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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
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
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
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
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
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
|
-- VHDL lexical scanner.
-- Copyright (C) 2002 - 2014 Tristan Gingold
--
-- GHDL is free software; you can redistribute it and/or modify it under
-- the terms of the GNU General Public License as published by the Free
-- Software Foundation; either version 2, or (at your option) any later
-- version.
--
-- GHDL is distributed in the hope that it will be useful, but WITHOUT ANY
-- WARRANTY; without even the implied warranty of MERCHANTABILITY or
-- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
-- for more details.
--
-- You should have received a copy of the GNU General Public License
-- along with GHDL; see the file COPYING. If not, write to the Free
-- Software Foundation, 59 Temple Place - Suite 330, Boston, MA
-- 02111-1307, USA.
with Ada.Characters.Latin_1; use Ada.Characters.Latin_1;
with Ada.Characters.Handling;
with Errorout; use Errorout;
with Name_Table;
with Files_Map; use Files_Map;
with Std_Names;
with Str_Table;
with Flags; use Flags;
package body Scanner is
-- This classification is a simplification of the categories of LRM93 13.1
-- LRM93 13.1
-- The only characters allowed in the text of a VHDL description are the
-- graphic characters and format effector.
type Character_Kind_Type is
(
-- Neither a format effector nor a graphic character.
Invalid,
Format_Effector,
Upper_Case_Letter,
Digit,
Special_Character,
Space_Character,
Lower_Case_Letter,
Other_Special_Character);
-- LRM93 13.1
-- BASIC_GRAPHIC_CHARACTER ::=
-- UPPER_CASE_LETTER | DIGIT | SPECIAL_CHARACTER | SPACE_CHARACTER
--subtype Basic_Graphic_Character is
-- Character_Kind_Type range Upper_Case_Letter .. Space_Character;
-- LRM93 13.1
-- GRAPHIC_CHARACTER ::=
-- BASIC_GRAPHIC_CHARACTER | LOWER_CASE_LETTER | OTHER_SPECIAL_CHARACTER
-- Note: There is 191 graphic character.
subtype Graphic_Character is
Character_Kind_Type range Upper_Case_Letter .. Other_Special_Character;
-- LRM93 13.1
-- The characters included in each of the categories of basic graphic
-- characters are defined as follows:
type Character_Array is array (Character) of Character_Kind_Type;
Characters_Kind : constant Character_Array :=
(NUL .. BS => Invalid,
-- Format effectors are the ISO (and ASCII) characters called horizontal
-- tabulation, vertical tabulation, carriage return, line feed, and form
-- feed.
HT | LF | VT | FF | CR => Format_Effector,
SO .. US => Invalid,
-- 1. upper case letters
'A' .. 'Z' | UC_A_Grave .. UC_O_Diaeresis |
UC_O_Oblique_Stroke .. UC_Icelandic_Thorn => Upper_Case_Letter,
-- 2. digits
'0' .. '9' => Digit,
-- 3. special characters
Quotation | '#' | '&' | ''' | '(' | ')' | '+' | ',' | '-' | '.' | '/'
| ':' | ';' | '<' | '=' | '>' | '[' | ']'
| '_' | '|' | '*' => Special_Character,
-- 4. the space characters
' ' | No_Break_Space => Space_Character,
-- 5. lower case letters
'a' .. 'z' | LC_German_Sharp_S .. LC_O_Diaeresis |
LC_O_Oblique_Stroke .. LC_Y_Diaeresis => Lower_Case_Letter,
-- 6. other special characters
'!' | '$' | '%' | '@' | '?' | '\' | '^' | '`' | '{' | '}' | '~'
| Inverted_Exclamation .. Inverted_Question | Multiplication_Sign |
Division_Sign => Other_Special_Character,
-- '¡' -- INVERTED EXCLAMATION MARK
-- '¢' -- CENT SIGN
-- '£' -- POUND SIGN
-- '¤' -- CURRENCY SIGN
-- '¥' -- YEN SIGN
-- '¦' -- BROKEN BAR
-- '§' -- SECTION SIGN
-- '¨' -- DIAERESIS
-- '©' -- COPYRIGHT SIGN
-- 'ª' -- FEMININE ORDINAL INDICATOR
-- '«' -- LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
-- '¬' -- NOT SIGN
-- '' -- SOFT HYPHEN
-- '®' -- REGISTERED SIGN
-- '¯' -- MACRON
-- '°' -- DEGREE SIGN
-- '±' -- PLUS-MINUS SIGN
-- '²' -- SUPERSCRIPT TWO
-- '³' -- SUPERSCRIPT THREE
-- '´' -- ACUTE ACCENT
-- 'µ' -- MICRO SIGN
-- '¶' -- PILCROW SIGN
-- '·' -- MIDDLE DOT
-- '¸' -- CEDILLA
-- '¹' -- SUPERSCRIPT ONE
-- 'º' -- MASCULINE ORDINAL INDICATOR
-- '»' -- RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
-- '¼' -- VULGAR FRACTION ONE QUARTER
-- '½' -- VULGAR FRACTION ONE HALF
-- '¾' -- VULGAR FRACTION THREE QUARTERS
-- '¿' -- INVERTED QUESTION MARK
-- '×' -- MULTIPLICATION SIGN
-- '÷' -- DIVISION SIGN
DEL .. APC => Invalid);
-- The context contains the whole internal state of the scanner, ie
-- it can be used to push/pop a lexical analysis, to restart the
-- scanner from a context marking a previous point.
type Scan_Context is record
Source: File_Buffer_Acc;
Source_File: Source_File_Entry;
Line_Number: Natural;
Line_Pos: Source_Ptr;
Pos: Source_Ptr;
Token_Pos: Source_Ptr;
File_Len: Source_Ptr;
File_Name: Name_Id;
Token: Token_Type;
Prev_Token: Token_Type;
Str_Id : String8_Id;
Str_Len : Nat32;
Identifier: Name_Id;
Int64: Iir_Int64;
Fp64: Iir_Fp64;
end record;
-- The current context.
-- Default value is an invalid context.
