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
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
|
/*
* Mesa 3-D graphics library
* Version: 6.6
*
* Copyright (C) 1999-2006 Brian Paul All Rights Reserved.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included
* in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
* OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* BRIAN PAUL BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
* AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
/**
* \file grammar.c
* syntax parsing engine
* \author Michal Krol
*/
#ifndef GRAMMAR_PORT_BUILD
#error Do not build this file directly, build your grammar_XXX.c instead, which includes this file
#endif
/*
*/
/*
INTRODUCTION
------------
The task is to check the syntax of an input string. Input string is a stream of ASCII
characters terminated with a null-character ('\0'). Checking it using C language is
difficult and hard to implement without bugs. It is hard to maintain and make changes when
the syntax changes.
This is because of a high redundancy of the C code. Large blocks of code are duplicated with
only small changes. Even use of macros does not solve the problem because macros cannot
erase the complexity of the problem.
The resolution is to create a new language that will be highly oriented to our task. Once
we describe a particular syntax, we are done. We can then focus on the code that implements
the language. The size and complexity of it is relatively small than the code that directly
checks the syntax.
First, we must implement our new language. Here, the language is implemented in C, but it
could also be implemented in any other language. The code is listed below. We must take
a good care that it is bug free. This is simple because the code is simple and clean.
Next, we must describe the syntax of our new language in itself. Once created and checked
manually that it is correct, we can use it to check another scripts.
Note that our new language loading code does not have to check the syntax. It is because we
assume that the script describing itself is correct, and other scripts can be syntactically
checked by the former script. The loading code must only do semantic checking which leads us to
simple resolving references.
THE LANGUAGE
------------
Here I will describe the syntax of the new language (further called "Synek"). It is mainly a
sequence of declarations terminated by a semicolon. The declaration consists of a symbol,
which is an identifier, and its definition. A definition is in turn a sequence of specifiers
connected with ".and" or ".or" operator. These operators cannot be mixed together in a one
definition. Specifier can be a symbol, string, character, character range or a special
keyword ".true" or ".false".
On the very beginning of the script there is a declaration of a root symbol and is in the form:
.syntax <root_symbol>;
The <root_symbol> must be on of the symbols in declaration sequence. The syntax is correct if
the root symbol evaluates to true. A symbol evaluates to true if the definition associated with
the symbol evaluates to true. Definition evaluation depends on the operator used to connect
specifiers in the definition. If ".and" operator is used, definition evaluates to true if and
only if all the specifiers evaluate to true. If ".or" operator is used, definition evalutes to
true if any of the specifiers evaluates to true. If definition contains only one specifier,
it is evaluated as if it was connected with ".true" keyword by ".and" operator.
If specifier is a ".true" keyword, it always evaluates to true.
If specifier is a ".false" keyword, it always evaluates to false. Specifier evaluates to false
when it does not evaluate to true.
Character range specifier is in the form:
'<first_character>' - '<second_character>'
If specifier is a character range, it evaluates to true if character in the stream is greater
or equal to <first_character> and less or equal to <second_character>. In that situation
the stream pointer is advanced to point to next character in the stream. All C-style escape
sequences are supported although trigraph sequences are not. The comparisions are performed
on 8-bit unsigned integers.
Character specifier is in the form:
'<single_character>'
It evaluates to true if the following character range specifier evaluates to true:
'<single_character>' - '<single_character>'
String specifier is in the form:
"<string>"
Let N be the number of characters in <string>. Let <string>[i] designate i-th character in
<string>. Then the string specifier evaluates to true if and only if for i in the range [0, N)
the following character specifier evaluates to true:
'<string>[i]'
If <string>[i] is a quotation mark, '<string>[i]' is replaced with '\<string>[i]'.
Symbol specifier can be optionally preceded by a ".loop" keyword in the form:
.loop <symbol> (1)
where <symbol> is defined as follows:
<symbol> <definition>; (2)
Construction (1) is replaced by the following code:
<symbol$1>
and declaration (2) is replaced by the following:
<symbol$1> <symbol$2> .or .true;
<symbol$2> <symbol> .and <symbol$1>;
<symbol> <definition>;
Synek supports also a register mechanizm. User can, in its SYN file, declare a number of
registers that can be accessed in the syn body. Each reg has its name and a default value.
The register is one byte wide. The C code can change the default value by calling
grammar_set_reg8() with grammar id, register name and a new value. As we know, each rule is
a sequence of specifiers joined with .and or .or operator. And now each specifier can be
prefixed with a condition expression in a form ".if (<reg_name> <operator> <hex_literal>)"
where <operator> can be == or !=. If the condition evaluates to false, the specifier
evaluates to .false. Otherwise it evalutes to the specifier.
ESCAPE SEQUENCES
----------------
Synek supports all escape sequences in character specifiers. The mapping table is listed below.
All occurences of the characters in the first column are replaced with the corresponding
character in the second column.
Escape sequence Represents
------------------------------------------------------------------------------------------------
\a Bell (alert)
\b Backspace
\f Formfeed
\n New line
\r Carriage return
\t Horizontal tab
\v Vertical tab
\' Single quotation mark
\" Double quotation mark
\\ Backslash
\? Literal question mark
\ooo ASCII character in octal notation
\xhhh ASCII character in hexadecimal notation
------------------------------------------------------------------------------------------------
RAISING ERRORS
--------------
Any specifier can be followed by a special construction that is executed when the specifier
evaluates to false. The construction is in the form:
.error <ERROR_TEXT>
<ERROR_TEXT> is an identifier declared earlier by error text declaration. The declaration is
in the form:
.errtext <ERROR_TEXT> "<error_desc>"
When specifier evaluates to false and this construction is present, parsing is stopped
immediately and <error_desc> is returned as a result of parsing. The error position is also
returned and it is meant as an offset from the beggining of the stream to the character that
was valid so far. Example:
(**** syntax script ****)
.syntax program;
.errtext MISSING_SEMICOLON "missing ';'"
program declaration .and .loop space .and ';' .error MISSING_SEMICOLON .and
.loop space .and '\0';
declaration "declare" .and .loop space .and identifier;
space ' ';
(**** sample code ****)
declare foo ,
In the example above checking the sample code will result in error message "missing ';'" and
error position 12. The sample code is not correct. Note the presence of '\0' specifier to
assure that there is no code after semicolon - only spaces.
