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
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
|
------------------------------------------------------------------------------
-- --
-- GNAT COMPILER COMPONENTS --
-- --
-- S C N G --
-- --
-- B o d y --
-- --
-- Copyright (C) 1992-2020, Free Software Foundation, Inc. --
-- --
-- GNAT is free software; you can redistribute it and/or modify it under --
-- terms of the GNU General Public License as published by the Free Soft- --
-- ware Foundation; either version 3, or (at your option) any later ver- --
-- sion. GNAT is distributed in the hope that it will be useful, but WITH- --
-- OUT 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 distributed with GNAT; see file COPYING3. If not, go to --
-- http://www.gnu.org/licenses for a complete copy of the license. --
-- --
-- GNAT was originally developed by the GNAT team at New York University. --
-- Extensive contributions were provided by Ada Core Technologies Inc. --
-- --
------------------------------------------------------------------------------
with Atree; use Atree;
with Csets; use Csets;
with Hostparm; use Hostparm;
with Namet; use Namet;
with Opt; use Opt;
with Scans; use Scans;
with Sinput; use Sinput;
with Snames; use Snames;
with Stringt; use Stringt;
with Stylesw; use Stylesw;
with Uintp; use Uintp;
with Urealp; use Urealp;
with Widechar; use Widechar;
pragma Warnings (Off);
-- This package is used also by gnatcoll
with System.CRC32;
with System.UTF_32; use System.UTF_32;
with System.WCh_Con; use System.WCh_Con;
pragma Warnings (On);
package body Scng is
use ASCII;
-- Make control characters visible
Special_Characters : array (Character) of Boolean := (others => False);
-- For characters that are Special token, the value is True
Comment_Is_Token : Boolean := False;
-- True if comments are tokens
End_Of_Line_Is_Token : Boolean := False;
-- True if End_Of_Line is a token
-----------------------
-- Local Subprograms --
-----------------------
procedure Accumulate_Token_Checksum;
pragma Inline (Accumulate_Token_Checksum);
-- Called after each numeric literal and identifier/keyword. For keywords,
-- the token used is Tok_Identifier. This allows detection of additional
-- spaces added in sources when using the builder switch -m.
procedure Accumulate_Checksum (C : Character);
pragma Inline (Accumulate_Checksum);
-- This routine accumulates the checksum given character C. During the
-- scanning of a source file, this routine is called with every character
-- in the source, excluding blanks, and all control characters (except
-- that ESC is included in the checksum). Upper case letters not in string
-- literals are folded by the caller. See Sinput spec for the documentation
-- of the checksum algorithm. Note: checksum values are only used if we
-- generate code, so it is not necessary to worry about making the right
-- sequence of calls in any error situation.
procedure Accumulate_Checksum (C : Char_Code);
pragma Inline (Accumulate_Checksum);
-- This version is identical, except that the argument, C, is a character
-- code value instead of a character. This is used when wide characters
-- are scanned. We use the character code rather than the ASCII characters
-- so that the checksum is independent of wide character encoding method.
procedure Initialize_Checksum;
pragma Inline (Initialize_Checksum);
-- Initialize checksum value
-------------------------
-- Accumulate_Checksum --
-------------------------
procedure Accumulate_Checksum (C : Character) is
begin
System.CRC32.Update (System.CRC32.CRC32 (Checksum), C);
end Accumulate_Checksum;
procedure Accumulate_Checksum (C : Char_Code) is
begin
if C > 16#FFFF# then
Accumulate_Checksum (Character'Val (C / 2 ** 24));
Accumulate_Checksum (Character'Val ((C / 2 ** 16) mod 256));
Accumulate_Checksum (Character'Val ((C / 256) mod 256));
else
Accumulate_Checksum (Character'Val (C / 256));
end if;
Accumulate_Checksum (Character'Val (C mod 256));
end Accumulate_Checksum;
-------------------------------
-- Accumulate_Token_Checksum --
-------------------------------
procedure Accumulate_Token_Checksum is
begin
System.CRC32.Update
(System.CRC32.CRC32 (Checksum),
Character'Val (Token_Type'Pos (Token)));
end Accumulate_Token_Checksum;
-----------------------
-- Check_End_Of_Line --
-----------------------
procedure Check_End_Of_Line is
Len : constant Int :=
Int (Scan_Ptr) -
Int (Current_Line_Start) -
Wide_Char_Byte_Count;
-- Start of processing for Check_End_Of_Line
begin
if Style_Check then
Style.Check_Line_Terminator (Len);
end if;
-- Deal with checking maximum line length
if Style_Check and Style_Check_Max_Line_Length then
Style.Check_Line_Max_Length (Len);
-- If style checking is inactive, check maximum line length against
-- standard value.
elsif Len > Max_Line_Length then
Error_Msg
("this line is too long",
Current_Line_Start + Source_Ptr (Max_Line_Length));
end if;
-- Now one more checking circuit. Normally we are only enforcing a limit
-- of physical characters, with tabs counting as one character. But if
-- after tab expansion we would have a total line length that exceeded
-- 32766, that would really cause trouble, because column positions
-- would exceed the maximum we allow for a column count. Note: the limit
-- is 32766 rather than 32767, since we use a value of 32767 for special
-- purposes (see Sinput). Now we really do not want to go messing with
-- tabs in the normal case, so what we do is to check for a line that
-- has more than 4096 physical characters. Any shorter line could not
-- be a problem, even if it was all tabs.
if Len >= 4096 then
declare
Col : Natural;
Ptr : Source_Ptr;
begin
Col := 1;
Ptr := Current_Line_Start;
loop
exit when Ptr = Scan_Ptr;
if Source (Ptr) = ASCII.HT then
Col := (Col - 1 + 8) / 8 * 8 + 1;
else
Col := Col + 1;
end if;
if Col > 32766 then
Error_Msg
("this line is longer than 32766 characters",
Current_Line_Start);
raise Unrecoverable_Error;
end if;
Ptr := Ptr + 1;
end loop;
end;
end if;
-- Reset wide character byte count for next line
Wide_Char_Byte_Count := 0;
end Check_End_Of_Line;
----------------------------
-- Determine_Token_Casing --
----------------------------
function Determine_Token_Casing return Casing_Type is
begin
return Determine_Casing (Source (Token_Ptr .. Scan_Ptr - 1));
end Determine_Token_Casing;
-------------------------
-- Initialize_Checksum --
-------------------------
procedure Initialize_Checksum is
begin
System.CRC32.Initialize (System.CRC32.CRC32 (Checksum));
end Initialize_Checksum;
------------------------
-- Initialize_Scanner --
------------------------
procedure Initialize_Scanner (Index : Source_File_Index) is
begin
-- Establish reserved words
Scans.Initialize_Ada_Keywords;
-- Initialize scan control variables
Current_Source_File := Index;
Source := Source_Text (Current_Source_File);
Scan_Ptr := Source_First (Current_Source_File);
Token := No_Token;
Token_Ptr := Scan_Ptr;
Current_Line_Start := Scan_Ptr;
Token_Node := Empty;
Token_Name := No_Name;
Start_Column := Set_Start_Column;
First_Non_Blank_Location := Scan_Ptr;
Initialize_Checksum;
Wide_Char_Byte_Count := 0;
-- Do not call Scan, otherwise the License stuff does not work in Scn
end Initialize_Scanner;
------------------------------
-- Reset_Special_Characters --
------------------------------
procedure Reset_Special_Characters is
begin
Special_Characters := (others => False);
end Reset_Special_Characters;
----------
-- Scan --
----------
procedure Scan is
Start_Of_Comment : Source_Ptr;
-- Record start of comment position
Underline_Found : Boolean;
-- During scanning of an identifier, set to True if last character
-- scanned was an underline or other punctuation character. This
-- is used to flag the error of two underlines/punctuations in a
-- row or ending an identifier with a underline/punctuation. Here
-- punctuation means any UTF_32 character in the Unicode category
-- Punctuation,Connector.
Wptr : Source_Ptr;
-- Used to remember start of last wide character scanned
function Double_Char_Token (C : Character) return Boolean;
-- This function is used for double character tokens like := or <>. It
-- checks if the character following Source (Scan_Ptr) is C, and if so
-- bumps Scan_Ptr past the pair of characters and returns True. A space
-- between the two characters is also recognized with an appropriate
-- error message being issued. If C is not present, False is returned.
-- Note that Double_Char_Token can only be used for tokens defined in
-- the Ada syntax (it's use for error cases like && is not appropriate
-- since we do not want a junk message for a case like &-space-&).
procedure Error_Illegal_Character;
-- Give illegal character error, Scan_Ptr points to character. On
-- return, Scan_Ptr is bumped past the illegal character.
procedure Error_Illegal_Wide_Character;
-- Give illegal wide character message. On return, Scan_Ptr is bumped
-- past the illegal character, which may still leave us pointing to
-- junk, not much we can do if the escape sequence is messed up.
procedure Error_No_Double_Underline;
-- Signal error of two underline or punctuation characters in a row.
