Natools

Check-in [ebefb3c832]
Login

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Overview
Comment:smaz-tools: add dictionary-independent scoring functions
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: ebefb3c8324f6ce55268cd09d4d32154a81e4ba2
User & Date: nat 2016-11-18 22:43:41
Context
2016-11-19
21:35
smaz-tools: refactor scoring in To_Scored_Word check-in: 25e91595e4 user: nat tags: trunk
2016-11-18
22:43
smaz-tools: add dictionary-independent scoring functions check-in: ebefb3c832 user: nat tags: trunk
2016-11-17
21:23
smaz_tests: new tests suite for instantiated Smaz packages check-in: 769ae2dc25 user: nat tags: trunk
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to src/natools-smaz-tools.ads.

198
199
200
201
202
203
204




























205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
      Counts : in Dictionary_Counts;
      Method : in Methods.Enum)
     return Ada.Streams.Stream_Element;
      --  Return the element with worst score


   type Score_Value is range 0 .. 2 ** 31 - 1;





























   function Length
     (Dict : in Dictionary;
      E : in Ada.Streams.Stream_Element)
     return Score_Value
     is (Natools.Smaz.Dict_Entry (Dict, E)'Length);
      --  Length of a dictionary entry

   function Score_Encoded
     (Dict : in Dictionary;
      Counts : in Natools.Smaz.Tools.Dictionary_Counts;
      E : Ada.Streams.Stream_Element)
     return Score_Value
     is (Score_Value (Counts (E)) * Length (Dict, E));
      --  Score value using the amount of encoded data using E

   function Score_Frequency
     (Dict : in Dictionary;
      Counts : in Natools.Smaz.Tools.Dictionary_Counts;
      E : Ada.Streams.Stream_Element)
     return Score_Value
     is (Score_Value (Counts (E)));
      --  Score value using the number of times E was used

   function Score_Gain
     (Dict : in Dictionary;
      Counts : in Natools.Smaz.Tools.Dictionary_Counts;
      E : Ada.Streams.Stream_Element)
     return Score_Value
     is (Score_Value (Counts (E)) * (Length (Dict, E) - 1));
      --  Score value using the number of bytes saved using E

   function Score
     (Dict : in Dictionary;
      Counts : in Natools.Smaz.Tools.Dictionary_Counts;
      E : in Ada.Streams.Stream_Element;
      Method : in Methods.Enum)
     return Score_Value
     is (case Method is
         when Methods.Encoded => Score_Encoded (Dict, Counts, E),
         when Methods.Frequency => Score_Frequency (Dict, Counts, E),
         when Methods.Gain => Score_Gain (Dict, Counts, E));
      --  Scare value with dynamically chosen method

private

   package Word_Maps is new Ada.Containers.Indefinite_Ordered_Maps
     (String, String_Count);








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




|








|







|







|








|
<
<
<







198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271



272
273
274
275
276
277
278
      Counts : in Dictionary_Counts;
      Method : in Methods.Enum)
     return Ada.Streams.Stream_Element;
      --  Return the element with worst score


   type Score_Value is range 0 .. 2 ** 31 - 1;

   function Score_Encoded
     (Count : in String_Count; Length : in Positive) return Score_Value
     is (Score_Value (Count) * Score_Value (Length));
      --  Score value using the amount of encoded data by the element

   function Score_Frequency
     (Count : in String_Count; Length : in Positive) return Score_Value
     is (Score_Value (Count));
      --  Score value using the number of times the element was used

   function Score_Gain
     (Count : in String_Count; Length : in Positive) return Score_Value
     is (Score_Value (Count) * (Score_Value (Length) - 1));
      --  Score value using the number of bytes saved using the element

   function Score
     (Count : in String_Count;
      Length : in Positive;
      Method : in Methods.Enum)
     return Score_Value
     is (case Method is
         when Methods.Encoded => Score_Encoded (Count, Length),
         when Methods.Frequency => Score_Frequency (Count, Length),
         when Methods.Gain => Score_Gain (Count, Length));
      --  Scare value with dynamically chosen method



   function Length
     (Dict : in Dictionary;
      E : in Ada.Streams.Stream_Element)
     return Positive
     is (Natools.Smaz.Dict_Entry (Dict, E)'Length);
      --  Length of a dictionary entry

   function Score_Encoded
     (Dict : in Dictionary;
      Counts : in Natools.Smaz.Tools.Dictionary_Counts;
      E : Ada.Streams.Stream_Element)
     return Score_Value
     is (Score_Encoded (Counts (E), Length (Dict, E)));
      --  Score value using the amount of encoded data using E

   function Score_Frequency
     (Dict : in Dictionary;
      Counts : in Natools.Smaz.Tools.Dictionary_Counts;
      E : Ada.Streams.Stream_Element)
     return Score_Value
     is (Score_Frequency (Counts (E), Length (Dict, E)));
      --  Score value using the number of times E was used

   function Score_Gain
     (Dict : in Dictionary;
      Counts : in Natools.Smaz.Tools.Dictionary_Counts;
      E : Ada.Streams.Stream_Element)
     return Score_Value
     is (Score_Gain (Counts (E), Length (Dict, E)));
      --  Score value using the number of bytes saved using E

   function Score
     (Dict : in Dictionary;
      Counts : in Natools.Smaz.Tools.Dictionary_Counts;
      E : in Ada.Streams.Stream_Element;
      Method : in Methods.Enum)
     return Score_Value
     is (Score (Counts (E), Length (Dict, E), Method));



      --  Scare value with dynamically chosen method

private

   package Word_Maps is new Ada.Containers.Indefinite_Ordered_Maps
     (String, String_Count);