<error_desc> can optionally contain identifier surrounded by dollar signs $. In such a case,
the identifier and dollar signs are replaced by a string retrieved by invoking symbol with
the identifier name. The starting position is the error position. The lenght of the resulting
string is the position after invoking the symbol.
PRODUCTION
----------
Synek not only checks the syntax but it can also produce (emit) bytes associated with specifiers
that evaluate to true. That is, every specifier and optional error construction can be followed
by a number of emit constructions that are in the form:
.emit <parameter>
<paramater> can be a HEX number, identifier, a star * or a dollar $. HEX number is preceded by
0x or 0X. If <parameter> is an identifier, it must be earlier declared by emit code declaration
in the form:
.emtcode <identifier> <hex_number>
When given specifier evaluates to true, all emits associated with the specifier are output
in order they were declared. A star means that last-read character should be output instead
of constant value. Example:
(**** syntax script ****)
.syntax foobar;
.emtcode WORD_FOO 0x01
.emtcode WORD_BAR 0x02
foobar FOO .emit WORD_FOO .or BAR .emit WORD_BAR .or .true .emit 0x00;
FOO "foo" .and SPACE;
BAR "bar" .and SPACE;
SPACE ' ' .or '\0';
(**** sample text 1 ****)
foo
(**** sample text 2 ****)
foobar
For both samples the result will be one-element array. For first sample text it will be
value 1, for second - 0. Note that every text will be accepted because of presence of
.true as an alternative.
Another example:
(**** syntax script ****)
.syntax declaration;
.emtcode VARIABLE 0x01
declaration "declare" .and .loop space .and
identifier .emit VARIABLE .and (1)
.true .emit 0x00 .and (2)
.loop space .and ';';
space ' ' .or '\t';
identifier .loop id_char .emit *; (3)
id_char 'a'-'z' .or 'A'-'Z' .or '_';
(**** sample code ****)
declare fubar;
In specifier (1) symbol <identifier> is followed by .emit VARIABLE. If it evaluates to
true, VARIABLE constant and then production of the symbol is output. Specifier (2) is used
to terminate the string with null to signal when the string ends. Specifier (3) outputs
all characters that make declared identifier. The result of sample code will be the
following array:
{ 1, 'f', 'u', 'b', 'a', 'r', 0 }
If .emit is followed by dollar $, it means that current position should be output. Current
position is a 32-bit unsigned integer distance from the very beginning of the parsed string to
first character consumed by the specifier associated with the .emit instruction. Current
position is stored in the output buffer in Little-Endian convention (the lowest byte comes
first).
*/
#include <stdio.h>
static void mem_free (void **);
/*
internal error messages
*/
static const byte *OUT_OF_MEMORY = (byte *) "internal error 1001: out of physical memory";
static const byte *UNRESOLVED_REFERENCE = (byte *) "internal error 1002: unresolved reference '$'";
static const byte *INVALID_GRAMMAR_ID = (byte *) "internal error 1003: invalid grammar object";
static const byte *INVALID_REGISTER_NAME = (byte *) "internal error 1004: invalid register name: '$'";
/*static const byte *DUPLICATE_IDENTIFIER = (byte *) "internal error 1005: identifier '$' already defined";*/
static const byte *UNREFERENCED_IDENTIFIER =(byte *) "internal error 1006: unreferenced identifier '$'";
static const byte *error_message = NULL; /* points to one of the error messages above */
static byte *error_param = NULL; /* this is inserted into error_message in place of $ */
static int error_position = -1;
static byte *unknown = (byte *) "???";
static void clear_last_error (void)
{
/* reset error message */
error_message = NULL;
/* free error parameter - if error_param is a "???" don't free it - it's static */
if (error_param != unknown)
mem_free ((void **) (void *) &error_param);
else
error_param = NULL;
/* reset error position */
error_position = -1;
}
static void set_last_error (const byte *msg, byte *param, int pos)
{
/* error message can be set only once */
if (error_message != NULL)
{
mem_free ((void **) (void *) ¶m);
return;
}
error_message = msg;
/* if param is NULL, set error_param to unknown ("???") */
/* note: do not try to strdup the "???" - it may be that we are here because of */
/* out of memory error so strdup can fail */
if (param != NULL)
error_param = param;
else
error_param = unknown;
error_position = pos;
}
/*
memory management routines
*/
static void *mem_alloc (size_t size)
{
void *ptr = grammar_alloc_malloc (size);
if (ptr == NULL)
set_last_error (OUT_OF_MEMORY, NULL, -1);
return ptr;
}
static void *mem_copy (void *dst, const void *src, size_t size)
{
return grammar_memory_copy (dst, src, size);
}
static void mem_free (void **ptr)
{
grammar_alloc_free (*ptr);
*ptr = NULL;
}
static void *mem_realloc (void *ptr, size_t old_size, size_t new_size)
{
void *ptr2 = grammar_alloc_realloc (ptr, old_size, new_size);
if (ptr2 == NULL)
set_last_error (OUT_OF_MEMORY, NULL, -1);
return ptr2;
}
static byte *str_copy_n (byte *dst, const byte *src, size_t max_len)
{
return grammar_string_copy_n (dst, src, max_len);
}
static byte *str_duplicate (const byte *str)
{
byte *new_str = grammar_string_duplicate (str);
if (new_str == NULL)
set_last_error (OUT_OF_MEMORY, NULL, -1);
return new_str;
}
static int str_equal (const byte *str1, const byte *str2)
{
return grammar_string_compare (str1, str2) == 0;
}
static int str_equal_n (const byte *str1, const byte *str2, unsigned int n)
{
return grammar_string_compare_n (str1, str2, n) == 0;
}
static int
str_length (const byte *str)
{
return (int) (grammar_string_length (str));
}
/*
useful macros
*/
#define GRAMMAR_IMPLEMENT_LIST_APPEND(_Ty)\
static void _Ty##_append (_Ty **x, _Ty *nx) {\
while (*x) x = &(**x).next;\
*x = nx;\
}
/*
string to byte map typedef
*/
typedef struct map_byte_
{
byte *key;
byte data;
struct map_byte_ *next;
} map_byte;
static void map_byte_create (map_byte **ma)
{
*ma = (map_byte *) mem_alloc (sizeof (map_byte));
if (*ma)
{
(**ma).key = NULL;
(**ma).data = '\0';
(**ma).next = NULL;
}
}
static void map_byte_destroy (map_byte **ma)
{
if (*ma)
{
map_byte_destroy (&(**ma).next);
mem_free ((void **) &(**ma).key);
mem_free ((void **) ma);
}
}
GRAMMAR_IMPLEMENT_LIST_APPEND(map_byte)
/*
searches the map for the specified key,
returns pointer to the element with the specified key if it exists
returns NULL otherwise
*/
static map_byte *map_byte_locate (map_byte **ma, const byte *key)
{
while (*ma)
{
if (str_equal ((**ma).key, key))
return *ma;
ma = &(**ma).next;
}
set_last_error (UNRESOLVED_REFERENCE, str_duplicate (key), -1);
return NULL;
}
/*
searches the map for specified key,
if the key is matched, *data is filled with data associated with the key,
returns 0 if the key is matched,
returns 1 otherwise
*/
static int map_byte_find (map_byte **ma, const byte *key, byte *data)
{
map_byte *found = map_byte_locate (ma, key);
if (found != NULL)
{
*data = found->data;
return 0;
}
return 1;
}
/*
regbyte context typedef
Each regbyte consists of its name and a default value. These are static and created at
grammar script compile-time, for example the following line:
.regbyte vertex_blend 0x00
adds a new regbyte named "vertex_blend" to the static list and initializes it to 0.