-- Called with Scan_Ptr pointing to second underline/punctuation char.
procedure Nlit;
-- This is the procedure for scanning out numeric literals. On entry,
-- Scan_Ptr points to the digit that starts the numeric literal (the
-- checksum for this character has not been accumulated yet). On return
-- Scan_Ptr points past the last character of the numeric literal, Token
-- and Token_Node are set appropriately, and the checksum is updated.
procedure Slit;
-- This is the procedure for scanning out string literals. On entry,
-- Scan_Ptr points to the opening string quote (the checksum for this
-- character has not been accumulated yet). On return Scan_Ptr points
-- past the closing quote of the string literal, Token and Token_Node
-- are set appropriately, and the checksum is updated.
procedure Skip_Other_Format_Characters;
-- Skips past any "other format" category characters at the current
-- cursor location (does not skip past spaces or any other characters).
function Start_Of_Wide_Character return Boolean;
-- Returns True if the scan pointer is pointing to the start of a wide
-- character sequence, does not modify the scan pointer in any case.
-----------------------
-- Double_Char_Token --
-----------------------
function Double_Char_Token (C : Character) return Boolean is
begin
if Source (Scan_Ptr + 1) = C then
Accumulate_Checksum (C);
Scan_Ptr := Scan_Ptr + 2;
return True;
elsif Source (Scan_Ptr + 1) = ' '
and then Source (Scan_Ptr + 2) = C
then
Scan_Ptr := Scan_Ptr + 1;
Error_Msg_S -- CODEFIX
("no space allowed here");
Scan_Ptr := Scan_Ptr + 2;
return True;
else
return False;
end if;
end Double_Char_Token;
-----------------------------
-- Error_Illegal_Character --
-----------------------------
procedure Error_Illegal_Character is
begin
Error_Msg_S ("illegal character");
Scan_Ptr := Scan_Ptr + 1;
end Error_Illegal_Character;
----------------------------------
-- Error_Illegal_Wide_Character --
----------------------------------
procedure Error_Illegal_Wide_Character is
begin
Scan_Ptr := Scan_Ptr + 1;
Error_Msg ("illegal wide character", Wptr);
end Error_Illegal_Wide_Character;
-------------------------------
-- Error_No_Double_Underline --
-------------------------------
procedure Error_No_Double_Underline is
begin
Underline_Found := False;
-- There are four cases, and we special case the messages
if Source (Scan_Ptr) = '_' then
if Source (Scan_Ptr - 1) = '_' then
Error_Msg_S -- CODEFIX
("two consecutive underlines not permitted");
else
Error_Msg_S ("underline cannot follow punctuation character");
end if;
else
if Source (Scan_Ptr - 1) = '_' then
Error_Msg_S ("punctuation character cannot follow underline");
else
Error_Msg_S
("two consecutive punctuation characters not permitted");
end if;
end if;
end Error_No_Double_Underline;
----------
-- Nlit --
----------
procedure Nlit is
C : Character;
-- Current source program character
Base_Char : Character;
-- Either # or : (character at start of based number)
Base : Int;
-- Value of base
UI_Base : Uint;
-- Value of base in Uint format
UI_Int_Value : Uint;
-- Value of integer scanned by Scan_Integer in Uint format
UI_Num_Value : Uint;
-- Value of integer in numeric value being scanned
Scale : Int;
-- Scale value for real literal
UI_Scale : Uint;
-- Scale in Uint format
Exponent_Is_Negative : Boolean;
-- Set true for negative exponent
Extended_Digit_Value : Int;
-- Extended digit value
Point_Scanned : Boolean;
-- Flag for decimal point scanned in numeric literal
-----------------------
-- Local Subprograms --
-----------------------
procedure Error_Digit_Expected;
-- Signal error of bad digit, Scan_Ptr points to the location at
-- which the digit was expected on input, and is unchanged on return.
procedure Scan_Integer;
-- Scan integer literal. On entry, Scan_Ptr points to a digit, on
-- exit Scan_Ptr points past the last character of the integer.
--
-- For each digit encountered, UI_Int_Value is multiplied by 10, and
-- the value of the digit added to the result. In addition, the value
-- in Scale is decremented by one for each actual digit scanned.
--------------------------
-- Error_Digit_Expected --
--------------------------
procedure Error_Digit_Expected is
begin
Error_Msg_S ("digit expected");
end Error_Digit_Expected;
------------------
-- Scan_Integer --
------------------
procedure Scan_Integer is
C : Character;
-- Next character scanned
begin
C := Source (Scan_Ptr);
-- Loop through digits (allowing underlines)
loop
Accumulate_Checksum (C);
UI_Int_Value :=
UI_Int_Value * 10 + (Character'Pos (C) - Character'Pos ('0'));
Scan_Ptr := Scan_Ptr + 1;
Scale := Scale - 1;
C := Source (Scan_Ptr);
-- Case of underline encountered
if C = '_' then
-- We do not accumulate the '_' in the checksum, so that
-- 1_234 is equivalent to 1234, and does not trigger
-- compilation for "minimal recompilation" (gnatmake -m).
loop
Scan_Ptr := Scan_Ptr + 1;
C := Source (Scan_Ptr);
exit when C /= '_';
Error_No_Double_Underline;
end loop;
if C not in '0' .. '9' then
Error_Digit_Expected;
exit;
end if;
else
exit when C not in '0' .. '9';
end if;
end loop;
end Scan_Integer;
-- Start of processing for Nlit
begin
Base := 10;
UI_Base := Uint_10;
UI_Int_Value := Uint_0;
Based_Literal_Uses_Colon := False;
Scale := 0;
Scan_Integer;
Point_Scanned := False;
UI_Num_Value := UI_Int_Value;
-- Various possibilities now for continuing the literal are period,
-- E/e (for exponent), or :/# (for based literal).
Scale := 0;
C := Source (Scan_Ptr);
if C = '.' then
-- Scan out point, but do not scan past .. which is a range
-- sequence, and must not be eaten up scanning a numeric literal.
while C = '.' and then Source (Scan_Ptr + 1) /= '.' loop
Accumulate_Checksum ('.');
if Point_Scanned then
Error_Msg_S ("duplicate point ignored");
end if;
Point_Scanned := True;
Scan_Ptr := Scan_Ptr + 1;
C := Source (Scan_Ptr);
if C not in '0' .. '9' then
Error_Msg
("real literal cannot end with point", Scan_Ptr - 1);
else
Scan_Integer;
UI_Num_Value := UI_Int_Value;
end if;
end loop;
-- Based literal case. The base is the value we already scanned.
-- In the case of colon, we insist that the following character
-- is indeed an extended digit or a period. This catches a number
-- of common errors, as well as catching the well known tricky
-- bug otherwise arising from "x : integer range 1 .. 10:= 6;"
elsif C = '#'
or else (C = ':' and then
(Source (Scan_Ptr + 1) = '.'