Current_Context: Scan_Context := (Source => null,
Source_File => No_Source_File_Entry,
Line_Number => 0,
Line_Pos => 0,
Pos => 0,
Token_Pos => 0,
File_Len => 0,
File_Name => Null_Identifier,
Token => Tok_Invalid,
Prev_Token => Tok_Invalid,
Identifier => Null_Identifier,
Str_Id => Null_String8,
Str_Len => 0,
Int64 => 0,
Fp64 => 0.0);
Source: File_Buffer_Acc renames Current_Context.Source;
Pos: Source_Ptr renames Current_Context.Pos;
-- When CURRENT_TOKEN is an identifier, its name_id is stored into
-- this global variable.
-- Function current_text can be used to convert it into an iir.
function Current_Identifier return Name_Id is
begin
return Current_Context.Identifier;
end Current_Identifier;
procedure Invalidate_Current_Identifier is
begin
Current_Context.Identifier := Null_Identifier;
end Invalidate_Current_Identifier;
procedure Invalidate_Current_Token is
begin
if Current_Token /= Tok_Invalid then
Current_Context.Prev_Token := Current_Token;
Current_Token := Tok_Invalid;
end if;
end Invalidate_Current_Token;
function Current_String_Id return String8_Id is
begin
return Current_Context.Str_Id;
end Current_String_Id;
function Current_String_Length return Nat32 is
begin
return Current_Context.Str_Len;
end Current_String_Length;
function Current_Iir_Int64 return Iir_Int64 is
begin
return Current_Context.Int64;
end Current_Iir_Int64;
function Current_Iir_Fp64 return Iir_Fp64 is
begin
return Current_Context.Fp64;
end Current_Iir_Fp64;
function Get_Current_File return Name_Id is
begin
return Current_Context.File_Name;
end Get_Current_File;
function Get_Current_Source_File return Source_File_Entry is
begin
return Current_Context.Source_File;
end Get_Current_Source_File;
function Get_Current_Line return Natural is
begin
return Current_Context.Line_Number;
end Get_Current_Line;
function Get_Current_Column return Natural
is
Col : Natural;
Name : Name_Id;
begin
Coord_To_Position
(Current_Context.Source_File,
Current_Context.Line_Pos,
Integer (Current_Context.Pos - Current_Context.Line_Pos),
Name, Col);
return Col;
end Get_Current_Column;
function Get_Token_Column return Natural
is
Col : Natural;
Name : Name_Id;
begin
Coord_To_Position
(Current_Context.Source_File,
Current_Context.Line_Pos,
Integer (Current_Context.Token_Pos - Current_Context.Line_Pos),
Name, Col);
return Col;
end Get_Token_Column;
function Get_Token_Position return Source_Ptr is
begin
return Current_Context.Token_Pos;
end Get_Token_Position;
function Get_Position return Source_Ptr is
begin
return Current_Context.Pos;
end Get_Position;
procedure Set_File (Source_File : Source_File_Entry)
is
N_Source: File_Buffer_Acc;
begin
if Current_Context.Source /= null then
raise Internal_Error;
end if;
if Source_File = No_Source_File_Entry then
raise Internal_Error;
end if;
N_Source := Get_File_Source (Source_File);
Current_Context := (Source => N_Source,
Source_File => Source_File,
Line_Number => 1,
Line_Pos => 0,
Pos => N_Source'First,
Token_Pos => 0, -- should be invalid,
File_Len => Get_File_Length (Source_File),
File_Name => Get_File_Name (Source_File),
Token => Tok_Invalid,
Prev_Token => Tok_Invalid,
Identifier => Null_Identifier,
Str_Id => Null_String8,
Str_Len => 0,
Int64 => -1,
Fp64 => 0.0);
Current_Token := Tok_Invalid;
end Set_File;
procedure Set_Current_Position (Position: Source_Ptr)
is
Loc : Location_Type;
Offset: Natural;
File_Entry : Source_File_Entry;
begin
if Current_Context.Source = null then
raise Internal_Error;
end if;
Current_Token := Tok_Invalid;
Current_Context.Pos := Position;
Loc := File_Pos_To_Location (Current_Context.Source_File,
Current_Context.Pos);
Location_To_Coord (Loc,
File_Entry, Current_Context.Line_Pos,
Current_Context.Line_Number, Offset);
end Set_Current_Position;
procedure Close_File is
begin
Current_Context.Source := null;
end Close_File;
-- Emit an error when a character above 128 was found.
-- This must be called only in vhdl87.
procedure Error_8bit is
begin
Error_Msg_Scan ("8 bits characters not allowed in vhdl87");
end Error_8bit;
-- Emit an error when a separator is expected.
procedure Error_Separator is
begin
Error_Msg_Scan ("a separator is required here");
end Error_Separator;
-- scan a decimal literal or a based literal.
--
-- LRM93 13.4.1
-- DECIMAL_LITERAL ::= INTEGER [ . INTEGER ] [ EXPONENT ]
-- EXPONENT ::= E [ + ] INTEGER | E - INTEGER
--
-- LRM93 13.4.2
-- BASED_LITERAL ::= BASE # BASED_INTEGER [ . BASED_INTEGER ] # EXPONENT
-- BASE ::= INTEGER
procedure Scan_Literal is separate;
-- Scan a string literal.
--
-- LRM93 13.6 / LRM08 15.7
-- A string literal is formed by a sequence of graphic characters
-- (possibly none) enclosed between two quotation marks used as string
-- brackets.
-- STRING_LITERAL ::= " { GRAPHIC_CHARACTER } "
--
-- IN: for a string, at the call of this procedure, the current character
-- must be either '"' or '%'.
procedure Scan_String
is
-- The quotation character (can be " or %).
Mark: Character;
-- Current character.
C : Character;
-- Current length.
Length : Nat32;
begin
-- String delimiter.
Mark := Source (Pos);
pragma Assert (Mark = Quotation or else Mark = '%');
Pos := Pos + 1;
Length := 0;
Current_Context.Str_Id := Str_Table.Create_String8;
loop
C := Source (Pos);
if C = Mark then
-- LRM93 13.6
-- If a quotation mark value is to be represented in the sequence
-- of character values, then a pair of adjacent quoatation
-- characters marks must be written at the corresponding place
-- within the string literal.