When the script is executed, this regbyte can be accessed by name for read and write. When a
particular regbyte is written, a new regbyte_ctx entry is added to the top of the regbyte_ctx
stack. The new entry contains information abot which regbyte it references and its new value.
When a given regbyte is accessed for read, the stack is searched top-down to find an
entry that references the regbyte. The first matching entry is used to return the current
value it holds. If no entry is found, the default value is returned.
*/
typedef struct regbyte_ctx_
{
map_byte *m_regbyte;
byte m_current_value;
struct regbyte_ctx_ *m_prev;
} regbyte_ctx;
static void regbyte_ctx_create (regbyte_ctx **re)
{
*re = (regbyte_ctx *) mem_alloc (sizeof (regbyte_ctx));
if (*re)
{
(**re).m_regbyte = NULL;
(**re).m_prev = NULL;
}
}
static void regbyte_ctx_destroy (regbyte_ctx **re)
{
if (*re)
{
mem_free ((void **) re);
}
}
static byte regbyte_ctx_extract (regbyte_ctx **re, map_byte *reg)
{
/* first lookup in the register stack */
while (*re != NULL)
{
if ((**re).m_regbyte == reg)
return (**re).m_current_value;
re = &(**re).m_prev;
}
/* if not found - return the default value */
return reg->data;
}
/*
emit type typedef
*/
typedef enum emit_type_
{
et_byte, /* explicit number */
et_stream, /* eaten character */
et_position /* current position */
} emit_type;
/*
emit destination typedef
*/
typedef enum emit_dest_
{
ed_output, /* write to the output buffer */
ed_regbyte /* write a particular regbyte */
} emit_dest;
/*
emit typedef
*/
typedef struct emit_
{
emit_dest m_emit_dest;
emit_type m_emit_type; /* ed_output */
byte m_byte; /* et_byte */
map_byte *m_regbyte; /* ed_regbyte */
byte *m_regname; /* ed_regbyte - temporary */
struct emit_ *m_next;
} emit;
static void emit_create (emit **em)
{
*em = (emit *) mem_alloc (sizeof (emit));
if (*em)
{
(**em).m_emit_dest = ed_output;
(**em).m_emit_type = et_byte;
(**em).m_byte = '\0';
(**em).m_regbyte = NULL;
(**em).m_regname = NULL;
(**em).m_next = NULL;
}
}
static void emit_destroy (emit **em)
{
if (*em)
{
emit_destroy (&(**em).m_next);
mem_free ((void **) &(**em).m_regname);
mem_free ((void **) em);
}
}
static unsigned int emit_size (emit *_E, const char *str)
{
unsigned int n = 0;
while (_E != NULL)
{
if (_E->m_emit_dest == ed_output)
{
if (_E->m_emit_type == et_position)
n += 4; /* position is a 32-bit unsigned integer */
else if (_E->m_emit_type == et_stream) {
n += strlen(str) + 1;
} else
n++;
}
_E = _E->m_next;
}
return n;
}
static int emit_push (emit *_E, byte *_P, const char *str, unsigned int _Pos, regbyte_ctx **_Ctx)
{
while (_E != NULL)
{
if (_E->m_emit_dest == ed_output)
{
if (_E->m_emit_type == et_byte)
*_P++ = _E->m_byte;
else if (_E->m_emit_type == et_stream) {
strcpy(_P, str);
_P += strlen(str) + 1;
} else /* _Em->type == et_position */
{
*_P++ = (byte) (_Pos);
*_P++ = (byte) (_Pos >> 8);
*_P++ = (byte) (_Pos >> 16);
*_P++ = (byte) (_Pos >> 24);
}
}
else
{
regbyte_ctx *new_rbc;
regbyte_ctx_create (&new_rbc);
if (new_rbc == NULL)
return 1;
new_rbc->m_prev = *_Ctx;
new_rbc->m_regbyte = _E->m_regbyte;
*_Ctx = new_rbc;
if (_E->m_emit_type == et_byte)
new_rbc->m_current_value = _E->m_byte;
else if (_E->m_emit_type == et_stream)
new_rbc->m_current_value = str[0];
}
_E = _E->m_next;
}
return 0;
}
/*
error typedef
*/
typedef struct error_
{
byte *m_text;
byte *m_token_name;
struct rule_ *m_token;
} error;
static void error_create (error **er)
{
*er = (error *) mem_alloc (sizeof (error));
if (*er)
{
(**er).m_text = NULL;
(**er).m_token_name = NULL;
(**er).m_token = NULL;
}
}
static void error_destroy (error **er)
{
if (*er)
{
mem_free ((void **) &(**er).m_text);
mem_free ((void **) &(**er).m_token_name);
mem_free ((void **) er);
}
}
struct dict_;
static byte *
error_get_token (error *, struct dict_ *, const byte *, int);
/*
condition operand type typedef
*/
typedef enum cond_oper_type_
{
cot_byte, /* constant 8-bit unsigned integer */
cot_regbyte /* pointer to byte register containing the current value */
} cond_oper_type;
/*
condition operand typedef
*/
typedef struct cond_oper_
{
cond_oper_type m_type;
byte m_byte; /* cot_byte */
map_byte *m_regbyte; /* cot_regbyte */
byte *m_regname; /* cot_regbyte - temporary */
} cond_oper;
/*
condition type typedef
*/
typedef enum cond_type_
{
ct_equal,
ct_not_equal
} cond_type;
/*
condition typedef
*/
typedef struct cond_
{
cond_type m_type;
cond_oper m_operands[2];
} cond;
static void cond_create (cond **co)
{
*co = (cond *) mem_alloc (sizeof (cond));
if (*co)
{
(**co).m_operands[0].m_regname = NULL;
(**co).m_operands[1].m_regname = NULL;
}
}
static void cond_destroy (cond **co)
{
if (*co)
{
mem_free ((void **) &(**co).m_operands[0].m_regname);
mem_free ((void **) &(**co).m_operands[1].m_regname);
mem_free ((void **) co);
}
}
/*
specifier type typedef
