-
Notifications
You must be signed in to change notification settings - Fork 3
/
word_package.adb
2224 lines (1866 loc) · 103 KB
/
word_package.adb
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
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
197
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
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
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
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
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
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
896
897
898
899
900
901
902
903
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
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
with TEXT_IO;
with LATIN_FILE_NAMES; use LATIN_FILE_NAMES;
with STRINGS_PACKAGE; use STRINGS_PACKAGE;
with CONFIG; use CONFIG;
with UNIQUES_PACKAGE; use UNIQUES_PACKAGE;
with ADDONS_PACKAGE; use ADDONS_PACKAGE;
with WORD_PARAMETERS; use WORD_PARAMETERS;
with PREFACE;
with DEVELOPER_PARAMETERS; use DEVELOPER_PARAMETERS;
with LINE_STUFF; use LINE_STUFF;
with ENGLISH_SUPPORT_PACKAGE; use ENGLISH_SUPPORT_PACKAGE;
package body WORD_PACKAGE is
INFLECTIONS_SECTIONS_FILE : LEL_SECTION_IO.FILE_TYPE;
procedure PAUSE(OUTPUT : TEXT_IO.FILE_TYPE) is
use CONFIG;
PAUSE_LINE : STRING(1..300);
PAUSE_LAST : INTEGER := 0;
begin
if WORDS_MDEV(PAUSE_IN_SCREEN_OUTPUT) then
if METHOD = INTERACTIVE then
if TEXT_IO.NAME(OUTPUT) =
TEXT_IO.NAME(TEXT_IO.STANDARD_OUTPUT) then
TEXT_IO.PUT_LINE(TEXT_IO.STANDARD_OUTPUT,
" MORE - hit RETURN/ENTER to continue");
TEXT_IO.GET_LINE(TEXT_IO.STANDARD_INPUT, PAUSE_LINE, PAUSE_LAST);
end if;
elsif METHOD = COMMAND_LINE_INPUT then
TEXT_IO.PUT_LINE(TEXT_IO.STANDARD_OUTPUT,
" MORE - hit RETURN/ENTER to continue");
TEXT_IO.GET_LINE(TEXT_IO.STANDARD_INPUT, PAUSE_LINE, PAUSE_LAST);
elsif METHOD = COMMAND_LINE_FILES then
null; -- Do not PAUSE
end if;
end if;
exception
when others =>
TEXT_IO.PUT_LINE("Unexpected exception in PAUSE");
end PAUSE;
function MIN(A, B : INTEGER) return INTEGER is
begin
if A <= B then
return A; end if;
return B;
end MIN;
function LTU(C, D : CHARACTER) return BOOLEAN is
begin
if (D = 'v') then
if (C < 'u') then
return TRUE;
else
return FALSE;
end if;
elsif (D = 'j') then
if (C < 'i') then
return TRUE;
else
return FALSE;
end if;
elsif (D = 'V') then
if (C < 'U') then
return TRUE;
else
return FALSE;
end if;
elsif (D = 'J') then
if (C < 'I') then
return TRUE;
else
return FALSE;
end if;
else
return C < D;
end if;
end LTU;
function EQU(C, D : CHARACTER) return BOOLEAN is
begin
if (D = 'u') or (D = 'v') then
if (C = 'u') or (C = 'v') then
return TRUE;
else
return FALSE;
end if;
elsif (D = 'i') or (D = 'j') then
if (C = 'i') or (C = 'j') then
return TRUE;
else
return FALSE;
end if;
elsif (D = 'U') or (D = 'V') then
if (C = 'U') or (C = 'V') then
return TRUE;
else
return FALSE;
end if;
elsif (D = 'I') or (D = 'J') then
if (C = 'I') or (C = 'J') then
return TRUE;
else
return FALSE;
end if;
else
return C = D;
end if;
end EQU;
function GTU(C, D : CHARACTER) return BOOLEAN is
begin
if D = 'u' then
if (C > 'v') then
return TRUE;
else
return FALSE;
end if;
elsif D = 'i' then
if (C > 'j') then
return TRUE;
else
return FALSE;
end if;
elsif D = 'U' then
if (C > 'V') then
return TRUE;
else
return FALSE;
end if;
elsif D = 'I' then
if (C > 'J') then
return TRUE;
else
return FALSE;
end if;
else
return C > D;
end if;
end GTU;
function LTU(S, T : STRING) return BOOLEAN is
begin
for I in 1..S'LENGTH loop -- Not TRIMed, so same length
if EQU(S(S'FIRST+I-1), T(T'FIRST+I-1)) then
null;
elsif GTU(S(S'FIRST+I-1), T(T'FIRST+I-1)) then
return FALSE;
elsif LTU(S(S'FIRST+I-1), T(T'FIRST+I-1)) then
return TRUE;
end if;
end loop;
return FALSE;
end LTU;
function GTU(S, T : STRING) return BOOLEAN is
begin
for I in 1..S'LENGTH loop -- Not TRIMed, so same length
if EQU(S(S'FIRST+I-1), T(T'FIRST+I-1)) then
null;
elsif LTU(S(S'FIRST+I-1), T(T'FIRST+I-1)) then
return FALSE;
elsif GTU(S(S'FIRST+I-1), T(T'FIRST+I-1)) then
return TRUE;
end if;
end loop;
return FALSE;
end GTU;
function EQU(S, T : STRING) return BOOLEAN is
begin
if S'LENGTH /= T'LENGTH then
return FALSE;
end if;
for I in 1..S'LENGTH loop
if not EQU(S(S'FIRST+I-1), T(T'FIRST+I-1)) then
return FALSE;
end if;
end loop;
return TRUE;
end EQU;
procedure RUN_UNIQUES(S : in STRING; UNIQUE_FOUND : out BOOLEAN;
PA : in out PARSE_ARRAY; PA_LAST : in out INTEGER) is
SL : constant STRING -- BAD NAME!!!!!!!!!!!!!!!!!!