-- LRM93 13.10
-- Any pourcent sign within the sequence of characters must then
-- be doubled, and each such doubled percent sign is interpreted
-- as a single percent sign value.
-- The same replacement is allowed for a bit string literal,
-- provieded that both bit string brackets are replaced.
Pos := Pos + 1;
exit when Source (Pos) /= Mark;
end if;
case Characters_Kind (C) is
when Format_Effector =>
Error_Msg_Scan ("format effector not allowed in a string");
exit;
when Invalid =>
Error_Msg_Scan
("invalid character not allowed, even in a string");
when Graphic_Character =>
if Vhdl_Std = Vhdl_87 and then C > Character'Val (127) then
Error_8bit;
end if;
end case;
if C = Quotation and Mark = '%' then
-- LRM93 13.10
-- The quotation marks (") used as string brackets at both ends of
-- a string literal can be replaced by percent signs (%), provided
-- that the enclosed sequence of characters constains no quotation
-- marks, and provided that both string brackets are replaced.
Error_Msg_Scan
("'""' cannot be used in a string delimited with '%'");
end if;
Length := Length + 1;
Str_Table.Append_String8 (Character'Pos (C));
Pos := Pos + 1;
end loop;
Current_Token := Tok_String;
Current_Context.Str_Len := Length;
end Scan_String;
-- Scan a bit string literal.
--
-- LRM93 13.7
-- A bit string literal is formed by a sequence of extended digits
-- (possibly none) enclosed between two quotations used as bit string
-- brackets, preceded by a base specifier.
-- BIT_STRING_LITERAL ::= BASE_SPECIFIER " [ BIT_VALUE ] "
-- BIT_VALUE ::= EXTENDED_DIGIT { [ UNDERLINE ] EXTENDED_DIGIT }
--
-- The current character must be a base specifier, followed by '"' or '%'.
-- The base must be valid.
procedure Scan_Bit_String
is
-- The base specifier.
Base_Log : Nat32 range 1 .. 4;
-- The quotation character (can be " or %).
Mark: Character;
-- Current character.
C : Character;
-- Current length.
Length : Nat32;
-- Digit value.
V, D : Nat8;
-- Position of character '0'.
Pos_0 : constant Nat8 := Character'Pos ('0');
begin
-- LRM93 13.7
-- A letter in a bit string literal (... or the base specificer) can be
-- written either in lowercase or in upper case, with the same meaning.
--
-- LRM08 15.8 Bit string literals
-- Not present!
case Source (Pos) is
when 'x' | 'X' =>
Base_Log := 4;
when 'o' | 'O' =>
Base_Log := 3;
when 'b' | 'B' =>
Base_Log := 1;
when others =>
raise Internal_Error;
end case;
Pos := Pos + 1;
Mark := Source (Pos);
pragma Assert (Mark = Quotation or else Mark = '%');
Pos := Pos + 1;
Length := 0;
Current_Context.Str_Id := Str_Table.Create_String8;
loop
<< Again >> null;
C := Source (Pos);
Pos := Pos + 1;
exit when C = Mark;
-- LRM93 13.7
-- If the base specifier is 'B', the extended digits in the bit
-- value are restricted to 0 and 1.
-- If the base specifier is 'O', the extended digits int the bit
-- value are restricted to legal digits in the octal number
-- system, ie, the digits 0 through 7.
-- If the base specifier is 'X', the extended digits are all digits
-- together with the letters A through F.
case C is
when '0' .. '9' =>
V := Character'Pos (C) - Character'Pos ('0');
when 'A' .. 'F' =>
V := Character'Pos (C) - Character'Pos ('A') + 10;
when 'a' .. 'f' =>
-- LRM93 13.7
-- A letter in a bit string literal (...) can be written either
-- in lowercase or in upper case, with the same meaning.
V := Character'Pos (C) - Character'Pos ('a') + 10;
when '_' =>
if Source (Pos) = '_' then
Error_Msg_Scan
("double underscore not allowed in a bit string");
end if;
if Source (Pos - 2) = Mark then
Error_Msg_Scan
("underscore not allowed at the start of a bit string");
elsif Source (Pos) = Mark then
Error_Msg_Scan
("underscore not allowed at the end of a bit string");
end if;
goto Again;
when '"' =>
pragma Assert (Mark = '%');
Error_Msg_Scan
("'""' cannot close a bit string opened by '%'");
exit;
when '%' =>
pragma Assert (Mark = '"');
Error_Msg_Scan
("'%' cannot close a bit string opened by '""'");
exit;
when others =>
Error_Msg_Scan ("bit string not terminated");
Pos := Pos - 1;
exit;
end case;
case Base_Log is
when 1 =>
if V > 1 then
Error_Msg_Scan ("invalid character in a binary bit string");
V := 1;
end if;
Str_Table.Append_String8 (Pos_0 + V);
when 2 =>
raise Internal_Error;
when 3 =>
if V > 7 then
Error_Msg_Scan ("invalid character in a octal bit string");
V := 7;
end if;
for I in 1 .. 3 loop
D := V / 4;
Str_Table.Append_String8 (Pos_0 + D);
V := (V - 4 * D) * 2;
end loop;
when 4 =>
for I in 1 .. 4 loop
D := V / 8;
Str_Table.Append_String8 (Pos_0 + D);
V := (V - 8 * D) * 2;
end loop;
end case;
Length := Length + Base_Log;
end loop;
if Length = 0 then
Error_Msg_Scan ("empty bit string is not allowed");
end if;
Current_Token := Tok_Bit_String;
Current_Context.Int64 := Iir_Int64 (Base_Log);
Current_Context.Str_Len := Length;
end Scan_Bit_String;
-- LRM93 13.3.1
-- Basic Identifiers
-- A basic identifier consists only of letters, digits, and underlines.
-- BASIC_IDENTIFIER ::= LETTER { [ UNDERLINE ] LETTER_OR_DIGIT }
-- LETTER_OR_DIGIT ::= LETTER | DIGIT
-- LETTER ::= UPPER_CASE_LETTER | LOWER_CASE_LETTER
--
-- NB: At the call of this procedure, the current character must be a legal
-- character for a basic identifier.
procedure Scan_Identifier
is
use Name_Table;
C : Character;
Len : Natural;
begin
-- This is an identifier or a key word.