or else
Source (Scan_Ptr + 1) in '0' .. '9'
or else
Source (Scan_Ptr + 1) in 'A' .. 'Z'
or else
Source (Scan_Ptr + 1) in 'a' .. 'z'))
then
Accumulate_Checksum (C);
Base_Char := C;
UI_Base := UI_Int_Value;
if Base_Char = ':' then
Based_Literal_Uses_Colon := True;
end if;
if UI_Base < 2 or else UI_Base > 16 then
Error_Msg_SC ("base not 2-16");
UI_Base := Uint_16;
end if;
Base := UI_To_Int (UI_Base);
Scan_Ptr := Scan_Ptr + 1;
-- Scan out extended integer [. integer]
C := Source (Scan_Ptr);
UI_Int_Value := Uint_0;
Scale := 0;
loop
if C in '0' .. '9' then
Accumulate_Checksum (C);
Extended_Digit_Value :=
Int'(Character'Pos (C)) - Int'(Character'Pos ('0'));
elsif C in 'A' .. 'F' then
Accumulate_Checksum (Character'Val (Character'Pos (C) + 32));
Extended_Digit_Value :=
Int'(Character'Pos (C)) - Int'(Character'Pos ('A')) + 10;
elsif C in 'a' .. 'f' then
Accumulate_Checksum (C);
Extended_Digit_Value :=
Int'(Character'Pos (C)) - Int'(Character'Pos ('a')) + 10;
else
Error_Msg_S ("extended digit expected");
exit;
end if;
if Extended_Digit_Value >= Base then
Error_Msg_S ("digit '>= base");
end if;
UI_Int_Value := UI_Int_Value * UI_Base + Extended_Digit_Value;
Scale := Scale - 1;
Scan_Ptr := Scan_Ptr + 1;
C := Source (Scan_Ptr);
if C = '_' then
loop
Accumulate_Checksum ('_');
Scan_Ptr := Scan_Ptr + 1;
C := Source (Scan_Ptr);
exit when C /= '_';
Error_No_Double_Underline;
end loop;
elsif C = '.' then
Accumulate_Checksum ('.');
if Point_Scanned then
Error_Msg_S ("duplicate point ignored");
end if;
Scan_Ptr := Scan_Ptr + 1;
C := Source (Scan_Ptr);
Point_Scanned := True;
Scale := 0;
elsif C = Base_Char then
Accumulate_Checksum (C);
Scan_Ptr := Scan_Ptr + 1;
exit;
elsif C = '#' or else C = ':' then
Error_Msg_S ("based number delimiters must match");
Scan_Ptr := Scan_Ptr + 1;
exit;
elsif not Identifier_Char (C) then
if Base_Char = '#' then
Error_Msg_S -- CODEFIX
("missing '#");
else
Error_Msg_S -- CODEFIX
("missing ':");
end if;
exit;
end if;
end loop;
UI_Num_Value := UI_Int_Value;
end if;
-- Scan out exponent
if not Point_Scanned then
Scale := 0;
UI_Scale := Uint_0;
else
UI_Scale := UI_From_Int (Scale);
end if;
if Source (Scan_Ptr) = 'e' or else Source (Scan_Ptr) = 'E' then
Accumulate_Checksum ('e');
Scan_Ptr := Scan_Ptr + 1;
Exponent_Is_Negative := False;
if Source (Scan_Ptr) = '+' then
Accumulate_Checksum ('+');
Scan_Ptr := Scan_Ptr + 1;
elsif Source (Scan_Ptr) = '-' then
Accumulate_Checksum ('-');
if not Point_Scanned then
Error_Msg_S
("negative exponent not allowed for integer literal");
else
Exponent_Is_Negative := True;
end if;
Scan_Ptr := Scan_Ptr + 1;
end if;
UI_Int_Value := Uint_0;
if Source (Scan_Ptr) in '0' .. '9' then
Scan_Integer;
else
Error_Digit_Expected;
end if;
if Exponent_Is_Negative then
UI_Scale := UI_Scale - UI_Int_Value;
else
UI_Scale := UI_Scale + UI_Int_Value;
end if;
end if;
-- Case of real literal to be returned
if Point_Scanned then
Token := Tok_Real_Literal;
Real_Literal_Value :=
UR_From_Components (
Num => UI_Num_Value,
Den => -UI_Scale,
Rbase => Base);
-- Case of integer literal to be returned
else
Token := Tok_Integer_Literal;
if UI_Scale = 0 then
Int_Literal_Value := UI_Num_Value;
-- Avoid doing possibly expensive calculations in cases like
-- parsing 163E800_000# when semantics will not be done anyway.
-- This is especially useful when parsing garbled input.
elsif Operating_Mode /= Check_Syntax
and then (Serious_Errors_Detected = 0 or else Try_Semantics)
then
Int_Literal_Value := UI_Num_Value * UI_Base ** UI_Scale;
else
Int_Literal_Value := No_Uint;
end if;
end if;
Accumulate_Token_Checksum;
end Nlit;
----------
-- Slit --
----------
procedure Slit is
Delimiter : Character;
-- Delimiter (first character of string)
C : Character;
-- Current source program character
Code : Char_Code;
-- Current character code value
Err : Boolean;
-- Error flag for Scan_Wide call
String_Start : Source_Ptr;
-- Point to first character of string
procedure Error_Bad_String_Char;
-- Signal bad character in string/character literal. On entry
-- Scan_Ptr points to the improper character encountered during the
-- scan. Scan_Ptr is not modified, so it still points to the bad
-- character on return.
procedure Error_Unterminated_String;
-- Procedure called if a line terminator character is encountered
-- during scanning a string, meaning that the string is not properly
-- terminated.
procedure Set_String;
-- Procedure used to distinguish between string and operator symbol.
-- On entry the string has been scanned out, and its characters start
-- at Token_Ptr and end one character before Scan_Ptr. On exit Token
-- is set to Tok_String_Literal/Tok_Operator_Symbol as appropriate,
-- and Token_Node is appropriately initialized. In addition, in the
-- operator symbol case, Token_Name is appropriately set, and the
-- flags [Wide_]Wide_Character_Found are set appropriately.
---------------------------
-- Error_Bad_String_Char --
---------------------------
procedure Error_Bad_String_Char is
C : constant Character := Source (Scan_Ptr);
begin
if C = HT then
Error_Msg_S ("horizontal tab not allowed in string");
elsif C = VT or else C = FF then
Error_Msg_S ("format effector not allowed in string");
elsif C in Upper_Half_Character then
Error_Msg_S ("(Ada 83) upper half character not allowed");
else
Error_Msg_S ("control character not allowed in string");
end if;
end Error_Bad_String_Char;
-------------------------------
-- Error_Unterminated_String --
-------------------------------
procedure Error_Unterminated_String is
S : Source_Ptr;
begin
-- An interesting little refinement. Consider the following
-- examples:
-- A := "this is an unterminated string;
-- A := "this is an unterminated string &
-- P(A, "this is a parameter that didn't get terminated);
-- P("this is a parameter that didn't get terminated, A);
-- We fiddle a little to do slightly better placement in these
-- cases also if there is white space at the end of the line we
-- place the flag at the start of this white space, not at the
-- end. Note that we only have to test for blanks, since tabs
-- aren't allowed in strings in the first place and would have
-- caused an error message.
-- Two more cases that we treat specially are:
-- A := "this string uses the wrong terminator'
-- A := "this string uses the wrong terminator' &
-- In these cases we give a different error message as well
-- We actually reposition the scan pointer to the point where we
-- place the flag in these cases, since it seems a better bet on
-- the original intention.
while Source (Scan_Ptr - 1) = ' '
or else Source (Scan_Ptr - 1) = '&'
loop
Scan_Ptr := Scan_Ptr - 1;
Unstore_String_Char;
end loop;
-- Check for case of incorrect string terminator, but single quote
-- is not considered incorrect if the opening terminator misused
-- a single quote (error message already given).
if Delimiter /= '''
and then Source (Scan_Ptr - 1) = '''
then
Unstore_String_Char;
Error_Msg
("incorrect string terminator character", Scan_Ptr - 1);
return;
end if;
-- Backup over semicolon or right-paren/semicolon sequence
if Source (Scan_Ptr - 1) = ';' then
Scan_Ptr := Scan_Ptr - 1;
Unstore_String_Char;
if Source (Scan_Ptr - 1) = ')' then
Scan_Ptr := Scan_Ptr - 1;
Unstore_String_Char;
end if;
end if;
-- See if there is a comma in the string, if so, guess that
-- the first comma terminates the string.
S := String_Start;
while S < Scan_Ptr loop
if Source (S) = ',' then
while Scan_Ptr > S loop
Scan_Ptr := Scan_Ptr - 1;
Unstore_String_Char;
end loop;
exit;
end if;
S := S + 1;
end loop;
-- Now we have adjusted the scan pointer, give message
Error_Msg_S -- CODEFIX
("missing string quote");
end Error_Unterminated_String;
----------------
-- Set_String --
----------------
procedure Set_String is
Slen : constant Int := Int (Scan_Ptr - Token_Ptr - 2);
C1 : Character;
C2 : Character;
C3 : Character;
begin
-- Token_Name is currently set to Error_Name. The following
-- section of code resets Token_Name to the proper Name_Op_xx
-- value if the string is a valid operator symbol, otherwise it is
-- left set to Error_Name.
if Slen = 1 then
C1 := Source (Token_Ptr + 1);
case C1 is
when '=' =>
Token_Name := Name_Op_Eq;
when '>' =>
Token_Name := Name_Op_Gt;
when '<' =>
Token_Name := Name_Op_Lt;
when '+' =>
Token_Name := Name_Op_Add;
when '-' =>
Token_Name := Name_Op_Subtract;
when '&' =>
Token_Name := Name_Op_Concat;
when '*' =>
Token_Name := Name_Op_Multiply;
when '/' =>
Token_Name := Name_Op_Divide;
when others =>
null;
end case;
elsif Slen = 2 then
C1 := Source (Token_Ptr + 1);
C2 := Source (Token_Ptr + 2);
if C1 = '*' and then C2 = '*' then
Token_Name := Name_Op_Expon;
elsif C2 = '=' then
if C1 = '/' then
Token_Name := Name_Op_Ne;
elsif C1 = '<' then
Token_Name := Name_Op_Le;
elsif C1 = '>' then
Token_Name := Name_Op_Ge;
end if;
elsif (C1 = 'O' or else C1 = 'o') and then -- OR
(C2 = 'R' or else C2 = 'r')
then
Token_Name := Name_Op_Or;
end if;
elsif Slen = 3 then
C1 := Source (Token_Ptr + 1);
C2 := Source (Token_Ptr + 2);
C3 := Source (Token_Ptr + 3);
if (C1 = 'A' or else C1 = 'a') and then -- AND
(C2 = 'N' or else C2 = 'n') and then
(C3 = 'D' or else C3 = 'd')
then
Token_Name := Name_Op_And;
elsif (C1 = 'A' or else C1 = 'a') and then -- ABS
(C2 = 'B' or else C2 = 'b') and then
(C3 = 'S' or else C3 = 's')
then
Token_Name := Name_Op_Abs;
elsif (C1 = 'M' or else C1 = 'm') and then -- MOD
(C2 = 'O' or else C2 = 'o') and then
(C3 = 'D' or else C3 = 'd')
then
Token_Name := Name_Op_Mod;
elsif (C1 = 'N' or else C1 = 'n') and then -- NOT
(C2 = 'O' or else C2 = 'o') and then
(C3 = 'T' or else C3 = 't')
then
Token_Name := Name_Op_Not;
elsif (C1 = 'R' or else C1 = 'r') and then -- REM
(C2 = 'E' or else C2 = 'e') and then
(C3 = 'M' or else C3 = 'm')
then
Token_Name := Name_Op_Rem;
elsif (C1 = 'X' or else C1 = 'x') and then -- XOR
(C2 = 'O' or else C2 = 'o') and then
(C3 = 'R' or else C3 = 'r')
then
Token_Name := Name_Op_Xor;
end if;
end if;
-- If it is an operator symbol, then Token_Name is set. If it is
-- some other string value, then Token_Name still contains
-- Error_Name.