*/
typedef enum spec_type_
{
st_false,
st_true,
st_token,
st_byte,
st_byte_range,
st_string,
st_identifier,
st_identifier_loop,
st_debug
} spec_type;
/*
specifier typedef
*/
typedef struct spec_
{
spec_type m_spec_type;
enum sl_pp_token m_token; /* st_token */
byte m_byte[2]; /* st_byte, st_byte_range */
byte *m_string; /* st_string */
struct rule_ *m_rule; /* st_identifier, st_identifier_loop */
emit *m_emits;
error *m_errtext;
cond *m_cond;
struct spec_ *next;
} spec;
static void spec_create (spec **sp)
{
*sp = (spec *) mem_alloc (sizeof (spec));
if (*sp)
{
(**sp).m_spec_type = st_false;
(**sp).m_byte[0] = '\0';
(**sp).m_byte[1] = '\0';
(**sp).m_string = NULL;
(**sp).m_rule = NULL;
(**sp).m_emits = NULL;
(**sp).m_errtext = NULL;
(**sp).m_cond = NULL;
(**sp).next = NULL;
}
}
static void spec_destroy (spec **sp)
{
if (*sp)
{
spec_destroy (&(**sp).next);
emit_destroy (&(**sp).m_emits);
error_destroy (&(**sp).m_errtext);
mem_free ((void **) &(**sp).m_string);
cond_destroy (&(**sp).m_cond);
mem_free ((void **) sp);
}
}
GRAMMAR_IMPLEMENT_LIST_APPEND(spec)
/*
operator typedef
*/
typedef enum oper_
{
op_none,
op_and,
op_or
} oper;
/*
rule typedef
*/
typedef struct rule_
{
oper m_oper;
spec *m_specs;
struct rule_ *next;
int m_referenced;
} rule;
static void rule_create (rule **ru)
{
*ru = (rule *) mem_alloc (sizeof (rule));
if (*ru)
{
(**ru).m_oper = op_none;
(**ru).m_specs = NULL;
(**ru).next = NULL;
(**ru).m_referenced = 0;
}
}
static void rule_destroy (rule **ru)
{
if (*ru)
{
rule_destroy (&(**ru).next);
spec_destroy (&(**ru).m_specs);
mem_free ((void **) ru);
}
}
GRAMMAR_IMPLEMENT_LIST_APPEND(rule)
/*
returns unique grammar id
*/
static grammar next_valid_grammar_id (void)
{
static grammar id = 0;
return ++id;
}
/*
dictionary typedef
*/
typedef struct dict_
{
rule *m_rulez;
rule *m_syntax;
rule *m_string;
map_byte *m_regbytes;
grammar m_id;
struct dict_ *next;
} dict;
static void dict_create (dict **di)
{
*di = (dict *) mem_alloc (sizeof (dict));
if (*di)
{
(**di).m_rulez = NULL;
(**di).m_syntax = NULL;
(**di).m_string = NULL;
(**di).m_regbytes = NULL;
(**di).m_id = next_valid_grammar_id ();
(**di).next = NULL;
}
}
static void dict_destroy (dict **di)
{
if (*di)
{
rule_destroy (&(**di).m_rulez);
map_byte_destroy (&(**di).m_regbytes);
mem_free ((void **) di);
}
}
GRAMMAR_IMPLEMENT_LIST_APPEND(dict)
static void dict_find (dict **di, grammar key, dict **data)
{
while (*di)
{
if ((**di).m_id == key)
{
*data = *di;
return;
}
di = &(**di).next;
}
*data = NULL;
}
static dict *g_dicts = NULL;
/*
byte array typedef
*/
typedef struct barray_
{
byte *data;
unsigned int len;
} barray;
static void barray_create (barray **ba)
{
*ba = (barray *) mem_alloc (sizeof (barray));
if (*ba)
{
(**ba).data = NULL;
(**ba).len = 0;
}
}
static void barray_destroy (barray **ba)
{
if (*ba)
{
mem_free ((void **) &(**ba).data);
mem_free ((void **) ba);
}
}
/*
reallocates byte array to requested size,
returns 0 on success,
returns 1 otherwise
*/
static int barray_resize (barray **ba, unsigned int nlen)
{
byte *new_pointer;
if (nlen == 0)
{
mem_free ((void **) &(**ba).data);
(**ba).data = NULL;
(**ba).len = 0;
return 0;
}
else
{
new_pointer = (byte *) mem_realloc ((**ba).data, (**ba).len * sizeof (byte),
nlen * sizeof (byte));
if (new_pointer)
{
(**ba).data = new_pointer;
(**ba).len = nlen;
return 0;
}
}
return 1;
}
/*
adds byte array pointed by *nb to the end of array pointed by *ba,
returns 0 on success,
returns 1 otherwise
*/
static int barray_append (barray **ba, barray **nb)
{
const unsigned int len = (**ba).len;
if (barray_resize (ba, (**ba).len + (**nb).len))
return 1;
mem_copy ((**ba).data + len, (**nb).data, (**nb).len);
return 0;
}
/*
adds emit chain pointed by em to the end of array pointed by *ba,
returns 0 on success,
returns 1 otherwise
*/
static int barray_push (barray **ba, emit *em, byte c, unsigned int pos, regbyte_ctx **rbc)
{
unsigned int count = emit_size(em, " ");
if (barray_resize (ba, (**ba).len + count))
return 1;
return emit_push (em, (**ba).data + ((**ba).len - count), " ", pos, rbc);
}
/*
byte pool typedef
*/
typedef struct bytepool_
{
byte *_F;
unsigned int _Siz;
} bytepool;
static void bytepool_destroy (bytepool **by)
{
if (*by != NULL)
{
mem_free ((void **) &(**by)._F);
mem_free ((void **) by);
}
}
static void bytepool_create (bytepool **by, int len)
{
*by = (bytepool *) (mem_alloc (sizeof (bytepool)));
if (*by != NULL)
{
(**by)._F = (byte *) (mem_alloc (sizeof (byte) * len));
(**by)._Siz = len;
if ((**by)._F == NULL)
bytepool_destroy (by);
}
}
static int bytepool_reserve (bytepool *by, unsigned int n)
{
byte *_P;
if (n <= by->_Siz)
return 0;
/* byte pool can only grow and at least by doubling its size */
n = n >= by->_Siz * 2 ? n : by->_Siz * 2;
/* reallocate the memory and adjust pointers to the new memory location */