Len := 0;
loop
-- Source (pos) is correct.
-- LRM93 13.3.1
-- All characters if a basic identifier are signifiant, including
-- any underline character inserted between a letter or digit and
-- an adjacent letter or digit.
-- Basic identifiers differing only in the use of the corresponding
-- upper and lower case letters are considered as the same.
-- This is achieved by converting all upper case letters into
-- equivalent lower case letters.
-- The opposite (converting in lower case letters) is not possible,
-- because two characters have no upper-case equivalent.
C := Source (Pos);
case C is
when 'A' .. 'Z' =>
C := Character'Val
(Character'Pos (C)
+ Character'Pos ('a') - Character'Pos ('A'));
when 'a' .. 'z' | '0' .. '9' =>
null;
when '_' =>
if Source (Pos + 1) = '_' then
Error_Msg_Scan ("two underscores can't be consecutive");
end if;
when ' ' | ')' | '.' | ';' | ':' =>
exit;
when others =>
-- Non common case.
case Characters_Kind (C) is
when Upper_Case_Letter | Lower_Case_Letter =>
if Vhdl_Std = Vhdl_87 then
Error_8bit;
end if;
Len := Len + 1;
C := Ada.Characters.Handling.To_Lower (C);
when Digit =>
raise Internal_Error;
when others =>
exit;
end case;
end case;
-- Put character in name buffer. FIXME: compute the hash at the same
-- time ?
Len := Len + 1;
Name_Buffer (Len) := C;
-- Next character.
Pos := Pos + 1;
end loop;
if Source (Pos - 1) = '_' then
if not Flag_Psl then
-- Some PSL reserved words finish with '_'. This case is handled
-- later.
Error_Msg_Scan ("identifier cannot finish with '_'");
end if;
Pos := Pos - 1;
Len := Len - 1;
C := '_';
end if;
-- LRM93 13.2
-- At least one separator is required between an identifier or an
-- abstract literal and an adjacent identifier or abstract literal.
case Characters_Kind (C) is
when Digit
| Upper_Case_Letter
| Lower_Case_Letter =>
raise Internal_Error;
when Other_Special_Character =>
if Vhdl_Std /= Vhdl_87 and then C = '\' then
Error_Separator;
end if;
when Invalid
| Format_Effector
| Space_Character
| Special_Character =>
null;
end case;
Name_Length := Len;
-- Hash it.
Current_Context.Identifier := Name_Table.Get_Identifier;
if Current_Identifier in Std_Names.Name_Id_Keywords then
-- LRM93 13.9
-- The identifiers listed below are called reserved words and are
-- reserved for signifiances in the language.
-- IN: this is also achieved in packages std_names and tokens.
Current_Token := Token_Type'Val
(Token_Type'Pos (Tok_First_Keyword)
+ Current_Identifier - Std_Names.Name_First_Keyword);
case Current_Identifier is
when Std_Names.Name_Id_AMS_Reserved_Words =>
if not AMS_Vhdl then
if Flags.Warn_Reserved_Word then
Warning_Msg_Scan
("using """ & Name_Buffer (1 .. Name_Length)
& """ AMS-VHDL reserved word as an identifier");
end if;
Current_Token := Tok_Identifier;
end if;
when Std_Names.Name_Id_Vhdl00_Reserved_Words =>
if Vhdl_Std < Vhdl_00 then
if Flags.Warn_Reserved_Word then
Warning_Msg_Scan
("using """ & Name_Buffer (1 .. Name_Length)
& """ vhdl00 reserved word as an identifier");
end if;
Current_Token := Tok_Identifier;
end if;
when Std_Names.Name_Id_Vhdl93_Reserved_Words =>
if Vhdl_Std = Vhdl_87 then
if Flags.Warn_Reserved_Word then
Warning_Msg_Scan
("using """ & Name_Buffer (1 .. Name_Length)
& """ vhdl93 reserved word as a vhdl87 identifier");
Warning_Msg_Scan
("(use option --std=93 to compile as vhdl93)");
end if;
Current_Token := Tok_Identifier;
end if;
when Std_Names.Name_Id_Vhdl87_Reserved_Words =>
null;
when others =>
raise Program_Error;
end case;
elsif Flag_Psl then
case Current_Identifier is
when Std_Names.Name_Clock =>
Current_Token := Tok_Psl_Clock;
when Std_Names.Name_Const =>
Current_Token := Tok_Psl_Const;
when Std_Names.Name_Boolean =>
Current_Token := Tok_Psl_Boolean;
when Std_Names.Name_Sequence =>
Current_Token := Tok_Psl_Sequence;
when Std_Names.Name_Property =>
Current_Token := Tok_Psl_Property;
when Std_Names.Name_Cover =>
Current_Token := Tok_Psl_Cover;
when Std_Names.Name_Default =>
Current_Token := Tok_Psl_Default;
when Std_Names.Name_Inf =>
Current_Token := Tok_Inf;
when Std_Names.Name_Within =>
Current_Token := Tok_Within;
when Std_Names.Name_Abort =>
Current_Token := Tok_Abort;
when Std_Names.Name_Before =>
Current_Token := Tok_Before;
when Std_Names.Name_Always =>
Current_Token := Tok_Always;
when Std_Names.Name_Never =>
Current_Token := Tok_Never;
when Std_Names.Name_Eventually =>
Current_Token := Tok_Eventually;
when Std_Names.Name_Next_A =>
Current_Token := Tok_Next_A;
when Std_Names.Name_Next_E =>
Current_Token := Tok_Next_E;
when Std_Names.Name_Next_Event =>
Current_Token := Tok_Next_Event;
when Std_Names.Name_Next_Event_A =>
Current_Token := Tok_Next_Event_A;
when Std_Names.Name_Next_Event_E =>
Current_Token := Tok_Next_Event_E;
when Std_Names.Name_Until =>
Current_Token := Tok_Until;
when others =>
Current_Token := Tok_Identifier;
if C = '_' then
Error_Msg_Scan ("identifiers cannot finish with '_'");
end if;
end case;
else
Current_Token := Tok_Identifier;
end if;
end Scan_Identifier;
-- LRM93 13.3.2
-- EXTENDED_IDENTIFIER ::= \ GRAPHIC_CHARACTER { GRAPHIC_CHARACTER } \
--
-- Create an (extended) indentifier.