if Token_Name = Error_Name then
Token := Tok_String_Literal;
else
Token := Tok_Operator_Symbol;
end if;
end Set_String;
-- Start of processing for Slit
begin
-- On entry, Scan_Ptr points to the opening character of the string
-- which is either a percent, double quote, or apostrophe (single
-- quote). The latter case is an error detected by the character
-- literal circuit.
String_Start := Scan_Ptr;
Delimiter := Source (Scan_Ptr);
Accumulate_Checksum (Delimiter);
Start_String;
Wide_Character_Found := False;
Wide_Wide_Character_Found := False;
Scan_Ptr := Scan_Ptr + 1;
-- Loop to scan out characters of string literal
loop
C := Source (Scan_Ptr);
if C = Delimiter then
Accumulate_Checksum (C);
Scan_Ptr := Scan_Ptr + 1;
exit when Source (Scan_Ptr) /= Delimiter;
Code := Get_Char_Code (C);
Accumulate_Checksum (C);
Scan_Ptr := Scan_Ptr + 1;
else
if C = '"' and then Delimiter = '%' then
Error_Msg_S
("quote not allowed in percent delimited string");
Code := Get_Char_Code (C);
Scan_Ptr := Scan_Ptr + 1;
elsif Start_Of_Wide_Character then
Wptr := Scan_Ptr;
Scan_Wide (Source, Scan_Ptr, Code, Err);
if Err then
Error_Illegal_Wide_Character;
Code := Get_Char_Code (' ');
end if;
Accumulate_Checksum (Code);
-- In Ada 95 mode we allow any wide characters in a string
-- but in Ada 2005, the set of characters allowed has been
-- restricted to graphic characters.
if Ada_Version >= Ada_2005
and then Is_UTF_32_Non_Graphic (UTF_32 (Code))
then
Error_Msg
("(Ada 2005) non-graphic character not permitted " &
"in string literal", Wptr);
end if;
else
Accumulate_Checksum (C);
if C not in Graphic_Character then
if C in Line_Terminator then
Error_Unterminated_String;
exit;
elsif C in Upper_Half_Character then
if Ada_Version = Ada_83 then
Error_Bad_String_Char;
end if;
else
Error_Bad_String_Char;
end if;
end if;
Code := Get_Char_Code (C);
Scan_Ptr := Scan_Ptr + 1;
end if;
end if;
Store_String_Char (Code);
if not In_Character_Range (Code) then
if In_Wide_Character_Range (Code) then
Wide_Character_Found := True;
else
Wide_Wide_Character_Found := True;
end if;
end if;
end loop;
String_Literal_Id := End_String;
Set_String;
return;
end Slit;
----------------------------------
-- Skip_Other_Format_Characters --
----------------------------------
procedure Skip_Other_Format_Characters is
P : Source_Ptr;
Code : Char_Code;
Err : Boolean;
begin
while Start_Of_Wide_Character loop
P := Scan_Ptr;
Scan_Wide (Source, Scan_Ptr, Code, Err);
if not Is_UTF_32_Other (UTF_32 (Code)) then
Scan_Ptr := P;
return;
end if;
end loop;
end Skip_Other_Format_Characters;
-----------------------------
-- Start_Of_Wide_Character --
-----------------------------
function Start_Of_Wide_Character return Boolean is
C : constant Character := Source (Scan_Ptr);
begin
-- ESC encoding method with ESC present
if C = ESC
and then Wide_Character_Encoding_Method in WC_ESC_Encoding_Method
then
return True;
-- Upper half character with upper half encoding
elsif C in Upper_Half_Character and then Upper_Half_Encoding then
return True;
-- Brackets encoding
elsif C = '['
and then Source (Scan_Ptr + 1) = '"'
and then Identifier_Char (Source (Scan_Ptr + 2))
then
return True;
-- Not the start of a wide character
else
return False;
end if;
end Start_Of_Wide_Character;
-- Start of processing for Scan
begin
Prev_Token := Token;
Prev_Token_Ptr := Token_Ptr;
Token_Name := Error_Name;
-- The following loop runs more than once only if a format effector
-- (tab, vertical tab, form feed, line feed, carriage return) is
-- encountered and skipped, or some error situation, such as an
-- illegal character, is encountered.
<<Scan_Next_Character>>
loop
-- Skip past blanks, loop is opened up for speed
while Source (Scan_Ptr) = ' ' loop
if Source (Scan_Ptr + 1) /= ' ' then
Scan_Ptr := Scan_Ptr + 1;
exit;
end if;
if Source (Scan_Ptr + 2) /= ' ' then
Scan_Ptr := Scan_Ptr + 2;
exit;
end if;
if Source (Scan_Ptr + 3) /= ' ' then
Scan_Ptr := Scan_Ptr + 3;
exit;
end if;
if Source (Scan_Ptr + 4) /= ' ' then
Scan_Ptr := Scan_Ptr + 4;
exit;
end if;
if Source (Scan_Ptr + 5) /= ' ' then
Scan_Ptr := Scan_Ptr + 5;
exit;
end if;
if Source (Scan_Ptr + 6) /= ' ' then
Scan_Ptr := Scan_Ptr + 6;
exit;
end if;
if Source (Scan_Ptr + 7) /= ' ' then
Scan_Ptr := Scan_Ptr + 7;
exit;
end if;
Scan_Ptr := Scan_Ptr + 8;
end loop;
-- We are now at a non-blank character, which is the first character
-- of the token we will scan, and hence the value of Token_Ptr.
Token_Ptr := Scan_Ptr;
-- Here begins the main case statement which transfers control on the
-- basis of the non-blank character we have encountered.
case Source (Scan_Ptr) is
-- Line terminator characters
when CR | LF | FF | VT =>
goto Scan_Line_Terminator;
-- Horizontal tab, just skip past it
when HT =>
if Style_Check then
Style.Check_HT;
end if;
Scan_Ptr := Scan_Ptr + 1;
-- End of file character, treated as an end of file only if it is
-- the last character in the buffer, otherwise it is ignored.
when EOF =>
if Scan_Ptr = Source_Last (Current_Source_File) then
Check_End_Of_Line;
if Style_Check then
Style.Check_EOF;
end if;
Token := Tok_EOF;
return;
else
Scan_Ptr := Scan_Ptr + 1;
end if;
-- Ampersand
when '&' =>
Accumulate_Checksum ('&');
if Source (Scan_Ptr + 1) = '&' then
Error_Msg_S -- CODEFIX
("'&'& should be `AND THEN`");
Scan_Ptr := Scan_Ptr + 2;
Token := Tok_And;
return;
else
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Ampersand;
return;
end if;
when '@' =>
if Ada_Version < Ada_2020 then
Error_Msg ("target_name is an Ada 202x feature", Scan_Ptr);
Scan_Ptr := Scan_Ptr + 1;
else
-- AI12-0125-03 : @ is target_name
Accumulate_Checksum ('@');
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_At_Sign;
return;
end if;
-- Asterisk (can be multiplication operator or double asterisk which
-- is the exponentiation compound delimiter).
when '*' =>
Accumulate_Checksum ('*');
if Source (Scan_Ptr + 1) = '*' then
Accumulate_Checksum ('*');
Scan_Ptr := Scan_Ptr + 2;
Token := Tok_Double_Asterisk;
return;
else
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Asterisk;
return;
end if;
-- Colon, which can either be an isolated colon, or part of an
-- assignment compound delimiter.