_P = (byte *) (mem_realloc (by->_F, sizeof (byte) * by->_Siz, sizeof (byte) * n));
if (_P != NULL)
{
by->_F = _P;
by->_Siz = n;
return 0;
}
return 1;
}
/*
string to string map typedef
*/
typedef struct map_str_
{
byte *key;
byte *data;
struct map_str_ *next;
} map_str;
static void map_str_create (map_str **ma)
{
*ma = (map_str *) mem_alloc (sizeof (map_str));
if (*ma)
{
(**ma).key = NULL;
(**ma).data = NULL;
(**ma).next = NULL;
}
}
static void map_str_destroy (map_str **ma)
{
if (*ma)
{
map_str_destroy (&(**ma).next);
mem_free ((void **) &(**ma).key);
mem_free ((void **) &(**ma).data);
mem_free ((void **) ma);
}
}
GRAMMAR_IMPLEMENT_LIST_APPEND(map_str)
/*
searches the map for specified key,
if the key is matched, *data is filled with data associated with the key,
returns 0 if the key is matched,
returns 1 otherwise
*/
static int map_str_find (map_str **ma, const byte *key, byte **data)
{
while (*ma)
{
if (str_equal ((**ma).key, key))
{
*data = str_duplicate ((**ma).data);
if (*data == NULL)
return 1;
return 0;
}
ma = &(**ma).next;
}
set_last_error (UNRESOLVED_REFERENCE, str_duplicate (key), -1);
return 1;
}
/*
string to rule map typedef
*/
typedef struct map_rule_
{
byte *key;
rule *data;
struct map_rule_ *next;
} map_rule;
static void map_rule_create (map_rule **ma)
{
*ma = (map_rule *) mem_alloc (sizeof (map_rule));
if (*ma)
{
(**ma).key = NULL;
(**ma).data = NULL;
(**ma).next = NULL;
}
}
static void map_rule_destroy (map_rule **ma)
{
if (*ma)
{
map_rule_destroy (&(**ma).next);
mem_free ((void **) &(**ma).key);
mem_free ((void **) ma);
}
}
GRAMMAR_IMPLEMENT_LIST_APPEND(map_rule)
/*
searches the map for specified key,
if the key is matched, *data is filled with data associated with the key,
returns 0 if the is matched,
returns 1 otherwise
*/
static int map_rule_find (map_rule **ma, const byte *key, rule **data)
{
while (*ma)
{
if (str_equal ((**ma).key, key))
{
*data = (**ma).data;
return 0;
}
ma = &(**ma).next;
}
set_last_error (UNRESOLVED_REFERENCE, str_duplicate (key), -1);
return 1;
}
/*
returns 1 if given character is a white space,
returns 0 otherwise
*/
static int is_space (byte c)
{
return c == ' ' || c == '\t' || c == '\n' || c == '\r';
}
/*
advances text pointer by 1 if character pointed by *text is a space,
returns 1 if a space has been eaten,
returns 0 otherwise
*/
static int eat_space (const byte **text)
{
if (is_space (**text))
{
(*text)++;
return 1;
}
return 0;
}
/*
returns 1 if text points to C-style comment start string,
returns 0 otherwise
*/
static int is_comment_start (const byte *text)
{
return text[0] == '/' && text[1] == '*';
}
/*
advances text pointer to first character after C-style comment block - if any,
returns 1 if C-style comment block has been encountered and eaten,
returns 0 otherwise
*/
static int eat_comment (const byte **text)
{
if (is_comment_start (*text))
{
/* *text points to comment block - skip two characters to enter comment body */
*text += 2;
/* skip any character except consecutive '*' and '/' */
while (!((*text)[0] == '*' && (*text)[1] == '/'))
(*text)++;
/* skip those two terminating characters */
*text += 2;
return 1;
}
return 0;
}
/*
advances text pointer to first character that is neither space nor C-style comment block
*/
static void eat_spaces (const byte **text)
{
while (eat_space (text) || eat_comment (text))
;
}
/*
resizes string pointed by *ptr to successfully add character c to the end of the string,
returns 0 on success,
returns 1 otherwise
*/
static int string_grow (byte **ptr, unsigned int *len, byte c)
{
/* reallocate the string in 16-byte increments */
if ((*len & 0x0F) == 0x0F || *ptr == NULL)
{
byte *tmp = (byte *) mem_realloc (*ptr, ((*len + 1) & ~0x0F) * sizeof (byte),
((*len + 1 + 0x10) & ~0x0F) * sizeof (byte));
if (tmp == NULL)
return 1;
*ptr = tmp;
}
if (c)
{
/* append given character */
(*ptr)[*len] = c;
(*len)++;
}
(*ptr)[*len] = '\0';
return 0;
}
/*
returns 1 if given character is a valid identifier character a-z, A-Z, 0-9 or _
returns 0 otherwise
*/
static int is_identifier (byte c)
{
return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '_';
}
/*
copies characters from *text to *id until non-identifier character is encountered,
assumes that *id points to NULL object - caller is responsible for later freeing the string,
text pointer is advanced to point past the copied identifier,
returns 0 if identifier was successfully copied,
returns 1 otherwise
*/
static int get_identifier (const byte **text, byte **id)
{
const byte *t = *text;
byte *p = NULL;
unsigned int len = 0;
if (string_grow (&p, &len, '\0'))
return 1;
/* loop while next character in buffer is valid for identifiers */
while (is_identifier (*t))
{
if (string_grow (&p, &len, *t++))
{
mem_free ((void **) (void *) &p);
return 1;
}
}
*text = t;
*id = p;
return 0;