:= LOWER_CASE(TRIM(S));
ST : constant STEM_TYPE := HEAD(SL, MAX_STEM_SIZE);
UNQL : UNIQUE_LIST; -- Unique list for a letter
begin
UNIQUE_FOUND := FALSE;
if SL(SL'FIRST) = 'v' then
UNQL := UNQ('u'); -- Unique list for a letter
elsif SL(SL'FIRST) = 'j' then
UNQL := UNQ('i'); -- Unique list for a letter
else
UNQL := UNQ(SL(SL'FIRST)); -- Unique list for a letter
end if;
--TEXT_IO.NEW_LINE;
--TEXT_IO.PUT_LINE("Called UNIQUES with =>" & SL & "|");
--TEXT_IO.NEW_LINE;
--TEXT_IO.PUT_LINE("UNQL ");
while UNQL /= null loop
-- If there is a match, add to PA
--TEXT_IO.PUT_LINE("UNIQUE =>" & UNQL.PR.STEM);
--if ST = LOWER_CASE(UNQL.PR.STEM) then
if EQU(ST, LOWER_CASE(UNQL.STEM)) then
PA_LAST := PA_LAST + 1;
PA(PA_LAST) := (UNQL.STEM,
(UNQL.QUAL,
0,
NULL_ENDING_RECORD,
X,
X),
UNIQUE,
UNQL.MNPC);
--TEXT_IO.PUT_LINE("UNIQUE HIT *********" & INTEGER'IMAGE(PA_LAST));
UNIQUE_FOUND := TRUE;
end if;
UNQL := UNQL.SUCC;
end loop;
end RUN_UNIQUES;
procedure RUN_INFLECTIONS(S : in STRING; SL : in out SAL;
RESTRICTION : DICT_RESTRICTION := REGULAR) is
-- Trys all possible inflections against the input word in S
-- and constructs a STEM_LIST of those that survive SL
use LEL_SECTION_IO;
use INFLECTION_RECORD_IO;
WORD : constant STRING := LOWER_CASE(TRIM(S));
LAST_OF_WORD : constant CHARACTER := WORD(WORD'LAST);
LENGTH_OF_WORD : constant INTEGER := WORD'LENGTH;
STEM_LENGTH : INTEGER := 0;
PR : PARSE_RECORD;
M : INTEGER := 1;
begin
--TEXT_IO.NEW_LINE;
--TEXT_IO.PUT_LINE("Called RUN_INFLECTIONS with =>" & WORD & "|");
if WORD'LENGTH = 0 then
SL(M) := NULL_PARSE_RECORD;
return;
end if;
SA := NOT_A_STEM_ARRAY;
-- Add all of these to list of possible ending records
-- since the blank ending agrees with everything
-- PACK/PRON have no blank endings
if ((RESTRICTION /= PACK_ONLY) and (RESTRICTION /= QU_PRON_ONLY)) and then
(WORD'LENGTH <= MAX_STEM_SIZE) then
for I in BELF(0, ' ')..BELL(0, ' ') loop
PR := (WORD & NULL_STEM_TYPE(LENGTH_OF_WORD+1..STEM_TYPE'LENGTH),
BEL(I), DEFAULT_DICTIONARY_KIND, NULL_MNPC);
SL(M) := PR;
M := M + 1;
end loop;
SA(LENGTH_OF_WORD) := PR.STEM; -- Is always a possibility (null ending)
end if;
-- Here we read in the INFLECTIONS_SECTION that is applicable
if RESTRICTION = REGULAR then
case LAST_OF_WORD is
when 'a' | 'c' | 'd' | 'e' | 'i' =>
READ(INFLECTIONS_SECTIONS_FILE, LEL, 1);
when 'm' | 'n' | 'o' | 'r' =>
READ(INFLECTIONS_SECTIONS_FILE, LEL, 2);
when 's' =>
READ(INFLECTIONS_SECTIONS_FILE, LEL, 3);
when 't' | 'u' =>
READ(INFLECTIONS_SECTIONS_FILE, LEL, 4);
when others =>
--PUT_LINE("Only blank inflections are found");
return;
end case;
elsif RESTRICTION = PACK_ONLY or RESTRICTION = QU_PRON_ONLY then
READ(INFLECTIONS_SECTIONS_FILE, LEL, 4);
end if;
-- Now do the non-blank endings -- Only go to LENGTH_OF_WORD
for Z in reverse 1..MIN(MAX_ENDING_SIZE, LENGTH_OF_WORD) loop
-- Check if Z agrees with a PDL SIZE !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
-- Maybe make PDL on size, if it has to be a list, or order by size if array