when ':' =>
Accumulate_Checksum (':');
if Double_Char_Token ('=') then
Token := Tok_Colon_Equal;
if Style_Check then
Style.Check_Colon_Equal;
end if;
return;
elsif Source (Scan_Ptr + 1) = '-'
and then Source (Scan_Ptr + 2) /= '-'
then
Token := Tok_Colon_Equal;
Error_Msg -- CODEFIX
(":- should be :=", Scan_Ptr);
Scan_Ptr := Scan_Ptr + 2;
return;
else
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Colon;
if Style_Check then
Style.Check_Colon;
end if;
return;
end if;
-- Left parenthesis
when '(' =>
Accumulate_Checksum ('(');
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Left_Paren;
if Style_Check then
Style.Check_Left_Paren;
end if;
return;
-- Left bracket
when '[' =>
-- [] under -gnatX is an aggregate notation and the special
-- wide character notation becomes unsupported since the two
-- are ambiguous.
if Extensions_Allowed then
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Left_Bracket;
return;
elsif Source (Scan_Ptr + 1) = '"' then
goto Scan_Wide_Character;
else
Error_Msg_S ("illegal character, replaced by ""(""");
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Left_Paren;
return;
end if;
-- Left brace
when '{' =>
Error_Msg_S ("illegal character, replaced by ""(""");
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Left_Paren;
return;
-- Comma
when ',' =>
Accumulate_Checksum (',');
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Comma;
if Style_Check then
Style.Check_Comma;
end if;
return;
-- Dot, which is either an isolated period, or part of a double dot
-- compound delimiter sequence. We also check for the case of a
-- digit following the period, to give a better error message.
when '.' =>
Accumulate_Checksum ('.');
if Double_Char_Token ('.') then
Token := Tok_Dot_Dot;
if Style_Check then
Style.Check_Dot_Dot;
end if;
return;
elsif Source (Scan_Ptr + 1) in '0' .. '9' then
Error_Msg_S ("numeric literal cannot start with point");
Scan_Ptr := Scan_Ptr + 1;
else
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Dot;
return;
end if;
-- Equal, which can either be an equality operator, or part of the
-- arrow (=>) compound delimiter.
when '=' =>
Accumulate_Checksum ('=');
if Double_Char_Token ('>') then
Token := Tok_Arrow;
if Style_Check then
Style.Check_Arrow (Inside_Depends);
end if;
return;
elsif Source (Scan_Ptr + 1) = '=' then
Error_Msg_S -- CODEFIX
("== should be =");
Scan_Ptr := Scan_Ptr + 1;
end if;
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Equal;
return;
-- Greater than, which can be a greater than operator, greater than
-- or equal operator, or first character of a right label bracket.
when '>' =>
Accumulate_Checksum ('>');
if Double_Char_Token ('=') then
Token := Tok_Greater_Equal;
return;
elsif Double_Char_Token ('>') then
Token := Tok_Greater_Greater;
return;
else
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Greater;
return;
end if;
-- Less than, which can be a less than operator, less than or equal
-- operator, or the first character of a left label bracket, or the
-- first character of a box (<>) compound delimiter.
when '<' =>
Accumulate_Checksum ('<');
if Double_Char_Token ('=') then
Token := Tok_Less_Equal;
return;
elsif Double_Char_Token ('>') then
Token := Tok_Box;
if Style_Check then
Style.Check_Box;
end if;
return;
elsif Double_Char_Token ('<') then
Token := Tok_Less_Less;
return;
else
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Less;
return;
end if;
-- Minus, which is either a subtraction operator, or the first
-- character of double minus starting a comment
when '-' => Minus_Case : begin
if Source (Scan_Ptr + 1) = '>' then
Error_Msg_S ("invalid token");
Scan_Ptr := Scan_Ptr + 2;
Token := Tok_Arrow;
return;
elsif Source (Scan_Ptr + 1) /= '-' then
Accumulate_Checksum ('-');
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Minus;
return;
-- Comment
else -- Source (Scan_Ptr + 1) = '-' then
if Style_Check then
Style.Check_Comment;
end if;
Scan_Ptr := Scan_Ptr + 2;
-- If we are in preprocessor mode with Replace_In_Comments set,
-- then we return the "--" as a token on its own.
if Replace_In_Comments then
Token := Tok_Comment;
return;
end if;
-- Otherwise scan out the comment
Start_Of_Comment := Scan_Ptr;
-- Loop to scan comment (this loop runs more than once only if
-- a horizontal tab or other non-graphic character is scanned)
loop
-- Scan to non graphic character (opened up for speed)
-- Note that we just eat left brackets, which means that
-- bracket notation cannot be used for end of line
-- characters in comments. This seems a reasonable choice,
-- since no one would ever use brackets notation in a real
-- program in this situation, and if we allow brackets
-- notation, we forbid some valid comments which contain a
-- brackets sequence that happens to match an end of line
-- character.
loop
exit when Source (Scan_Ptr) not in Graphic_Character;
Scan_Ptr := Scan_Ptr + 1;
exit when Source (Scan_Ptr) not in Graphic_Character;
Scan_Ptr := Scan_Ptr + 1;
exit when Source (Scan_Ptr) not in Graphic_Character;
Scan_Ptr := Scan_Ptr + 1;
exit when Source (Scan_Ptr) not in Graphic_Character;
Scan_Ptr := Scan_Ptr + 1;
exit when Source (Scan_Ptr) not in Graphic_Character;
Scan_Ptr := Scan_Ptr + 1;
end loop;
-- Keep going if horizontal tab
if Source (Scan_Ptr) = HT then
if Style_Check then
Style.Check_HT;
end if;
Scan_Ptr := Scan_Ptr + 1;
-- Terminate scan of comment if line terminator
elsif Source (Scan_Ptr) in Line_Terminator then
exit;
-- Terminate scan of comment if end of file encountered
-- (embedded EOF character or real last character in file)
elsif Source (Scan_Ptr) = EOF then
exit;
-- If we have a wide character, we have to scan it out,
-- because it might be a legitimate line terminator
elsif Start_Of_Wide_Character then
declare
Wptr : constant Source_Ptr := Scan_Ptr;
Code : Char_Code;
Err : Boolean;
begin
Scan_Wide (Source, Scan_Ptr, Code, Err);
-- If not well formed wide character, then just skip
-- past it and ignore it.
if Err then
Scan_Ptr := Wptr + 1;
-- If UTF_32 terminator, terminate comment scan
elsif Is_UTF_32_Line_Terminator (UTF_32 (Code)) then
Scan_Ptr := Wptr;
exit;
end if;
end;
-- Keep going if character in 80-FF range, or is ESC. These
-- characters are allowed in comments by RM-2.1(1), 2.7(2).
-- They are allowed even in Ada 83 mode according to the
-- approved AI. ESC was added to the AI in June 93.
elsif Source (Scan_Ptr) in Upper_Half_Character
or else Source (Scan_Ptr) = ESC
then
Scan_Ptr := Scan_Ptr + 1;
-- Otherwise we have an illegal comment character, ignore
-- this error in relaxed semantics mode.
else
if Relaxed_RM_Semantics then
Scan_Ptr := Scan_Ptr + 1;
else
Error_Illegal_Character;
end if;
end if;
end loop;
-- Note that, except when comments are tokens, we do NOT
-- execute a return here, instead we fall through to reexecute
-- the scan loop to look for a token.
if Comment_Is_Token then
Name_Len := Integer (Scan_Ptr - Start_Of_Comment);
Name_Buffer (1 .. Name_Len) :=
String (Source (Start_Of_Comment .. Scan_Ptr - 1));
Comment_Id := Name_Find;
Token := Tok_Comment;
return;
end if;
end if;
end Minus_Case;
-- Double quote or percent starting a string literal
when '"' | '%' =>
Slit;
Post_Scan;
return;
-- Apostrophe. This can either be the start of a character literal,
-- or an isolated apostrophe used in a qualified expression or an
-- attribute. In the following:
-- A := CHARACTER'('A');
-- the first apostrophe is treated as an isolated apostrophe, and the
-- second one is treated as the start of the character literal 'A'.
-- Note that RM-2.2(7) does not require a separator between "'" and
-- "(" in the above, so we cannot use lookahead to distinguish the
-- cases; we use look-back instead. Analysis of the grammar shows
-- that some tokens can be followed by an apostrophe, and some by a
-- character literal, but none by both. Some cannot be followed by
-- either, so it doesn't matter what we do in those cases, except to
-- get good error behavior.
when ''' => Char_Literal_Case : declare
Code : Char_Code;
Err : Boolean;
begin
Accumulate_Checksum (''');
Scan_Ptr := Scan_Ptr + 1;
-- Distinguish between apostrophe and character literal. It's an
-- apostrophe if the previous token is one of the following.
-- Reserved words are included for things like A.all'Address and
-- T'Digits'Img. Strings literals are included for things like
-- "abs"'Address. Other literals are included to give better error
-- behavior for illegal cases like 123'Img.