-- Extended identifiers are stored as they appear (leading and tailing
-- backslashes, doubling backslashes inside).
procedure Scan_Extended_Identifier
is
use Name_Table;
begin
-- LRM93 13.3.2
-- Moreover, every extended identifiers is distinct from any basic
-- identifier.
-- This is satisfied by storing '\' in the name table.
Name_Length := 1;
Name_Buffer (1) := '\';
loop
-- Next character.
Pos := Pos + 1;
if Source (Pos) = '\' then
-- LRM93 13.3.2
-- If a backslash is to be used as one of the graphic characters
-- of an extended literal, it must be doubled.
-- LRM93 13.3.2
-- (a doubled backslash couting as one character)
Name_Length := Name_Length + 1;
Name_Buffer (Name_Length) := '\';
Pos := Pos + 1;
exit when Source (Pos) /= '\';
end if;
-- source (pos) is correct.
case Characters_Kind (Source (Pos)) is
when Format_Effector =>
Error_Msg_Scan ("format effector in extended identifier");
exit;
when Graphic_Character =>
null;
when Invalid =>
Error_Msg_Scan ("invalid character in extended identifier");
end case;
Name_Length := Name_Length + 1;
-- LRM93 13.3.2
-- Extended identifiers differing only in the use of corresponding
-- upper and lower case letters are distinct.
Name_Buffer (Name_Length) := Source (Pos);
end loop;
if Name_Length <= 2 then
Error_Msg_Scan ("empty extended identifier is not allowed");
end if;
-- LRM93 13.2
-- At least one separator is required between an identifier or an
-- abstract literal and an adjacent identifier or abstract literal.
case Characters_Kind (Source (Pos)) is
when Digit
| Upper_Case_Letter
| Lower_Case_Letter =>
Error_Separator;
when Invalid
| Format_Effector
| Space_Character
| Special_Character
| Other_Special_Character =>
null;
end case;
-- Hash it.
Current_Context.Identifier := Name_Table.Get_Identifier;
Current_Token := Tok_Identifier;
end Scan_Extended_Identifier;
procedure Convert_Identifier
is
procedure Error_Bad is
begin
Error_Msg_Option ("bad character in identifier");
end Error_Bad;
procedure Error_8bit is
begin
Error_Msg_Option ("8 bits characters not allowed in vhdl87");
end Error_8bit;
use Name_Table;
C : Character;
begin
if Name_Length = 0 then
Error_Msg_Option ("identifier required");
return;
end if;
if Name_Buffer (1) = '\' then
-- Extended identifier.
if Vhdl_Std = Vhdl_87 then
Error_Msg_Option ("extended identifiers not allowed in vhdl87");
return;
end if;
if Name_Length < 3 then
Error_Msg_Option ("extended identifier is too short");
return;
end if;
if Name_Buffer (Name_Length) /= '\' then
Error_Msg_Option ("extended identifier must finish with a '\'");
return;
end if;
for I in 2 .. Name_Length - 1 loop
C := Name_Buffer (I);
case Characters_Kind (C) is
when Format_Effector =>
Error_Msg_Option ("format effector in extended identifier");
return;
when Graphic_Character =>
if C = '\' then
if Name_Buffer (I + 1) /= '\'
or else I = Name_Length - 1
then
Error_Msg_Option ("anti-slash must be doubled "
& "in extended identifier");
return;
end if;
end if;
when Invalid =>
Error_Bad;
end case;
end loop;
else
-- Identifier
for I in 1 .. Name_Length loop
C := Name_Buffer (I);
case Characters_Kind (C) is
when Upper_Case_Letter =>
if Vhdl_Std = Vhdl_87 and C > 'Z' then
Error_8bit;
end if;
Name_Buffer (I) := Ada.Characters.Handling.To_Lower (C);
when Lower_Case_Letter | Digit =>
if Vhdl_Std = Vhdl_87 and C > 'z' then
Error_8bit;
end if;
when Special_Character =>
-- The current character is legal in an identifier.
if C = '_' then
if I = 1 then
Error_Msg_Option
("identifier cannot start with an underscore");
return;
end if;
if Name_Buffer (I - 1) = '_' then
Error_Msg_Option
("two underscores can't be consecutive");
return;
end if;
if I = Name_Length then
Error_Msg_Option
("identifier cannot finish with an underscore");
return;
end if;
else
Error_Bad;
end if;
when others =>
Error_Bad;
end case;
end loop;
end if;
end Convert_Identifier;
-- Scan an identifier within a comment. Only lower case letters are
-- allowed.
function Scan_Comment_Identifier return Boolean
is
use Name_Table;
Len : Natural;
C : Character;
begin
-- Skip spaces.
while Source (Pos) = ' ' or Source (Pos) = HT loop
Pos := Pos + 1;
end loop;
-- The identifier shall start with a lower case letter.
if Source (Pos) not in 'a' .. 'z' then
return False;
end if;
-- Scan the identifier (in lower cases).
Len := 0;
loop
C := Source (Pos);
exit when C not in 'a' .. 'z' and C /= '_';
Len := Len + 1;
Name_Buffer (Len) := C;
Pos := Pos + 1;
end loop;
-- Shall be followed by a space or a new line.
case C is
when ' ' | HT | LF | CR =>
null;
when others =>
return False;
end case;
Name_Length := Len;
return True;
end Scan_Comment_Identifier;
-- Scan tokens within a comment. Return TRUE if Current_Token was set,
-- return FALSE to discard the comment (ie treat it like a real comment).
function Scan_Comment return Boolean
is
use Std_Names;
Id : Name_Id;
begin
if not Scan_Comment_Identifier then
return False;
end if;
-- Hash it.