if LELL(Z, LAST_OF_WORD) > 0 then -- Any likely inflections at all
for I in LELF(Z, LAST_OF_WORD)..LELL(Z, LAST_OF_WORD) loop
if EQU(LOWER_CASE(LEL(I).ENDING.SUF(1..Z)),
LOWER_CASE(WORD(WORD'LAST-Z+1..WORD'LAST))) then
-- Add to list of possible ending records
--STEM_LENGTH := WORD'LENGTH - LEL(I).ENDING.SIZE;
STEM_LENGTH := WORD'LENGTH - Z;
--PUT(STEM_LENGTH);
--TEXT_IO.PUT_LINE("#######################################################");
if STEM_LENGTH <= MAX_STEM_SIZE then -- Reject too long words
-- Check if LEL IR agrees with PDL IR !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
PR := (WORD(WORD'FIRST..STEM_LENGTH) &
NULL_STEM_TYPE(STEM_LENGTH+1..MAX_STEM_SIZE),
LEL(I), DEFAULT_DICTIONARY_KIND, NULL_MNPC);
SL(M) := PR;
M := M + 1;
SA(STEM_LENGTH) := PR.STEM; -- Gets set dozens of times
-- Could order the endings by length (suffix sort) so length changes slowly
--PUT_LINE("LENGTH = " & INTEGER'IMAGE(STEM_LENGTH)
--& " SA =>" & PR.STEM & "|");
end if;
end if;
end loop;
end if;
end loop;
--TEXT_IO.PUT_LINE("RUN_INF FOUND STEMS = " & INTEGER'IMAGE(M-1));
--exception
--when others =>
--TEXT_IO.PUT_LINE("exception RUN_INF FOUND STEMS = " & INTEGER'IMAGE(M-1));
--raise;
end RUN_INFLECTIONS;
procedure TRY_TO_LOAD_DICTIONARY(D_K : DICTIONARY_KIND) is
begin
-- PUT_LINE("Trying to load " & DICTIONARY_KIND'IMAGE(D_K) &
-- " dictionary from STEMFILE ");
STEM_IO.OPEN(STEM_FILE(D_K), STEM_IO.IN_FILE,
ADD_FILE_NAME_EXTENSION(STEM_FILE_NAME,
DICTIONARY_KIND'IMAGE(D_K)));
DICT_IO.OPEN(DICT_FILE(D_K), DICT_IO.IN_FILE,
ADD_FILE_NAME_EXTENSION(DICT_FILE_NAME,
DICTIONARY_KIND'IMAGE(D_K)));
LOAD_INDICES_FROM_INDX_FILE(ADD_FILE_NAME_EXTENSION(INDX_FILE_NAME,
DICTIONARY_KIND'IMAGE(D_K)), D_K);
DICTIONARY_AVAILABLE(D_K) := TRUE;
-- PUT_LINE("Successfully loaded " & DICTIONARY_KIND'IMAGE(D_K) &
-- " dictionary from STEMFILE ");
exception
when others =>
--PUT_LINE("Failed to load " & DICTIONARY_KIND'IMAGE(D_K) &
-- " dictionary from STEMFILE ");
DICTIONARY_AVAILABLE(D_K) := FALSE;
end TRY_TO_LOAD_DICTIONARY;
procedure DICTIONARY_SEARCH(SSA : STEM_ARRAY_TYPE;
PREFIX : PREFIX_ITEM;
SUFFIX : SUFFIX_ITEM;
D_K : DICTIONARY_KIND;
RESTRICTION : DICT_RESTRICTION := REGULAR) is
-- Prepares a PDL list of possible dictionary hits
-- Search a dictionary (D_K) looking for all stems that match
-- any of the stems that are physically possible with Latin inflections
use STEM_IO;
--type NAT_32 is range 0..2**31-1; --###############
J, J1, J2, JJ : STEM_IO.COUNT := 0;
INDEX_ON : constant STRING := SSA(SSA'LAST);
INDEX_FIRST, INDEX_LAST : STEM_IO.COUNT := 0;
DS : DICTIONARY_STEM;
FIRST_TRY, SECOND_TRY : BOOLEAN := TRUE;
function FIRST_TWO(W : STRING) return STRING is
-- 'v' could be represented by 'u', like the new Oxford Latin Dictionary
-- Fixes the first two letters of a word/stem which can be done right
S : constant STRING := LOWER_CASE(W);
SS : STRING(W'RANGE) := W;
function UI(C : CHARACTER) return CHARACTER is
begin
if (C = 'v') then
return 'u';
elsif (C = 'V') then
return 'U';