}
/*
converts sequence of DEC digits pointed by *text until non-DEC digit is encountered,
advances text pointer past the converted sequence,
returns the converted value
*/
static unsigned int dec_convert (const byte **text)
{
unsigned int value = 0;
while (**text >= '0' && **text <= '9')
{
value = value * 10 + **text - '0';
(*text)++;
}
return value;
}
/*
returns 1 if given character is HEX digit 0-9, A-F or a-f,
returns 0 otherwise
*/
static int is_hex (byte c)
{
return (c >= '0' && c <= '9') || (c >= 'A' && c <= 'F') || (c >= 'a' && c <= 'f');
}
/*
returns value of passed character as if it was HEX digit
*/
static unsigned int hex2dec (byte c)
{
if (c >= '0' && c <= '9')
return c - '0';
if (c >= 'A' && c <= 'F')
return c - 'A' + 10;
return c - 'a' + 10;
}
/*
converts sequence of HEX digits pointed by *text until non-HEX digit is encountered,
advances text pointer past the converted sequence,
returns the converted value
*/
static unsigned int hex_convert (const byte **text)
{
unsigned int value = 0;
while (is_hex (**text))
{
value = value * 0x10 + hex2dec (**text);
(*text)++;
}
return value;
}
/*
returns 1 if given character is OCT digit 0-7,
returns 0 otherwise
*/
static int is_oct (byte c)
{
return c >= '0' && c <= '7';
}
/*
returns value of passed character as if it was OCT digit
*/
static int oct2dec (byte c)
{
return c - '0';
}
static byte get_escape_sequence (const byte **text)
{
int value = 0;
/* skip '\' character */
(*text)++;
switch (*(*text)++)
{
case '\'':
return '\'';
case '"':
return '\"';
case '?':
return '\?';
case '\\':
return '\\';
case 'a':
return '\a';
case 'b':
return '\b';
case 'f':
return '\f';
case 'n':
return '\n';
case 'r':
return '\r';
case 't':
return '\t';
case 'v':
return '\v';
case 'x':
return (byte) hex_convert (text);
}
(*text)--;
if (is_oct (**text))
{
value = oct2dec (*(*text)++);
if (is_oct (**text))
{
value = value * 010 + oct2dec (*(*text)++);
if (is_oct (**text))
value = value * 010 + oct2dec (*(*text)++);
}
}
return (byte) value;
}
/*
copies characters from *text to *str until " or ' character is encountered,
assumes that *str points to NULL object - caller is responsible for later freeing the string,
assumes that *text points to " or ' character that starts the string,
text pointer is advanced to point past the " or ' character,
returns 0 if string was successfully copied,
returns 1 otherwise
*/
static int get_string (const byte **text, byte **str)
{
const byte *t = *text;
byte *p = NULL;
unsigned int len = 0;
byte term_char;
if (string_grow (&p, &len, '\0'))
return 1;
/* read " or ' character that starts the string */
term_char = *t++;
/* while next character is not the terminating character */
while (*t && *t != term_char)
{
byte c;
if (*t == '\\')
c = get_escape_sequence (&t);
else
c = *t++;
if (string_grow (&p, &len, c))
{
mem_free ((void **) (void *) &p);
return 1;
}
}
/* skip " or ' character that ends the string */
t++;
*text = t;
*str = p;
return 0;
}
/*
gets emit code, the syntax is:
".emtcode" " " <symbol> " " (("0x" | "0X") <hex_value>) | <dec_value> | <character>
assumes that *text already points to <symbol>,
returns 0 if emit code is successfully read,
returns 1 otherwise
*/
static int get_emtcode (const byte **text, map_byte **ma)
{
const byte *t = *text;
map_byte *m = NULL;
map_byte_create (&m);
if (m == NULL)
return 1;
if (get_identifier (&t, &m->key))
{
map_byte_destroy (&m);
return 1;
}
eat_spaces (&t);
if (*t == '\'')
{
byte *c;
if (get_string (&t, &c))
{
map_byte_destroy (&m);
return 1;
}
m->data = (byte) c[0];
mem_free ((void **) (void *) &c);
}
else if (t[0] == '0' && (t[1] == 'x' || t[1] == 'X'))
{
/* skip HEX "0x" or "0X" prefix */
t += 2;
m->data = (byte) hex_convert (&t);
}
else
{
m->data = (byte) dec_convert (&t);
}
eat_spaces (&t);
*text = t;
*ma = m;
return 0;
}
/*
gets regbyte declaration, the syntax is:
".regbyte" " " <symbol> " " (("0x" | "0X") <hex_value>) | <dec_value> | <character>
assumes that *text already points to <symbol>,
returns 0 if regbyte is successfully read,
returns 1 otherwise
*/
static int get_regbyte (const byte **text, map_byte **ma)
{
/* pass it to the emtcode parser as it has the same syntax starting at <symbol> */
return get_emtcode (text, ma);
}
/*
returns 0 on success,
returns 1 otherwise
*/
static int get_errtext (const byte **text, map_str **ma)
{
const byte *t = *text;
map_str *m = NULL;
map_str_create (&m);
if (m == NULL)
return 1;
if (get_identifier (&t, &m->key))
{
map_str_destroy (&m);
return 1;
}
eat_spaces (&t);
if (get_string (&t, &m->data))
{
map_str_destroy (&m);
return 1;
}
eat_spaces (&t);
*text = t;
*ma = m;
return 0;
}
/*
returns 0 on success,
returns 1 otherwise,
*/
static int get_error (const byte **text, error **er, map_str *maps)
{
const byte *t = *text;
byte *temp = NULL;
if (*t != '.')