Id := Name_Table.Get_Identifier;
case Id is
when Name_Psl =>
-- Accept tokens after '-- psl'.
if Flag_Psl_Comment then
Flag_Psl := True;
Flag_Scan_In_Comment := True;
return True;
end if;
when others =>
null;
end case;
return False;
end Scan_Comment;
function Scan_Exclam_Mark return Boolean is
begin
if Source (Pos) = '!' then
Pos := Pos + 1;
return True;
else
return False;
end if;
end Scan_Exclam_Mark;
function Scan_Underscore return Boolean is
begin
if Source (Pos) = '_' then
Pos := Pos + 1;
return True;
else
return False;
end if;
end Scan_Underscore;
-- The Scan_Next_Line procedure must be called after each end-of-line to
-- register to next line number. This is called by Scan_CR_Newline and
-- Scan_LF_Newline.
procedure Scan_Next_Line is
begin
Current_Context.Line_Number := Current_Context.Line_Number + 1;
Current_Context.Line_Pos := Pos;
File_Add_Line_Number
(Current_Context.Source_File, Current_Context.Line_Number, Pos);
end Scan_Next_Line;
-- Scan a CR end-of-line.
procedure Scan_CR_Newline is
begin
-- Accept CR or CR+LF as line separator.
if Source (Pos + 1) = LF then
Pos := Pos + 2;
else
Pos := Pos + 1;
end if;
Scan_Next_Line;
end Scan_CR_Newline;
-- Scan a LF end-of-line.
procedure Scan_LF_Newline is
begin
-- Accept LF or LF+CR as line separator.
if Source (Pos + 1) = CR then
Pos := Pos + 2;
else
Pos := Pos + 1;
end if;
Scan_Next_Line;
end Scan_LF_Newline;
-- Get a new token.
procedure Scan is
begin
if Current_Token /= Tok_Invalid then
Current_Context.Prev_Token := Current_Token;
end if;
<< Again >> null;
-- Skip commonly used separators.
while Source(Pos) = ' ' or Source(Pos) = HT loop
Pos := Pos + 1;
end loop;
Current_Context.Token_Pos := Pos;
Current_Context.Identifier := Null_Identifier;
case Source (Pos) is
when HT | ' ' =>
-- Must have already been skipped just above.
raise Internal_Error;
when NBSP =>
if Vhdl_Std = Vhdl_87 then
Error_Msg_Scan ("NBSP character not allowed in vhdl87");
end if;
Pos := Pos + 1;
goto Again;
when VT | FF =>
Pos := Pos + 1;
goto Again;
when LF =>
Scan_LF_Newline;
if Flag_Newline then
Current_Token := Tok_Newline;
return;
end if;
goto Again;
when CR =>
Scan_CR_Newline;
if Flag_Newline then
Current_Token := Tok_Newline;
return;
end if;
goto Again;
when '-' =>
if Source (Pos + 1) = '-' then
-- This is a comment.
-- LRM93 13.8
-- A comment starts with two adjacent hyphens and extends up
-- to the end of the line.
-- A comment can appear on any line line of a VHDL
-- description.
-- The presence or absence of comments has no influence on
-- wether a description is legal or illegal.
-- Futhermore, comments do not influence the execution of a
-- simulation module; their sole purpose is the enlightenment
-- of the human reader.
-- GHDL note: As a consequence, an obfruscating comment
-- is out of purpose, and a warning could be reported :-)
Pos := Pos + 2;
-- Scan inside a comment. So we just ignore the two dashes.
if Flag_Scan_In_Comment then
goto Again;
end if;
-- Handle keywords in comment (PSL).
if Flag_Comment_Keyword and then Scan_Comment then
goto Again;
end if;
-- LRM93 13.2
-- In any case, a sequence of one or more format
-- effectors other than horizontal tabulation must
-- cause at least one end of line.
while Source (Pos) /= CR and Source (Pos) /= LF and
Source (Pos) /= VT and Source (Pos) /= FF and
Source (Pos) /= Files_Map.EOT
loop
if not Flags.Mb_Comment
and then Characters_Kind (Source (Pos)) = Invalid
then
Error_Msg_Scan ("invalid character, even in a comment");
end if;
Pos := Pos + 1;
end loop;
if Flag_Comment then
Current_Token := Tok_Comment;
return;
end if;
goto Again;
elsif Flag_Psl and then Source (Pos + 1) = '>' then
Current_Token := Tok_Minus_Greater;
Pos := Pos + 2;
return;
else
Current_Token := Tok_Minus;
Pos := Pos + 1;
return;
end if;
when '+' =>
Current_Token := Tok_Plus;
Pos := Pos + 1;
return;
when '*' =>
if Source (Pos + 1) = '*' then
Current_Token := Tok_Double_Star;
Pos := Pos + 2;
else
Current_Token := Tok_Star;
Pos := Pos + 1;
end if;
return;
when '/' =>
if Source (Pos + 1) = '=' then
Current_Token := Tok_Not_Equal;
Pos := Pos + 2;
elsif Source (Pos + 1) = '*' then
-- LRM08 15.9 Comments
-- A delimited comment start with a solidus (slash) character
-- immediately followed by an asterisk character and extends up
-- to the first subsequent occurrence of an asterisk character
-- immediately followed by a solidus character.
if Vhdl_Std < Vhdl_08 then
Error_Msg_Scan
("block comment are not allowed before vhdl 2008");
end if;
-- Skip '/*'.
Pos := Pos + 2;
loop
case Source (Pos) is
when '/' =>
-- LRM08 15.9
-- Moreover, an occurrence of a solidus character
-- immediately followed by an asterisk character
-- within a delimited comment is not interpreted as
-- the start of a nested delimited comment.
if Source (Pos + 1) = '*' then
Warning_Msg_Scan
("'/*' found within a block comment");
end if;
Pos := Pos + 1;
when '*' =>
if Source (Pos + 1) = '/' then
Pos := Pos + 2;
exit;
else
Pos := Pos + 1;
end if;
when CR =>
Scan_CR_Newline;
when LF =>
Scan_LF_Newline;
when Files_Map.EOT =>
if Pos >= Current_Context.File_Len then
-- Point at the start of the comment.