elsif (C = 'j') then
return 'i';
elsif (C = 'J') then
return 'I';
else
return C;
end if;
end UI;
begin
if S'LENGTH = 1 then
SS(S'FIRST) := UI(W(S'FIRST));
else
SS(S'FIRST) := UI(W(S'FIRST));
SS(S'FIRST+1) := UI(W(S'FIRST+1));
end if;
return SS;
end FIRST_TWO;
procedure LOAD_PDL is
begin
case RESTRICTION is
when REGULAR =>
if not (DS.PART.POFS = PACK or
(DS.PART.POFS = PRON and then
(DS.PART.PRON.DECL.WHICH = 1))) then
PDL_INDEX := PDL_INDEX + 1;
PDL(PDL_INDEX) := PRUNED_DICTIONARY_ITEM'(DS, D_K);
end if;
when PACK_ONLY =>
if DS.PART.POFS = PACK then
PDL_INDEX := PDL_INDEX + 1;
PDL(PDL_INDEX) := PRUNED_DICTIONARY_ITEM'(DS, D_K);
end if;
when QU_PRON_ONLY =>
if DS.PART.POFS = PRON and then
(DS.PART.PRON.DECL.WHICH = 1) then
PDL_INDEX := PDL_INDEX + 1;
PDL(PDL_INDEX) := PRUNED_DICTIONARY_ITEM'(DS, D_K);
end if;
when others =>
PDL_INDEX := PDL_INDEX + 1;
PDL(PDL_INDEX) := PRUNED_DICTIONARY_ITEM'(DS, D_K);
end case;
end LOAD_PDL;
begin
-- Now go through the dictionary list DL for the first letters
-- and make a reduced dictionary list PDL
--TEXT_IO.PUT_LINE("Entering DICTIONARY_SEARCH PDL_INDEX = " & INTEGER'IMAGE(PDL_INDEX));
if D_K = LOCAL then
INDEX_FIRST := FIRST_INDEX((FIRST_TWO(INDEX_ON)(1), 'a'), D_K);
INDEX_LAST := LAST_INDEX((FIRST_TWO(INDEX_ON)(1), 'a'), D_K);
else
INDEX_FIRST := FIRST_INDEX(FIRST_TWO(INDEX_ON), D_K);
INDEX_LAST := LAST_INDEX(FIRST_TWO(INDEX_ON), D_K);
end if;
if INDEX_FIRST > 0 and then INDEX_FIRST <= INDEX_LAST then
J1 := STEM_IO.COUNT(INDEX_FIRST); --######################
J2 := STEM_IO.COUNT(INDEX_LAST);
STEM_ARRAY_LOOP:
for K in SSA'RANGE loop
if TRIM(SSA(K))'LENGTH > 1 then
-- This may be checking for 0 and 1 letter SSAs which are done elsewhere
--TEXT_IO.PUT(INTEGER'IMAGE(K) & " SSA(K) =>" );
--TEXT_IO.PUT_LINE(SSA(K));
if D_K = LOCAL then -- Special processing for unordered DICT.LOC
for J in J1..J2 loop -- Sweep exaustively through the scope
SET_INDEX(STEM_FILE(D_K), STEM_IO.COUNT(J));
READ(STEM_FILE(D_K), DS);
if EQU(LOWER_CASE(DS.STEM), SSA(K)) then
--TEXT_IO.PUT_LINE("HIT LOC = " & DS.STEM & " - " & SSA(K));
LOAD_PDL;
end if;
end loop;
else -- Regular dictionaries
FIRST_TRY := TRUE;
SECOND_TRY := TRUE;
J := (J1 + J2) / 2;
BINARY_SEARCH:
loop
if (J1 = J2-1) or (J1 = J2) then
if FIRST_TRY then
--TEXT_IO.PUT_LINE("FIRST_TRY");
J := J1;
FIRST_TRY := FALSE;
elsif SECOND_TRY then
--TEXT_IO.PUT_LINE("SECOND_TRY");
J := J2;
SECOND_TRY := FALSE;
else
--TEXT_IO.PUT_LINE("THIRD_TRY exit BINARY_SEARCH");
JJ := J;
exit BINARY_SEARCH;
end if;
end if;
SET_INDEX(STEM_FILE(D_K), STEM_IO.COUNT(J));
READ(STEM_FILE(D_K), DS);
if LTU(LOWER_CASE(DS.STEM), SSA(K)) then
J1 := J;
J := (J1 + J2) / 2;
elsif GTU(LOWER_CASE(DS.STEM), SSA(K)) then
J2 := J;
J := (J1 + J2) / 2;
else
for I in reverse J1..J loop
SET_INDEX(STEM_FILE(D_K), STEM_IO.COUNT(I));
READ(STEM_FILE(D_K), DS);
if EQU(LOWER_CASE(DS.STEM), SSA(K)) then
JJ := I;
--TEXT_IO.PUT_LINE("PDL STEM " & DS.STEM & " " & INTEGER'IMAGE(INTEGER(DS.MNPC)));
LOAD_PDL;
else
exit;
end if;
