Tools.Trie_Search (Natools.Smaz.Dict_Entry
           (Dict, I)) /= Natural (I)
         then
            Ada.Text_IO.Put_Line
              (Ada.Text_IO.Current_Error,
               "Fail at" & Ada.Streams.Stream_Element'Image (I)
               & " -> " & Natools.String_Escapes.C_Escape_Hex
                  (Natools.Smaz.Dict_Entry (Dict, I), True)
               & " ->" & Natural'Image (Natools.Smaz.Tools.Trie_Search
                  (Natools.Smaz.Dict_Entry (Dict, I))));
         end if;
      end loop;
   end Use_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







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







1419
1420
1421
1422
1423
1424
1425











































1426
1427
1428
1429
1430
1431
1432
               New_Line (Output);
               Put_Line (Output, Indent & Indent
                 & "Use retired base-256 implementation");
         end case;
      end loop;
   end Print_Help;













































   Opt_Config : constant Getopt.Configuration := Getopt_Config;
   Handler : Callback;
   Input_List, Input_Data : Natools.Smaz_Tools.String_Lists.List;
begin
   Process_Command_Line :
   begin