Error_Msg_Scan
("block comment not terminated at end of file",
File_Pos_To_Location
(Current_Context.Source_File,
Current_Context.Token_Pos));
exit;
end if;
Pos := Pos + 1;
when others =>
Pos := Pos + 1;
end case;
end loop;
if Flag_Comment then
Current_Token := Tok_Comment;
return;
end if;
goto Again;
else
Current_Token := Tok_Slash;
Pos := Pos + 1;
end if;
return;
when '(' =>
Current_Token := Tok_Left_Paren;
Pos := Pos + 1;
return;
when ')' =>
Current_Token := Tok_Right_Paren;
Pos := Pos + 1;
return;
when '|' =>
if Flag_Psl then
if Source (Pos + 1) = '|' then
Current_Token := Tok_Bar_Bar;
Pos := Pos + 2;
elsif Source (Pos + 1) = '-'
and then Source (Pos + 2) = '>'
then
Current_Token := Tok_Bar_Arrow;
Pos := Pos + 3;
elsif Source (Pos + 1) = '='
and then Source (Pos + 2) = '>'
then
Current_Token := Tok_Bar_Double_Arrow;
Pos := Pos + 3;
else
Current_Token := Tok_Bar;
Pos := Pos + 1;
end if;
else
Current_Token := Tok_Bar;
Pos := Pos + 1;
end if;
return;
when '!' =>
if Flag_Psl then
Current_Token := Tok_Exclam_Mark;
else
-- LRM93 13.10
-- A vertical line (|) can be replaced by an exclamation
-- mark (!) where used as a delimiter.
Current_Token := Tok_Bar;
end if;
Pos := Pos + 1;
return;
when ':' =>
if Source (Pos + 1) = '=' then
Current_Token := Tok_Assign;
Pos := Pos + 2;
else
Current_Token := Tok_Colon;
Pos := Pos + 1;
end if;
return;
when ';' =>
Current_Token := Tok_Semi_Colon;
Pos := Pos + 1;
return;
when ',' =>
Current_Token := Tok_Comma;
Pos := Pos + 1;
return;
when '.' =>
if Source (Pos + 1) = '.' then
-- Be Ada friendly...
Error_Msg_Scan ("'..' is invalid in vhdl, replaced by 'to'");
Current_Token := Tok_To;
Pos := Pos + 2;
return;
end if;
Current_Token := Tok_Dot;
Pos := Pos + 1;
return;
when '&' =>
if Flag_Psl and then Source (Pos + 1) = '&' then
Current_Token := Tok_And_And;
Pos := Pos + 2;
else
Current_Token := Tok_Ampersand;
Pos := Pos + 1;
end if;
return;
when '<' =>
if Source (Pos + 1) = '=' then
Current_Token := Tok_Less_Equal;
Pos := Pos + 2;
elsif Source (Pos + 1) = '>' then
Current_Token := Tok_Box;
Pos := Pos + 2;
else
Current_Token := Tok_Less;
Pos := Pos + 1;
end if;
return;
when '>' =>
if Source (Pos + 1) = '=' then
Current_Token := Tok_Greater_Equal;
Pos := Pos + 2;
else
Current_Token := Tok_Greater;
Pos := Pos + 1;
end if;
return;
when '=' =>
if Source (Pos + 1) = '=' then
if AMS_Vhdl then
Current_Token := Tok_Equal_Equal;
else
Error_Msg_Scan
("'==' is not the vhdl equality, replaced by '='");
Current_Token := Tok_Equal;
end if;
Pos := Pos + 2;
elsif Source (Pos + 1) = '>' then
Current_Token := Tok_Double_Arrow;
Pos := Pos + 2;
else
Current_Token := Tok_Equal;
Pos := Pos + 1;
end if;
return;
when ''' =>
-- Handle cases such as character'('a')
-- FIXME: what about f ()'length ? or .all'length
if Current_Context.Prev_Token /= Tok_Identifier
and then Current_Context.Prev_Token /= Tok_Character
and then Source (Pos + 2) = '''
then
-- LRM93 13.5
-- A character literal is formed by enclosing one of the 191
-- graphic character (...) between two apostrophe characters.
-- CHARACTER_LITERAL ::= ' GRAPHIC_CHARACTER '
if Characters_Kind (Source (Pos + 1)) not in Graphic_Character
then
Error_Msg_Scan
("a character literal can only be a graphic character");
elsif Vhdl_Std = Vhdl_87
and then Source (Pos + 1) > Character'Val (127)
then
Error_8bit;
end if;
Current_Token := Tok_Character;
Current_Context.Identifier :=
Name_Table.Get_Identifier (Source (Pos + 1));
Pos := Pos + 3;
return;
else
Current_Token := Tok_Tick;
Pos := Pos + 1;
end if;
return;
when '0' .. '9' =>
Scan_Literal;
-- LRM 13.2
-- At least one separator is required between an identifier or
-- an abstract literal and an adjacent identifier or abstract
-- literal.
case Characters_Kind (Source (Pos)) is
when Digit =>
raise Internal_Error;
when Upper_Case_Letter
| Lower_Case_Letter =>
-- Could call Error_Separator, but use a clearer message
-- for this common case.
-- Note: the term "unit name" is not correct here, since it
-- can be any identifier or even a keyword; however it is
-- probably the most common case (eg 10ns).