end loop;
for I in J+1..J2 loop
SET_INDEX(STEM_FILE(D_K), STEM_IO.COUNT(I));
READ(STEM_FILE(D_K), DS);
if EQU(LOWER_CASE(DS.STEM), SSA(K)) then
JJ := I;
--TEXT_IO.PUT_LINE("PDL STEM " & DS.STEM & " " & INTEGER'IMAGE(INTEGER(DS.MNPC)));
LOAD_PDL;
else
exit BINARY_SEARCH;
end if;
end loop;
exit BINARY_SEARCH;
end if;
end loop BINARY_SEARCH;
J1 := JJ;
J2 := STEM_IO.COUNT(INDEX_LAST);
end if; -- On LOCAL check
end if; -- On LENGTH > 1
end loop STEM_ARRAY_LOOP;
end if;
--TEXT_IO.PUT_LINE("Leaving DICTIONARY_SEARCH PDL_INDEX = " & INTEGER'IMAGE(PDL_INDEX));
-- exception
-- when others =>
--TEXT_IO.PUT_LINE("exception DICTIONARY_SEARCH PDL_INDEX = " & INTEGER'IMAGE(PDL_INDEX));
-- raise;
end DICTIONARY_SEARCH;
procedure SEARCH_DICTIONARIES(SSA : in STEM_ARRAY_TYPE;
PREFIX : PREFIX_ITEM; SUFFIX : SUFFIX_ITEM;
RESTRICTION : DICT_RESTRICTION := REGULAR) is
use STEM_IO;
FC : CHARACTER := ' ';
begin
--PUT_LINE("Entering SEARCH_DICTIONARIES");
PDL := (others => NULL_PRUNED_DICTIONARY_ITEM);
PDL_INDEX := 0;
--PUT_LINE("Search for blank stems");
-- BDL is always used, so it is loaded initially and not called from disk
-- Check all stems of the dictionary entry against the reduced stems
-- Determine if there is a pure blank " " stem
if LEN(SSA(SSA'FIRST)) = 0 then -- a size would help?
--PUT("HIT on blank stem I = ");PUT('1');
--PUT(" STEM = ");PUT_LINE(BDL(1).STEM);
--PDL := new PRUNED_DICTIONARY_ITEM'(BDL(1), GENERAL, PDL);
PDL_INDEX := PDL_INDEX + 1;
PDL(PDL_INDEX) := PRUNED_DICTIONARY_ITEM'(BDL(1), GENERAL);
end if;
-- Now there is only one blank stem (2 of to_be), but need not always be so
-- Determine if there is a blank stem (SC = ' ')
-- Prepare for the posibility that one stem is short but there are others
FC := ' ';
if SSA(SSA'FIRST)(1) = ' ' then
if SSA'LENGTH > 1 and then SSA(SSA'FIRST+1)(2) = ' ' then
FC := SSA(SSA'FIRST+1)(1);
end if;
elsif SSA(SSA'FIRST)(2) = ' ' then
FC := SSA(SSA'FIRST)(1);
end if;
-- If there is a single letter stem (FC /= ' ') then
if FC /= ' ' then
for I in 2..BDL_LAST loop
-- Check all stems of the dictionary entry against the reduced stems
--if LOWER_CASE(BDL(I).STEM(1)) = FC then
if EQU(LOWER_CASE(BDL(I).STEM(1)), FC) then
--PUT("HIT on 1 letter stem I = ");PUT(I);PUT(" STEM = ");PUT_LINE(BDL(I).STEM);
PDL_INDEX := PDL_INDEX + 1;
PDL(PDL_INDEX) := PRUNED_DICTIONARY_ITEM'(BDL(I), GENERAL);
-- D_K set to GENERAL, but should not SPE have a chance? !!!!!!!!!
end if;
end loop;
end if;
if SSA'LENGTH = 0 then
-- PUT_LINE("Empty stem array, don't bother searching");
return;
-- elsif LEN(SSA(SSA'LAST)) <= 1 then
-- PUT_LINE("No two letter stems, have done searching");
-- else
-- PUT_LINE("Searching Dictionaries");
end if;
for D_K in DICTIONARY_KIND loop
if DICTIONARY_AVAILABLE(D_K) then
if not IS_OPEN(STEM_FILE(D_K)) then
OPEN(STEM_FILE(D_K), STEM_IO.IN_FILE,
ADD_FILE_NAME_EXTENSION(STEM_FILE_NAME,
DICTIONARY_KIND'IMAGE(D_K)));
end if;
DICTIONARY_SEARCH(SSA, PREFIX, SUFFIX, D_K, RESTRICTION);
CLOSE(STEM_FILE(D_K)); --??????