return 0;
t++;
if (get_identifier (&t, &temp))
return 1;
eat_spaces (&t);
if (!str_equal ((byte *) "error", temp))
{
mem_free ((void **) (void *) &temp);
return 0;
}
mem_free ((void **) (void *) &temp);
error_create (er);
if (*er == NULL)
return 1;
if (*t == '\"')
{
if (get_string (&t, &(**er).m_text))
{
error_destroy (er);
return 1;
}
eat_spaces (&t);
}
else
{
if (get_identifier (&t, &temp))
{
error_destroy (er);
return 1;
}
eat_spaces (&t);
if (map_str_find (&maps, temp, &(**er).m_text))
{
mem_free ((void **) (void *) &temp);
error_destroy (er);
return 1;
}
mem_free ((void **) (void *) &temp);
}
/* try to extract "token" from "...$token$..." */
{
byte *processed = NULL;
unsigned int len = 0;
int i = 0;
if (string_grow (&processed, &len, '\0'))
{
error_destroy (er);
return 1;
}
while (i < str_length ((**er).m_text))
{
/* check if the dollar sign is repeated - if so skip it */
if ((**er).m_text[i] == '$' && (**er).m_text[i + 1] == '$')
{
if (string_grow (&processed, &len, '$'))
{
mem_free ((void **) (void *) &processed);
error_destroy (er);
return 1;
}
i += 2;
}
else if ((**er).m_text[i] != '$')
{
if (string_grow (&processed, &len, (**er).m_text[i]))
{
mem_free ((void **) (void *) &processed);
error_destroy (er);
return 1;
}
i++;
}
else
{
if (string_grow (&processed, &len, '$'))
{
mem_free ((void **) (void *) &processed);
error_destroy (er);
return 1;
}
{
/* length of token being extracted */
unsigned int tlen = 0;
if (string_grow (&(**er).m_token_name, &tlen, '\0'))
{
mem_free ((void **) (void *) &processed);
error_destroy (er);
return 1;
}
/* skip the dollar sign */
i++;
while ((**er).m_text[i] != '$')
{
if (string_grow (&(**er).m_token_name, &tlen, (**er).m_text[i]))
{
mem_free ((void **) (void *) &processed);
error_destroy (er);
return 1;
}
i++;
}
/* skip the dollar sign */
i++;
}
}
}
mem_free ((void **) &(**er).m_text);
(**er).m_text = processed;
}
*text = t;
return 0;
}
/*
returns 0 on success,
returns 1 otherwise,
*/
static int get_emits (const byte **text, emit **em, map_byte *mapb)
{
const byte *t = *text;
byte *temp = NULL;
emit *e = NULL;
emit_dest dest;
if (*t != '.')
return 0;
t++;
if (get_identifier (&t, &temp))
return 1;
eat_spaces (&t);
/* .emit */
if (str_equal ((byte *) "emit", temp))
dest = ed_output;
/* .load */
else if (str_equal ((byte *) "load", temp))
dest = ed_regbyte;
else
{
mem_free ((void **) (void *) &temp);
return 0;
}
mem_free ((void **) (void *) &temp);
emit_create (&e);
if (e == NULL)
return 1;
e->m_emit_dest = dest;
if (dest == ed_regbyte)
{
if (get_identifier (&t, &e->m_regname))
{
emit_destroy (&e);
return 1;
}
eat_spaces (&t);
}
/* 0xNN */
if (*t == '0' && (t[1] == 'x' || t[1] == 'X'))
{
t += 2;
e->m_byte = (byte) hex_convert (&t);
e->m_emit_type = et_byte;
}
/* NNN */
else if (*t >= '0' && *t <= '9')
{
e->m_byte = (byte) dec_convert (&t);
e->m_emit_type = et_byte;
}
/* * */
else if (*t == '*')
{
t++;
e->m_emit_type = et_stream;
}
/* $ */
else if (*t == '$')
{
t++;
e->m_emit_type = et_position;
}
/* 'c' */
else if (*t == '\'')
{
if (get_string (&t, &temp))
{
emit_destroy (&e);
return 1;
}
e->m_byte = (byte) temp[0];
mem_free ((void **) (void *) &temp);
e->m_emit_type = et_byte;
}
else
{
if (get_identifier (&t, &temp))
{
emit_destroy (&e);
return 1;
}
if (map_byte_find (&mapb, temp, &e->m_byte))
{
mem_free ((void **) (void *) &temp);
emit_destroy (&e);
return 1;
}
mem_free ((void **) (void *) &temp);
e->m_emit_type = et_byte;
}
eat_spaces (&t);
if (get_emits (&t, &e->m_next, mapb))
{
emit_destroy (&e);
return 1;
}
*text = t;
*em = e;
return 0;
}
/*
returns 0 on success,
returns 1 otherwise,
*/
static int get_spec (const byte **text, spec **sp, map_str *maps, map_byte *mapb)
{
const byte *t = *text;
spec *s = NULL;
spec_create (&s);
if (s == NULL)
return 1;
/* first - read optional .if statement */
if (*t == '.')
{
const byte *u = t;
byte *keyword = NULL;
/* skip the dot */
u++;
if (get_identifier (&u, &keyword))
{
spec_destroy (&s);
return 1;
}
/* .if */
if (str_equal ((byte *) "if", keyword))
{
cond_create (&s->m_cond);
if (s->m_cond == NULL)
{
spec_destroy (&s);
return 1;
}
/* skip the left paren */
eat_spaces (&u);
u++;
/* get the left operand */
eat_spaces (&u);
if (get_identifier (&u, &s->m_cond->m_operands[0].m_regname))
{
spec_destroy (&s);
return 1;
}
s->m_cond->m_operands[0].m_type = cot_regbyte;
/* get the operator (!= or ==) */
eat_spaces (&u);
if (*u == '!')