Error_Msg_Scan
("space is required between number and unit name");
when Other_Special_Character =>
if Vhdl_Std /= Vhdl_87 and then Source (Pos) = '\' then
Error_Separator;
end if;
when Invalid
| Format_Effector
| Space_Character
| Special_Character =>
null;
end case;
return;
when '#' =>
Error_Msg_Scan ("'#' is used for based literals and "
& "must be preceded by a base");
-- Cannot easily continue.
raise Compilation_Error;
when Quotation | '%' =>
Scan_String;
return;
when '[' =>
if Flag_Psl then
if Source (Pos + 1) = '*' then
Current_Token := Tok_Brack_Star;
Pos := Pos + 2;
elsif Source (Pos + 1) = '+'
and then Source (Pos + 2) = ']'
then
Current_Token := Tok_Brack_Plus_Brack;
Pos := Pos + 3;
elsif Source (Pos + 1) = '-'
and then Source (Pos + 2) = '>'
then
Current_Token := Tok_Brack_Arrow;
Pos := Pos + 3;
elsif Source (Pos + 1) = '=' then
Current_Token := Tok_Brack_Equal;
Pos := Pos + 2;
else
Current_Token := Tok_Left_Bracket;
Pos := Pos + 1;
end if;
else
if Vhdl_Std = Vhdl_87 then
Error_Msg_Scan
("'[' is an invalid character in vhdl87, replaced by '('");
Current_Token := Tok_Left_Paren;
else
Current_Token := Tok_Left_Bracket;
end if;
Pos := Pos + 1;
end if;
return;
when ']' =>
if Vhdl_Std = Vhdl_87 and not Flag_Psl then
Error_Msg_Scan
("']' is an invalid character in vhdl87, replaced by ')'");
Current_Token := Tok_Right_Paren;
else
Current_Token := Tok_Right_Bracket;
end if;
Pos := Pos + 1;
return;
when '{' =>
if Flag_Psl then
Current_Token := Tok_Left_Curly;
else
Error_Msg_Scan ("'{' is an invalid character, replaced by '('");
Current_Token := Tok_Left_Paren;
end if;
Pos := Pos + 1;
return;
when '}' =>
if Flag_Psl then
Current_Token := Tok_Right_Curly;
else
Error_Msg_Scan ("'}' is an invalid character, replaced by ')'");
Current_Token := Tok_Right_Paren;
end if;
Pos := Pos + 1;
return;
when '\' =>
if Vhdl_Std = Vhdl_87 then
Error_Msg_Scan
("extended identifiers are not allowed in vhdl87");
end if;
Scan_Extended_Identifier;
return;
when '^' =>
Error_Msg_Scan ("'^' is not a VHDL operator, use 'xor'");
Pos := Pos + 1;
Current_Token := Tok_Xor;
return;
when '~' =>
Error_Msg_Scan ("'~' is not a VHDL operator, use 'not'");
Pos := Pos + 1;
Current_Token := Tok_Not;
return;
when '?' =>
if Vhdl_Std < Vhdl_08 then
Error_Msg_Scan ("'?' can only be used in strings or comments");
Pos := Pos + 1;
goto Again;
else
if Source (Pos + 1) = '<' then
if Source (Pos + 2) = '=' then
Current_Token := Tok_Match_Less_Equal;
Pos := Pos + 3;
else
Current_Token := Tok_Match_Less;
Pos := Pos + 2;
end if;
elsif Source (Pos + 1) = '>' then
if Source (Pos + 2) = '=' then
Current_Token := Tok_Match_Greater_Equal;
Pos := Pos + 3;
else
Current_Token := Tok_Match_Greater;
Pos := Pos + 2;
end if;
elsif Source (Pos + 1) = '?' then
Current_Token := Tok_Condition;
Pos := Pos + 2;
elsif Source (Pos + 1) = '=' then
Current_Token := Tok_Match_Equal;
Pos := Pos + 2;
elsif Source (Pos + 1) = '/'
and then Source (Pos + 2) = '='
then
Current_Token := Tok_Match_Not_Equal;
Pos := Pos + 3;
else
Error_Msg_Scan ("unknown matching operator");
Pos := Pos + 1;
goto Again;
end if;
end if;
return;
when '$' | '`'
| Inverted_Exclamation .. Inverted_Question
| Multiplication_Sign | Division_Sign =>
Error_Msg_Scan ("character """ & Source (Pos)
& """ can only be used in strings or comments");
Pos := Pos + 1;
goto Again;
when '@' =>
if Flag_Psl then
Current_Token := Tok_Arobase;
Pos := Pos + 1;
return;
else
Error_Msg_Scan
("character """ & Source (Pos)
& """ can only be used in strings or comments");
Pos := Pos + 1;
goto Again;
end if;
when '_' =>
Error_Msg_Scan ("an identifier can't start with '_'");
Pos := Pos + 1;
goto Again;
when 'B' | 'b' | 'O' | 'o' | 'X' | 'x' =>
if Source (Pos + 1) = Quotation or else Source (Pos + 1) = '%' then
-- LRM93 13.7
-- BASE_SPECIFIER ::= B | O | X
-- A letter in a bit string literal (either an extended digit or
-- the base specifier) can be written either in lower case or
-- in upper case, with the same meaning.
Scan_Bit_String;
else
Scan_Identifier;
end if;
return;
when 'A' | 'C' .. 'N' | 'P' .. 'W' | 'Y'| 'Z'
| 'a' | 'c' .. 'n' | 'p' .. 'w' | 'y'| 'z' =>
Scan_Identifier;
return;
when UC_A_Grave .. UC_O_Diaeresis
| UC_O_Oblique_Stroke .. UC_Icelandic_Thorn =>
if Vhdl_Std = Vhdl_87 then
Error_Msg_Scan
("upper case letters above 128 are not allowed in vhdl87");
end if;
Scan_Identifier;
return;
when LC_German_Sharp_S .. LC_O_Diaeresis
| LC_O_Oblique_Stroke .. LC_Y_Diaeresis =>
if Vhdl_Std = Vhdl_87 then
Error_Msg_Scan
("lower case letters above 128 are not allowed in vhdl87");
end if;
Scan_Identifier;
return;
when NUL .. ETX | ENQ .. BS | SO .. US | DEL .. APC =>
Error_Msg_Scan
("control character that is not CR, LF, FF, HT or VT " &
"is not allowed");
Pos := Pos + 1;
goto Again;
when Files_Map.EOT =>
if Pos >= Current_Context.File_Len then
-- FIXME: should conditionnaly emit a warning if the file
-- is not terminated by an end of line.
Current_Token := Tok_Eof;
else
Error_Msg_Scan ("EOT is not allowed inside the file");
Pos := Pos + 1;
goto Again;
end if;
return;
end case;
end Scan;
function Get_Token_Location return Location_Type is
begin
return File_Pos_To_Location
(Current_Context.Source_File, Current_Context.Token_Pos);
end Get_Token_Location;
end Scanner;
|