--
-- In Ada 2020, a target name (i.e. @) is a valid prefix of an
-- attribute, and functions like a name.
if Prev_Token = Tok_All
or else Prev_Token = Tok_At_Sign
or else Prev_Token = Tok_Delta
or else Prev_Token = Tok_Digits
or else Prev_Token = Tok_Identifier
or else Prev_Token = Tok_Project
or else Prev_Token = Tok_Right_Paren
or else Prev_Token = Tok_Right_Bracket
or else Prev_Token in Token_Class_Literal
then
Token := Tok_Apostrophe;
if Style_Check then
Style.Check_Apostrophe;
end if;
return;
-- Otherwise the apostrophe starts a character literal
else
-- Case of wide character literal
if Start_Of_Wide_Character then
Wptr := Scan_Ptr;
Scan_Wide (Source, Scan_Ptr, Code, Err);
Accumulate_Checksum (Code);
if Err then
Error_Illegal_Wide_Character;
Code := Character'Pos (' ');
-- In Ada 95 mode we allow any wide character in a character
-- literal, but in Ada 2005, the set of characters allowed
-- is restricted to graphic characters.
elsif Ada_Version >= Ada_2005
and then Is_UTF_32_Non_Graphic (UTF_32 (Code))
then
Error_Msg -- CODEFIX????
("(Ada 2005) non-graphic character not permitted " &
"in character literal", Wptr);
end if;
if Source (Scan_Ptr) /= ''' then
Error_Msg_S ("missing apostrophe");
else
Scan_Ptr := Scan_Ptr + 1;
end if;
-- If we do not find a closing quote in the expected place then
-- assume that we have a misguided attempt at a string literal.
-- However, if previous token is RANGE, then we return an
-- apostrophe instead since this gives better error recovery
elsif Source (Scan_Ptr + 1) /= ''' then
if Prev_Token = Tok_Range then
Token := Tok_Apostrophe;
return;
else
Scan_Ptr := Scan_Ptr - 1;
Error_Msg_S
("strings are delimited by double quote character");
Slit;
Post_Scan;
return;
end if;
-- Otherwise we have a (non-wide) character literal
else
Accumulate_Checksum (Source (Scan_Ptr));
if Source (Scan_Ptr) not in Graphic_Character then
if Source (Scan_Ptr) in Upper_Half_Character then
if Ada_Version = Ada_83 then
Error_Illegal_Character;
end if;
else
Error_Illegal_Character;
end if;
end if;
Code := Get_Char_Code (Source (Scan_Ptr));
Scan_Ptr := Scan_Ptr + 2;
end if;
-- Fall through here with Scan_Ptr updated past the closing
-- quote, and Code set to the Char_Code value for the literal
Accumulate_Checksum (''');
Token := Tok_Char_Literal;
Set_Character_Literal_Name (Code);
Token_Name := Name_Find;
Character_Code := Code;
Post_Scan;
return;
end if;
end Char_Literal_Case;
-- Right parenthesis
when ')' =>
Accumulate_Checksum (')');
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Right_Paren;
if Style_Check then
Style.Check_Right_Paren;
end if;
return;
-- Right bracket or right brace, treated as right paren but proper
-- aggregate delimiter in Ada 2020.
when ']' | '}' =>
if Ada_Version >= Ada_2020 then
Token := Tok_Right_Bracket;
else
Error_Msg_S ("illegal character, replaced by "")""");
Token := Tok_Right_Paren;
end if;
Scan_Ptr := Scan_Ptr + 1;
return;
-- Slash (can be division operator or first character of not equal)
when '/' =>
Accumulate_Checksum ('/');
if Double_Char_Token ('=') then
Token := Tok_Not_Equal;
return;
else
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Slash;
return;
end if;
-- Semicolon
when ';' =>
Accumulate_Checksum (';');
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Semicolon;
if Style_Check then
Style.Check_Semicolon;
end if;
return;
-- Vertical bar
when '|' => Vertical_Bar_Case : begin
Accumulate_Checksum ('|');
-- Special check for || to give nice message
if Source (Scan_Ptr + 1) = '|' then
Error_Msg_S -- CODEFIX
("""'|'|"" should be `OR ELSE`");
Scan_Ptr := Scan_Ptr + 2;
Token := Tok_Or;
return;
else
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Vertical_Bar;
if Style_Check then
Style.Check_Vertical_Bar;
end if;
Post_Scan;
return;
end if;
end Vertical_Bar_Case;
-- Exclamation, replacement character for vertical bar
when '!' => Exclamation_Case : begin
Accumulate_Checksum ('!');
if Source (Scan_Ptr + 1) = '=' then
Error_Msg_S -- CODEFIX
("'!= should be /=");
Scan_Ptr := Scan_Ptr + 2;
Token := Tok_Not_Equal;
return;
else
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Vertical_Bar;
Post_Scan;
return;
end if;
end Exclamation_Case;
-- Plus
when '+' => Plus_Case : begin
Accumulate_Checksum ('+');
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Plus;
return;
end Plus_Case;
-- Digits starting a numeric literal
when '0' .. '9' =>
-- First a bit of a scan ahead to see if we have a case of an
-- identifier starting with a digit (remembering exponent case).
declare
C : constant Character := Source (Scan_Ptr + 1);
begin
-- OK literal if digit followed by digit or underscore
if C in '0' .. '9' or else C = '_' then
null;
-- OK literal if digit not followed by identifier char
elsif not Identifier_Char (C) then
null;
-- OK literal if digit followed by e/E followed by digit/sign.
-- We also allow underscore after the E, which is an error, but
-- better handled by Nlit than deciding this is an identifier.
elsif (C = 'e' or else C = 'E')
and then (Source (Scan_Ptr + 2) in '0' .. '9'
or else Source (Scan_Ptr + 2) = '+'
or else Source (Scan_Ptr + 2) = '-'
or else Source (Scan_Ptr + 2) = '_')
then
null;
-- Here we have what really looks like an identifier that
-- starts with a digit, so give error msg.
else
Error_Msg_S ("identifier may not start with digit");
Name_Len := 1;
Underline_Found := False;
Name_Buffer (1) := Source (Scan_Ptr);
Accumulate_Checksum (Name_Buffer (1));
Scan_Ptr := Scan_Ptr + 1;
goto Scan_Identifier;
end if;
end;
-- Here we have an OK integer literal
Nlit;
-- Check for proper delimiter, ignoring other format characters
Skip_Other_Format_Characters;
if Identifier_Char (Source (Scan_Ptr)) then
Error_Msg_S
("delimiter required between literal and identifier");
end if;
Post_Scan;
return;
-- Lower case letters
when 'a' .. 'z' =>
Name_Len := 1;
Underline_Found := False;
Name_Buffer (1) := Source (Scan_Ptr);
Accumulate_Checksum (Name_Buffer (1));
Scan_Ptr := Scan_Ptr + 1;
goto Scan_Identifier;
-- Upper case letters
when 'A' .. 'Z' =>
Name_Len := 1;
Underline_Found := False;
Name_Buffer (1) :=
Character'Val (Character'Pos (Source (Scan_Ptr)) + 32);
Accumulate_Checksum (Name_Buffer (1));
Scan_Ptr := Scan_Ptr + 1;
goto Scan_Identifier;
-- Underline character
when '_' =>
if Special_Characters ('_') then
Token_Ptr := Scan_Ptr;
Scan_Ptr := Scan_Ptr + 1;
Token := Tok_Special;
Special_Character := '_';
return;
end if;
Error_Msg_S ("identifier cannot start with underline");
Name_Len := 1;
Name_Buffer (1) := '_';
Scan_Ptr := Scan_Ptr + 1;
Underline_Found := False;
goto Scan_Identifier;
-- Space (not possible, because we scanned past blanks)
when ' ' =>
raise Program_Error;
-- Characters in top half of ASCII 8-bit chart
when Upper_Half_Character =>
-- Wide character case
if Upper_Half_Encoding then
goto Scan_Wide_Character;
-- Otherwise we have OK Latin-1 character
else
-- Upper half characters may possibly be identifier letters
-- but can never be digits, so Identifier_Char can be used to
-- test for a valid start of identifier character.
if Identifier_Char (Source (Scan_Ptr)) then
Name_Len := 0;
Underline_Found := False;
goto Scan_Identifier;
else
Error_Illegal_Character;
end if;
end if;
when ESC =>
-- ESC character, possible start of identifier if wide characters
-- using ESC encoding are allowed in identifiers, which we can
-- tell by looking at the Identifier_Char flag for ESC, which is
-- only true if these conditions are met. In Ada 2005 mode, may
-- also be valid UTF_32 space or line terminator character.
if Identifier_Char (ESC) then
Name_Len := 0;
goto Scan_Wide_Character;
else
Error_Illegal_Character;
end if;
-- Invalid control characters
when ACK
| ASCII.SO
| BEL
| BS
| CAN
| DC1
| DC2
| DC3
| DC4
| DEL
| DLE
| EM
| ENQ
| EOT
| ETB
| ETX
| FS
| GS
| NAK
| NUL
| RS
| SI
| SOH
| STX
| SYN
| US
=>
Error_Illegal_Character;
-- Invalid graphic characters
-- Note that '@' is handled elsewhere, because following AI12-125
-- it denotes the target_name of an assignment.
when '#' | '$' | '?' | '`' | '\' | '^' | '~' =>
-- If Set_Special_Character has been called for this character,
-- set Scans.Special_Character and return a Special token.