end if;
end loop;
--TEXT_IO.PUT_LINE("Leaving SEARCH_DICTIONARY PDL_INDEX = " & INTEGER'IMAGE(PDL_INDEX));
end SEARCH_DICTIONARIES;
procedure CHANGE_LANGUAGE(C : CHARACTER) is
begin if UPPER_CASE(C) = 'L' then
LANGUAGE := LATIN_TO_ENGLISH;
PREFACE.PUT_LINE("Language changed to " & LANGUAGE_TYPE'IMAGE(LANGUAGE));
elsif UPPER_CASE(C) = 'E' then
if ENGLISH_DICTIONARY_AVAILABLE(GENERAL) then
LANGUAGE:= ENGLISH_TO_LATIN;
PREFACE.PUT_LINE("Language changed to " & LANGUAGE_TYPE'IMAGE(LANGUAGE));
PREFACE.PUT_LINE("Input a single English word (+ part of speech - N, ADJ, V, PREP, ...)");
else
PREFACE.PUT_LINE("No English dictionary available");
end if;
else
PREFACE.PUT_LINE("Bad LANGAUGE input - no change, remains " & LANGUAGE_TYPE'IMAGE(LANGUAGE));
end if;
exception
when others =>
PREFACE.PUT_LINE("Bad LANGAUGE input - no change, remains " & LANGUAGE_TYPE'IMAGE(LANGUAGE));
end CHANGE_LANGUAGE;
procedure WORD(RAW_WORD : in STRING;
PA : in out PARSE_ARRAY; PA_LAST : in out INTEGER) is
INPUT_WORD : constant STRING := LOWER_CASE(RAW_WORD);
PA_SAVE : INTEGER := PA_LAST;
UNIQUE_FOUND : BOOLEAN := FALSE;
SS, SSS : SAL := (others => NULL_PARSE_RECORD);
procedure ORDER_STEMS(SX : in out SAL) is
use INFLECTION_RECORD_IO;
use DICT_IO;
HITS : INTEGER := 0;
SL : SAL := SX;
SL_LAST : INTEGER := 0;
SM : PARSE_RECORD;
begin
if SX(1) = NULL_PARSE_RECORD then
return; end if;
--PUT_LINE("ORDERing_STEMS");
for I in SL'RANGE loop
exit when SL(I) = NULL_PARSE_RECORD;
SL_LAST := SL_LAST + 1;
end loop;
--PUT_LINE("In ORDER SL_LAST = " & INTEGER'IMAGE(SL_LAST));
-- Bubble sort since this list should usually be very small (1-5)
HIT_LOOP:
loop
HITS := 0;
SWITCH:
begin
-- Need to remove duplicates in ARRAY_STEMS
-- This sort is very sloppy
-- One problem is that it can mix up some of the order of PREFIX, XXX, LOC
-- I ought to do this for every set of results from different approaches
-- not just in one fell swoop at the end !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
INNER_LOOP:
for I in 1..SL_LAST-1 loop
if SL(I+1) /= NULL_PARSE_RECORD then
if (SL(I+1).MNPC < SL(I).MNPC) or else
(SL(I+1).MNPC = SL(I).MNPC and then
SL(I+1).IR.ENDING.SIZE < SL(I).IR.ENDING.SIZE) or else
(SL(I+1).MNPC = SL(I).MNPC and then
SL(I+1).IR.ENDING.SIZE = SL(I).IR.ENDING.SIZE and then
SL(I+1).IR.QUAL < SL(I).IR.QUAL) or else
(SL(I+1).MNPC = SL(I).MNPC and then
SL(I+1).IR.ENDING.SIZE = SL(I).IR.ENDING.SIZE and then
SL(I+1).IR.QUAL = SL(I).IR.QUAL and then
SL(I+1).D_K < SL(I).D_K) then
--PUT(SL(I+1).IR.QUAL); PUT(" < "); PUT(SL(I).IR.QUAL); NEW_LINE;
SM := SL(I);
SL(I) := SL(I+1); SL(I+1) := SM;
SL(I+1) := SM;
HITS := HITS + 1;
--else
--PUT(SL(I+1).IR.QUAL); PUT(" >= "); PUT(SL(I).IR.QUAL); NEW_LINE;
end if;
else
exit INNER_LOOP;
end if;
end loop INNER_LOOP;
end SWITCH;
--NEW_LINE;
--PUT_LINE("In ORDER HITS = " & INTEGER'IMAGE(HITS ));
--NEW_LINE;
--for I in 1..SL_LAST loop
--PUT(SL(I)); NEW_LINE;
--end loop;
--PUT_LINE("--------------------------------------------------------");
exit when HITS = 0;
end loop HIT_LOOP;
SX := SL;
end ORDER_STEMS;
procedure ARRAY_STEMS(SX : in SAL;
PA : in out PARSE_ARRAY; PA_LAST : in out INTEGER) is
SL : SAL := SX;
OPR : PARSE_RECORD := NULL_PARSE_RECORD;
begin
if SL(1) = NULL_PARSE_RECORD then
return;
else
OPR := NULL_PARSE_RECORD;
for I in SL'RANGE loop
if SL(I) /= NULL_PARSE_RECORD then
--PUT('*'); PUT(SL(I)); NEW_LINE;
SUPRESS_KEY_CHECK:
declare
function "<=" (A, B : PARSE_RECORD) return BOOLEAN is
use DICT_IO;
begin -- !!!!!!!!!!!!!!!!!!!!!!!!!!
if A.IR.QUAL = B.IR.QUAL and then
A.MNPC = B.MNPC then
return TRUE;
else
return FALSE;
end if;
end "<=";
begin
if SL(I) <= OPR then -- Get rid of duplicates, if ORDER is OK
--PUT('-'); PUT(SL(I)); NEW_LINE;
null;
else
PA_LAST := PA_LAST + 1;
--PUT('+'); PUT(SL(I)); NEW_LINE;
--PUT("SAL PR /= OPR and PA_LAST incremented to "); PUT(PA_LAST); NEW_LINE;
PA(PA_LAST) := SL(I);
OPR := SL(I);
end if;
end SUPRESS_KEY_CHECK;
else
exit;
end if;
end loop;
end if;
--TEXT_IO.PUT_LINE("At the end of ARRAY_STEMS");
--for I in 1..PA_LAST loop
--PUT(PA(I).STEM); PUT(" "); PUT(PA(I).IR); NEW_LINE;
--PUT(PA(I).D_K); PUT("> "); PUT(PA(I).AAMNPC.MNPC); NEW_LINE;
--end loop;
end ARRAY_STEMS;
procedure REDUCE_STEM_LIST(SL : in SAL; SXX : in out SAL;
-- Need in out if want to print it at the end
--procedure REDUCE_STEM_LIST(SL : in SAL; SXX : out SAL;
PREFIX : in PREFIX_ITEM := NULL_PREFIX_ITEM;
SUFFIX : in SUFFIX_ITEM := NULL_SUFFIX_ITEM) is
MNPC_PART : MNPC_TYPE := NULL_MNPC;
PDL_PART : PART_ENTRY;
COM : COMPARISON_TYPE := X;
NUM_SORT : NUMERAL_SORT_TYPE := X;
LS : INTEGER := 0;
M : INTEGER := 0;
PDL_KEY : STEM_KEY_TYPE;
PDL_P : PART_OF_SPEECH_TYPE;
SL_KEY : STEM_KEY_TYPE;
SL_P : PART_OF_SPEECH_TYPE;
function "<=" (LEFT, RIGHT : PART_OF_SPEECH_TYPE) return BOOLEAN is
begin
if RIGHT = LEFT or else
(LEFT = PACK and RIGHT = PRON) or else
RIGHT = X then
return TRUE;
else
return FALSE;
end if;
end "<=";
function "<=" (LEFT, RIGHT : GENDER_TYPE) return BOOLEAN is
begin
if (RIGHT = LEFT or else
(RIGHT = C and LEFT /= N) or else
(RIGHT = X)) then
return TRUE;
else
return FALSE;
end if;
end "<=";
function "<=" (LEFT, RIGHT : STEM_KEY_TYPE) return BOOLEAN is
begin
if (RIGHT = LEFT or else
(RIGHT = 0)) then
return TRUE;
else
return FALSE;
end if;
end "<=";
begin
SXX := (others => NULL_PARSE_RECORD); -- Essentially initializing
--for J in 1..PDL_INDEX loop
--NUMBER_IN_PDL := NUMBER_IN_PDL + 1;
--TEXT_IO.PUT(INTEGER'IMAGE(NUMBER_IN_PDL));
--TEXT_IO.PUT(" PDL "); TEXT_IO.PUT(PDL(J).DS.STEM);
--PART_ENTRY_IO.PUT(PDL(J).DS.PART);
--TEXT_IO.PUT(INTEGER'IMAGE(PDL(J).DS.KEY)); TEXT_IO.NEW_LINE;
--end loop;
--TEXT_IO.PUT_LINE("****************************");
--if WORDS_MODE(WRITE_STATISTICS_FILE) then
--declare
-- PSTAT : PRUNED_DICTIONARY_LIST := PDL;
--begin
-- TEXT_IO.PUT(STATS, "Number of PDL DICT hits");
-- TEXT_IO.SET_COL(STATS, 30);
-- INTEGER_IO.PUT(STATS, NUMBER_IN_PDL);
-- TEXT_IO.SET_COL(STATS, 40);
-- TEXT_IO.PUT(STATS, INPUT_WORD);
-- TEXT_IO.NEW_LINE(STATS);
--end;
--end if;
-------------------------------------------------------------
-- For the reduced dictionary list PDL
M := 0;
ON_PDL:
for J in 1..PDL_INDEX loop
PDL_PART := PDL(J).DS.PART;
PDL_KEY := PDL(J).DS.KEY;
MNPC_PART := PDL(J).DS.MNPC;
-- Is there any point in going through the process for this PDL
PDL_P := PDL(J).DS.PART.POFS; -- Used only for FIX logic below
-- If there is no SUFFIX then carry on
if (SUFFIX = NULL_SUFFIX_ITEM) then -- No suffix working, fall through
--PUT_LINE("No SUFFIX in REDUCE - Fall through to PREFIX check ");
null;
elsif
(PDL_P = N and then PDL_PART.N.DECL = (9, 8)) or -- No suffix for
(PDL_P = ADJ and then PDL_PART.ADJ.DECL = (9, 8)) then -- abbreviations
-- Can be no suffix on abbreviation");