if Special_Characters (Source (Scan_Ptr)) then
Token_Ptr := Scan_Ptr;
Token := Tok_Special;
Special_Character := Source (Scan_Ptr);
Scan_Ptr := Scan_Ptr + 1;
return;
-- Check for something looking like a preprocessor directive
elsif Source (Scan_Ptr) = '#'
and then (Source (Scan_Ptr + 1 .. Scan_Ptr + 2) = "if"
or else
Source (Scan_Ptr + 1 .. Scan_Ptr + 5) = "elsif"
or else
Source (Scan_Ptr + 1 .. Scan_Ptr + 4) = "else"
or else
Source (Scan_Ptr + 1 .. Scan_Ptr + 3) = "end")
then
Error_Msg_S
("preprocessor directive ignored, preprocessor not active");
-- Skip to end of line
loop
if Source (Scan_Ptr) in Graphic_Character
or else
Source (Scan_Ptr) = HT
then
Scan_Ptr := Scan_Ptr + 1;
-- Done if line terminator or EOF
elsif Source (Scan_Ptr) in Line_Terminator
or else
Source (Scan_Ptr) = EOF
then
exit;
-- If we have a wide character, we have to scan it out,
-- because it might be a legitimate line terminator
elsif Start_Of_Wide_Character then
declare
Wptr : constant Source_Ptr := Scan_Ptr;
Code : Char_Code;
Err : Boolean;
begin
Scan_Wide (Source, Scan_Ptr, Code, Err);
-- If not well formed wide character, then just skip
-- past it and ignore it.
if Err then
Scan_Ptr := Wptr + 1;
-- If UTF_32 terminator, terminate comment scan
elsif Is_UTF_32_Line_Terminator (UTF_32 (Code)) then
Scan_Ptr := Wptr;
exit;
end if;
end;
-- Else keep going (don't worry about bad comment chars
-- in this context, we just want to find the end of line.
else
Scan_Ptr := Scan_Ptr + 1;
end if;
end loop;
-- Otherwise, this is an illegal character
else
Error_Illegal_Character;
end if;
-- End switch on non-blank character
end case;
-- End loop past format effectors. The exit from this loop is by
-- executing a return statement following completion of token scan
-- (control never falls out of this loop to the code that follows).
end loop;
pragma Assert (False);
-- Wide_Character scanning routine. On entry we have encountered the
-- initial character of a wide character sequence.
<<Scan_Wide_Character>>
declare
Code : Char_Code;
Cat : Category;
Err : Boolean;
begin
Wptr := Scan_Ptr;
Scan_Wide (Source, Scan_Ptr, Code, Err);
-- If bad wide character, signal error and continue scan
if Err then
Error_Illegal_Wide_Character;
goto Scan_Next_Character;
end if;
Cat := Get_Category (UTF_32 (Code));
-- If OK letter, reset scan ptr and go scan identifier
if Is_UTF_32_Letter (Cat) then
Scan_Ptr := Wptr;
Name_Len := 0;
Underline_Found := False;
goto Scan_Identifier;
-- If OK wide space, ignore and keep scanning (we do not include
-- any ignored spaces in checksum)
elsif Is_UTF_32_Space (Cat) then
goto Scan_Next_Character;
-- If other format character, ignore and keep scanning (again we
-- do not include in the checksum) (this is for AI-0079).
elsif Is_UTF_32_Other (Cat) then
goto Scan_Next_Character;
-- If OK wide line terminator, terminate current line
elsif Is_UTF_32_Line_Terminator (UTF_32 (Code)) then
Scan_Ptr := Wptr;
goto Scan_Line_Terminator;
-- Punctuation is an error (at start of identifier)
elsif Is_UTF_32_Punctuation (Cat) then
Error_Msg ("identifier cannot start with punctuation", Wptr);
Scan_Ptr := Wptr;
Name_Len := 0;
Underline_Found := False;
goto Scan_Identifier;
-- Mark character is an error (at start of identifier)
elsif Is_UTF_32_Mark (Cat) then
Error_Msg ("identifier cannot start with mark character", Wptr);
Scan_Ptr := Wptr;
Name_Len := 0;
Underline_Found := False;
goto Scan_Identifier;
-- Extended digit character is an error. Could be bad start of
-- identifier or bad literal. Not worth doing too much to try to
-- distinguish these cases, but we will do a little bit.
elsif Is_UTF_32_Digit (Cat) then
Error_Msg
("identifier cannot start with digit character", Wptr);
Scan_Ptr := Wptr;
Name_Len := 0;
Underline_Found := False;
goto Scan_Identifier;
-- All other wide characters are illegal here
else
Error_Illegal_Wide_Character;
goto Scan_Next_Character;
end if;
end;
-- Routine to scan line terminator. On entry Scan_Ptr points to a
-- character which is one of FF,LR,CR,VT, or one of the wide characters
-- that is treated as a line terminator.
<<Scan_Line_Terminator>>
-- Check line too long
Check_End_Of_Line;
-- Set Token_Ptr, if End_Of_Line is a token, for the case when it is
-- a physical line.
if End_Of_Line_Is_Token then
Token_Ptr := Scan_Ptr;
end if;
declare
Physical : Boolean;
begin
Skip_Line_Terminators (Scan_Ptr, Physical);
-- If we are at start of physical line, update scan pointers to
-- reflect the start of the new line.
if Physical then
Current_Line_Start := Scan_Ptr;
Start_Column := Set_Start_Column;
First_Non_Blank_Location := Scan_Ptr;
-- If End_Of_Line is a token, we return it as it is a
-- physical line.
if End_Of_Line_Is_Token then
Token := Tok_End_Of_Line;
return;
end if;
end if;
end;
goto Scan_Next_Character;
-- Identifier scanning routine. On entry, some initial characters of
-- the identifier may have already been stored in Name_Buffer. If so,
-- Name_Len has the number of characters stored, otherwise Name_Len is
-- set to zero on entry. Underline_Found is also set False on entry.
<<Scan_Identifier>>
-- This loop scans as fast as possible past lower half letters and
-- digits, which we expect to be the most common characters.
loop
if Source (Scan_Ptr) in 'a' .. 'z'
or else Source (Scan_Ptr) in '0' .. '9'
then
Name_Buffer (Name_Len + 1) := Source (Scan_Ptr);
Accumulate_Checksum (Source (Scan_Ptr));
elsif Source (Scan_Ptr) in 'A' .. 'Z' then
Name_Buffer (Name_Len + 1) :=
Character'Val (Character'Pos (Source (Scan_Ptr)) + 32);
Accumulate_Checksum (Name_Buffer (Name_Len + 1));
else
exit;
end if;
Underline_Found := False;
Scan_Ptr := Scan_Ptr + 1;
Name_Len := Name_Len + 1;
end loop;
-- If we fall through, then we have encountered either an underline
-- character, or an extended identifier character (i.e. one from the
-- upper half), or a wide character, or an identifier terminator. The
-- initial test speeds us up in the most common case where we have
-- an identifier terminator. Note that ESC is an identifier character
-- only if a wide character encoding method that uses ESC encoding
-- is active, so if we find an ESC character we know that we have a
-- wide character.
if Identifier_Char (Source (Scan_Ptr))
or else (Source (Scan_Ptr) in Upper_Half_Character
and then Upper_Half_Encoding)
then
-- Case of underline
if Source (Scan_Ptr) = '_' then
Accumulate_Checksum ('_');
if Underline_Found then
Error_No_Double_Underline;
else
Underline_Found := True;
Name_Len := Name_Len + 1;
Name_Buffer (Name_Len) := '_';
end if;
Scan_Ptr := Scan_Ptr + 1;
goto Scan_Identifier;
-- Upper half character
elsif Source (Scan_Ptr) in Upper_Half_Character
and then not Upper_Half_Encoding
then
Accumulate_Checksum (Source (Scan_Ptr));
Store_Encoded_Character
(Get_Char_Code (Fold_Lower (Source (Scan_Ptr))));
Scan_Ptr := Scan_Ptr + 1;
Underline_Found := False;
goto Scan_Identifier;
-- Left bracket not followed by a quote terminates an identifier.
-- This is an error, but we don't want to give a junk error msg
-- about wide characters in this case.
elsif Source (Scan_Ptr) = '['
and then Source (Scan_Ptr + 1) /= '"'
then
null;
-- We know we have a wide character encoding here (the current
-- character is either ESC, left bracket, or an upper half
-- character depending on the encoding method).
else
-- Scan out the wide character and insert the appropriate
-- encoding into the name table entry for the identifier.
declare
Code : Char_Code;
Err : Boolean;
Chr : Character;
Cat : Category;
begin
Wptr := Scan_Ptr;
Scan_Wide (Source, Scan_Ptr, Code, Err);
-- If error, signal error
if Err then
Error_Illegal_Wide_Character;
-- If the character scanned is a normal identifier
-- character, then we treat it that way.
elsif In_Character_Range (Code)
and then Identifier_Char (Get_Character (Code))
then
Chr := Get_Character (Code);
Accumulate_Checksum (Chr);
Store_Encoded_Character
(Get_Char_Code (Fold_Lower (Chr)));
Underline_Found := False;
-- Here if not a normal identifier character
else
Cat := Get_Category (UTF_32 (Code));
-- Wide character in Unicode category "Other, Format"
-- is not accepted in an identifier. This is because it
-- it is considered a security risk (AI-0091).
-- However, it is OK for such a character to appear at
-- the end of an identifier.
if Is_UTF_32_Other (Cat) then
if not Identifier_Char (Source (Scan_Ptr)) then
goto Scan_Identifier_Complete;
else
Error_Msg
("identifier cannot contain other_format "
& "character", Wptr);
goto Scan_Identifier;
end if;
-- Wide character in category Separator,Space terminates
elsif Is_UTF_32_Space (Cat) then
goto Scan_Identifier_Complete;
end if;
-- Here if wide character is part of the identifier
-- Make sure we are allowing wide characters in
-- identifiers. Note that we allow wide character
-- notation for an OK identifier character. This in
-- particular allows bracket or other notation to be
-- used for upper half letters.
-- Wide characters are always allowed in Ada 2005
if Identifier_Character_Set /= 'w'
and then Ada_Version < Ada_2005
then
Error_Msg
("wide character not allowed in identifier", Wptr);
end if;
-- AI12-0004: An identifier shall only contain characters
-- that may be present in Normalization Form KC.
if not Is_UTF_32_NFKC (UTF_32 (Code)) then
Error_Msg
("invalid wide character in identifier", Wptr);
-- If OK letter, store it folding to upper case. Note
-- that we include the folded letter in the checksum.
elsif Is_UTF_32_Letter (Cat) then
Code :=
Char_Code (UTF_32_To_Upper_Case (UTF_32 (Code)));
Accumulate_Checksum (Code);
Store_Encoded_Character (Code);
Underline_Found := False;
-- If OK extended digit or mark, then store it
elsif Is_UTF_32_Digit (Cat)
or else Is_UTF_32_Mark (Cat)
then
Accumulate_Checksum (Code);
Store_Encoded_Character (Code);
Underline_Found := False;
-- Wide punctuation is also stored, but counts as an
-- underline character for error checking purposes.
elsif Is_UTF_32_Punctuation (Cat) then
Accumulate_Checksum (Code);
if Underline_Found then
declare
Cend : constant Source_Ptr := Scan_Ptr;
begin
Scan_Ptr := Wptr;
Error_No_Double_Underline;
Scan_Ptr := Cend;
end;
else
Store_Encoded_Character (Code);
Underline_Found := True;
end if;
-- Any other wide character is not acceptable
else
Error_Msg
("invalid wide character in identifier", Wptr);
end if;
end if;
goto Scan_Identifier;
end;
end if;
end if;
-- Scan of identifier is complete. The identifier is stored in
-- Name_Buffer, and Scan_Ptr points past the last character.
<<Scan_Identifier_Complete>>
Token_Name := Name_Find;
-- Check for identifier ending with underline or punctuation char
if Underline_Found then
Underline_Found := False;
if Source (Scan_Ptr - 1) = '_' then
Error_Msg
("identifier cannot end with underline", Scan_Ptr - 1);
else
Error_Msg
("identifier cannot end with punctuation character", Wptr);
end if;
end if;
-- We will assume it is an identifier, not a keyword, so that the
-- checksum is independent of the Ada version.
Token := Tok_Identifier;
-- Here is where we check if it was a keyword
if Is_Keyword_Name (Token_Name) then
Accumulate_Token_Checksum;
Token := Token_Type'Val (Get_Name_Table_Byte (Token_Name));
-- See Exp_Put_Image for documentation of Tagged_Seen
if Token = Tok_Tagged then
Tagged_Seen := True;
end if;
-- Keyword style checks
if Style_Check then
-- Deal with possible style check for non-lower case keyword,
-- but we don't treat ACCESS, DELTA, DIGITS, RANGE as keywords
-- for this purpose if they appear as attribute designators.
-- Actually we only check the first character for speed.
-- Ada 2005 (AI-284): Do not apply the style check in case of
-- "pragma Interface"
-- Ada 2005 (AI-340): Do not apply the style check in case of
-- MOD attribute.
if Source (Token_Ptr) <= 'Z'
and then (Prev_Token /= Tok_Apostrophe
or else
(Token /= Tok_Access and then
Token /= Tok_Delta and then
Token /= Tok_Digits and then
Token /= Tok_Mod and then
Token /= Tok_Range))
and then (Token /= Tok_Interface
or else
(Token = Tok_Interface
and then Prev_Token /= Tok_Pragma))
then
Style.Non_Lower_Case_Keyword;
end if;
-- Check THEN/ELSE style rules. These do not apply to AND THEN
-- or OR ELSE, and do not apply in if expressions.
if (Token = Tok_Then and then Prev_Token /= Tok_And)
or else
(Token = Tok_Else and then Prev_Token /= Tok_Or)
then
if Inside_If_Expression = 0 then
Style.Check_Separate_Stmt_Lines;
end if;
end if;
end if;
-- We must reset Token_Name since this is not an identifier and
-- if we leave Token_Name set, the parser gets confused because
-- it thinks it is dealing with an identifier instead of the
-- corresponding keyword.
Token_Name := No_Name;
return;
-- It is an identifier after all
else
Accumulate_Token_Checksum;
Post_Scan;
end if;
end Scan;
--------------------------
-- Set_Comment_As_Token --
--------------------------
procedure Set_Comment_As_Token (Value : Boolean) is
begin
Comment_Is_Token := Value;
end Set_Comment_As_Token;
------------------------------
-- Set_End_Of_Line_As_Token --
------------------------------
procedure Set_End_Of_Line_As_Token (Value : Boolean) is
begin
End_Of_Line_Is_Token := Value;
end Set_End_Of_Line_As_Token;
---------------------------
-- Set_Special_Character --
---------------------------
procedure Set_Special_Character (C : Character) is
begin
case C is
when '#' | '$' | '_' | '?' | '@' | '`' | '\' | '^' | '~' =>
Special_Characters (C) := True;
when others =>
null;
end case;
end Set_Special_Character;
----------------------
-- Set_Start_Column --
----------------------
-- Note: it seems at first glance a little expensive to compute this value
-- for every source line (since it is certainly not used for all source
-- lines). On the other hand, it doesn't take much more work to skip past
-- the initial white space on the line counting the columns than it would
-- to scan past the white space using the standard scanning circuits.
function Set_Start_Column return Column_Number is
Start_Column : Column_Number := 0;
begin
-- Outer loop scans past horizontal tab characters
Tabs_Loop : loop
-- Inner loop scans past blanks as fast as possible, bumping Scan_Ptr
-- past the blanks and adjusting Start_Column to account for them.
Blanks_Loop : loop
if Source (Scan_Ptr) = ' ' then
if Source (Scan_Ptr + 1) = ' ' then
if Source (Scan_Ptr + 2) = ' ' then
if Source (Scan_Ptr + 3) = ' ' then
if Source (Scan_Ptr + 4) = ' ' then
if Source (Scan_Ptr + 5) = ' ' then
if Source (Scan_Ptr + 6) = ' ' then
Scan_Ptr := Scan_Ptr + 7;
Start_Column := Start_Column + 7;
else
Scan_Ptr := Scan_Ptr + 6;
Start_Column := Start_Column + 6;
exit Blanks_Loop;
end if;
else
Scan_Ptr := Scan_Ptr + 5;
Start_Column := Start_Column + 5;
exit Blanks_Loop;
end if;
else
Scan_Ptr := Scan_Ptr + 4;
Start_Column := Start_Column + 4;
exit Blanks_Loop;
end if;
else
Scan_Ptr := Scan_Ptr + 3;
Start_Column := Start_Column + 3;
exit Blanks_Loop;
end if;
else
Scan_Ptr := Scan_Ptr + 2;
Start_Column := Start_Column + 2;
exit Blanks_Loop;
end if;
else
Scan_Ptr := Scan_Ptr + 1;
Start_Column := Start_Column + 1;
exit Blanks_Loop;
end if;
else
exit Blanks_Loop;
end if;
end loop Blanks_Loop;
-- Outer loop keeps going only if a horizontal tab follows
if Source (Scan_Ptr) = HT then
if Style_Check then
Style.Check_HT;
end if;
Scan_Ptr := Scan_Ptr + 1;
Start_Column := (Start_Column / 8) * 8 + 8;
else
exit Tabs_Loop;
end if;
end loop Tabs_Loop;
return Start_Column;
-- A constraint error can happen only if we have a compiler with checks on
-- and a line with a ludicrous number of tabs or spaces at the start. In
-- such a case, we really don't care if Start_Column is right or not.
exception
when Constraint_Error =>
return Start_Column;
end Set_Start_Column;
end Scng;
|