goto END_OF_PDL_LOOP;
else -- There is SUFFIX, see if it agrees with PDL
if PDL_P <= SUFFIX.ENTR.ROOT and then -- Does SUFFIX agree in ROOT
((PDL_KEY <= SUFFIX.ENTR.ROOT_KEY) or else
((PDL_KEY = 0) and then
((PDL_P = N) or (PDL_P = ADJ) or (PDL_P = V)) and then
((SUFFIX.ENTR.ROOT_KEY = 1) or (SUFFIX.ENTR.ROOT_KEY = 2)))) then
--PUT_LINE("HIT HIT HIT HIT HIT HIT HIT HIT HIT SUFFIX SUFFIX in REDUCE");
case SUFFIX.ENTR.TARGET.POFS is -- Transform PDL_PART to TARGET
when N =>
PDL_PART := (N, SUFFIX.ENTR.TARGET.N);
when PRON =>
PDL_PART := (PRON, SUFFIX.ENTR.TARGET.PRON);
when ADJ =>
PDL_PART := (ADJ, SUFFIX.ENTR.TARGET.ADJ);
when NUM =>
PDL_PART := (NUM, SUFFIX.ENTR.TARGET.NUM);
when ADV =>
PDL_PART := (ADV, SUFFIX.ENTR.TARGET.ADV);
when V =>
PDL_PART := (V, SUFFIX.ENTR.TARGET.V);
when others =>
null; -- No others so far, except X = all
end case;
PDL_KEY := SUFFIX.ENTR.TARGET_KEY;
PDL_P := PDL_PART.POFS; -- Used only for FIX logic below
--PUT(" Changed to "); PUT(PDL_PART); PUT(PDL_KEY); NEW_LINE;
else
--PUT_LINE("In REDUCE_STEM_LIST There is no legal suffix");
-- exit;
goto END_OF_PDL_LOOP;
end if;
end if;
if (PREFIX = NULL_PREFIX_ITEM) then -- No PREFIX, drop through
--PUT_LINE("No PREFIX in REDUCE - Fall through to MATCHing ");
null;
elsif
(PDL_P = N and then PDL_PART.N.DECL = (9, 8)) or -- No prefix for
(PDL_P = ADJ and then PDL_PART.ADJ.DECL = (9, 8)) or -- abbreviations
(PDL_P = INTERJ or PDL_P = CONJ) then -- or INTERJ or CONJ
--PUT_LINE("In REDUCE_STEM_LIST no prefix on abbreviationi, interj, conj");
goto END_OF_PDL_LOOP;
else -- Check if PREFIX agrees
--PUT("PREFIX in REDUCE ");
--PUT(PDL_P); PUT(" <= "); PUT(PREFIX.ENTR.ROOT); PUT(" OR"); NEW_LINE;
--PUT(" "); PUT(PDL_PART); PUT(" <= ");
--PUT(PREFIX.ENTR.ROOT); NEW_LINE;
if (PDL_P = PREFIX.ENTR.ROOT) or -- = ROOT
(PDL_PART.POFS = PREFIX.ENTR.ROOT) then -- or part mod by suf
--PUT_LINE("PREFIX in REDUCE PART HIT");
null;
elsif (PREFIX.ENTR.ROOT = X) then -- or ROOT = X
if PDL_P = N or PDL_P = PRON or
PDL_P = ADJ or PDL_P = ADV or PDL_P = V then
-- Dont prefix PREP, CONJ, ...
-- PUT_LINE("PREFIX in REDUCE X HIT");
null;
end if;
else
goto END_OF_PDL_LOOP;
--PUT_LINE("In REDUCE_STEM_LIST There is no legal prefix");
-- exit;
end if;
end if;
-- SUFFIX and PREFIX either agree or don't exist (agrees with everything)
--PUT("ON_PDL:+ "); PUT(PDL(J).DS.STEM); PUT(PDL(J).DS.PART);
--PUT(PDL(J).DS.KEY); NEW_LINE;
--PUT_LINE(ADD_PREFIX(PDL(J).DS.STEM, PREFIX) & "|");
--PUT_LINE(ADD_SUFFIX(ADD_PREFIX(PDL(J).DS.STEM, PREFIX), SUFFIX) & "|");
LS := LEN(ADD_SUFFIX(ADD_PREFIX(PDL(J).DS.STEM, PREFIX), SUFFIX));
--PUT("LS = LEN of "); PUT(ADD_SUFFIX(ADD_PREFIX(PDL(J).DS.STEM, PREFIX), SUFFIX
--PUT(" = "); PUT(LS); NEW_LINE;
--TEXT_IO.PUT_LINE("Entering ON_SL loop");
ON_SL:
for I in SL'RANGE loop
exit when SL(I) = NULL_PARSE_RECORD;
--TEXT_IO.PUT("SL(I) "); PARSE_RECORD_IO.PUT(SL(I)); TEXT_IO.NEW_LINE;
--TEXT_IO.PUT(" PDL "); TEXT_IO.PUT(PDL(J).DS.STEM);
--PART_ENTRY_IO.PUT(PDL(J).DS.PART);
--TEXT_IO.PUT(INTEGER'IMAGE(PDL(J).DS.KEY)); TEXT_IO.NEW_LINE;
--TEXT_IO.PUT("LS "); TEXT_IO.PUT(INTEGER'IMAGE(LS));
--TEXT_IO.PUT(" LEN SL(I).STEM "); TEXT_IO.PUT_LINE(INTEGER'IMAGE(LEN(SL(I).STEM)));