s->m_cond->m_type = ct_not_equal;
else
s->m_cond->m_type = ct_equal;
u += 2;
eat_spaces (&u);
if (u[0] == '0' && (u[1] == 'x' || u[1] == 'X'))
{
/* skip the 0x prefix */
u += 2;
/* get the right operand */
s->m_cond->m_operands[1].m_byte = hex_convert (&u);
s->m_cond->m_operands[1].m_type = cot_byte;
}
else /*if (*u >= '0' && *u <= '9')*/
{
/* get the right operand */
s->m_cond->m_operands[1].m_byte = dec_convert (&u);
s->m_cond->m_operands[1].m_type = cot_byte;
}
/* skip the right paren */
eat_spaces (&u);
u++;
eat_spaces (&u);
t = u;
}
mem_free ((void **) (void *) &keyword);
}
if (*t == '\'')
{
byte *temp = NULL;
if (get_string (&t, &temp))
{
spec_destroy (&s);
return 1;
}
eat_spaces (&t);
if (*t == '-')
{
byte *temp2 = NULL;
/* skip the '-' character */
t++;
eat_spaces (&t);
if (get_string (&t, &temp2))
{
mem_free ((void **) (void *) &temp);
spec_destroy (&s);
return 1;
}
eat_spaces (&t);
s->m_spec_type = st_byte_range;
s->m_byte[0] = *temp;
s->m_byte[1] = *temp2;
mem_free ((void **) (void *) &temp2);
}
else
{
s->m_spec_type = st_byte;
*s->m_byte = *temp;
}
mem_free ((void **) (void *) &temp);
}
else if (*t == '"')
{
if (get_string (&t, &s->m_string))
{
spec_destroy (&s);
return 1;
}
eat_spaces (&t);
/* Try to convert string to a token. */
if (s->m_string[0] == '@') {
s->m_spec_type = st_token;
if (!strcmp(s->m_string, "@,")) {
s->m_token = SL_PP_COMMA;
} else if (!strcmp(s->m_string, "@;")) {
s->m_token = SL_PP_SEMICOLON;
} else if (!strcmp(s->m_string, "@{")) {
s->m_token = SL_PP_LBRACE;
} else if (!strcmp(s->m_string, "@}")) {
s->m_token = SL_PP_RBRACE;
} else if (!strcmp(s->m_string, "@(")) {
s->m_token = SL_PP_LPAREN;
} else if (!strcmp(s->m_string, "@)")) {
s->m_token = SL_PP_RPAREN;
} else if (!strcmp(s->m_string, "@[")) {
s->m_token = SL_PP_LBRACKET;
} else if (!strcmp(s->m_string, "@]")) {
s->m_token = SL_PP_RBRACKET;
} else if (!strcmp(s->m_string, "@.")) {
s->m_token = SL_PP_DOT;
} else if (!strcmp(s->m_string, "@++")) {
s->m_token = SL_PP_INCREMENT;
} else if (!strcmp(s->m_string, "@+=")) {
s->m_token = SL_PP_ADDASSIGN;
} else if (!strcmp(s->m_string, "@+")) {
s->m_token = SL_PP_PLUS;
} else if (!strcmp(s->m_string, "@--")) {
s->m_token = SL_PP_DECREMENT;
} else if (!strcmp(s->m_string, "@-=")) {
s->m_token = SL_PP_SUBASSIGN;
} else if (!strcmp(s->m_string, "@-")) {
s->m_token = SL_PP_MINUS;
} else if (!strcmp(s->m_string, "@~")) {
s->m_token = SL_PP_BITNOT;
} else if (!strcmp(s->m_string, "@!=")) {
s->m_token = SL_PP_NOTEQUAL;
} else if (!strcmp(s->m_string, "@!")) {
s->m_token = SL_PP_NOT;
} else if (!strcmp(s->m_string, "@*=")) {
s->m_token = SL_PP_MULASSIGN;
} else if (!strcmp(s->m_string, "@*")) {
s->m_token = SL_PP_STAR;
} else if (!strcmp(s->m_string, "@/=")) {
s->m_token = SL_PP_DIVASSIGN;
} else if (!strcmp(s->m_string, "@/")) {
s->m_token = SL_PP_SLASH;
} else if (!strcmp(s->m_string, "@%=")) {
s->m_token = SL_PP_MODASSIGN;
} else if (!strcmp(s->m_string, "@%")) {
s->m_token = SL_PP_MODULO;
} else if (!strcmp(s->m_string, "@<<=")) {
s->m_token = SL_PP_LSHIFTASSIGN;
} else if (!strcmp(s->m_string, "@<<")) {
s->m_token = SL_PP_LSHIFT;
} else if (!strcmp(s->m_string, "@<=")) {
s->m_token = SL_PP_LESSEQUAL;
} else if (!strcmp(s->m_string, "@<")) {
s->m_token = SL_PP_LESS;
} else if (!strcmp(s->m_string, "@>>=")) {
s->m_token = SL_PP_RSHIFTASSIGN;
} else if (!strcmp(s->m_string, "@>>")) {
s->m_token = SL_PP_RSHIFT;
} else if (!strcmp(s->m_string, "@>=")) {
s->m_token = SL_PP_GREATEREQUAL;
} else if (!strcmp(s->m_string, "@>")) {
s->m_token = SL_PP_GREATER;
} else if (!strcmp(s->m_string, "@==")) {
s->m_token = SL_PP_EQUAL;
} else if (!strcmp(s->m_string, "@=")) {
s->m_token = SL_PP_ASSIGN;
} else if (!strcmp(s->m_string, "@&&")) {
s->m_token = SL_PP_AND;
} else if (!strcmp(s->m_string, "@&=")) {
s->m_token = SL_PP_BITANDASSIGN;
} else if (!strcmp(s->m_string, "@&")) {
s->m_token = SL_PP_BITAND;
} else if (!strcmp(s->m_string, "@^^")) {
s->m_token = SL_PP_XOR;
} else if (!strcmp(s->m_string, "@^=")) {
s->m_token = SL_PP_BITXORASSIGN;
} else if (!strcmp(s->m_string, "@^")) {
s->m_token = SL_PP_BITXOR;
} else if (!strcmp(s->m_string, "@||")) {
s->m_token = SL_PP_OR;
} else if (!strcmp(s->m_string, "@|=")) {
s->m_token = SL_PP_BITORASSIGN;
} else if (!strcmp(s->m_string, "@|")) {
s->m_token = SL_PP_BITOR;
} else if (!strcmp(s->m_string, "@?")) {
s->m_token = SL_PP_QUESTION;
} else if (!strcmp(s->m_string, "@:")) {
s->m_token = SL_PP_COLON;
} else if (!strcmp(s->m_string, "@ID")) {
s->m_token = SL_PP_IDENTIFIER;
} else if (!strcmp(s->m_string, "@UINT")) {
s->m_token = SL_PP_UINT;
} else if (!strcmp(s->m_string, "@FLOAT")) {
s->m_token = SL_PP_FLOAT;
} else if (!strcmp(s->m_string, "@EOF")) {
s->m_token = SL_PP_EOF;
} else {
spec_destroy(&s);
return 1;
}
} else {
s->m_spec_type = st_string;
}
}
else if (*t == '.')
{
byte *keyword = NULL;
/* skip the dot */
t++;
if (get_identifier (&t, &keyword))
{
spec_destroy (&s);
return 1;
}
eat_spaces (&t);
/* .true */
if (str_equal ((byte *) "true", keyword))
{
s->m_spec_type = st_true;
}
/* .false */
else if (str_equal ((byte *) "false", keyword))
{
s->m_spec_type = st_false;
}
/* .debug */
else if (str_equal ((byte *) "debug", keyword))
{
s->m_spec_type = st_debug;
}
/* .loop */
else if (str_equal ((byte *) "loop", keyword))
{
if (get_identifier (&t, &s->m_string))
{
mem_free ((void **) (void *) &keyword);
spec_destroy (&s);
return 1;
}
eat_spaces (&t);
s->m_spec_type = st_identifier_loop;
}
mem_free ((void **) (void *) &keyword);
}
else
{
if (get_identifier (&t, &s->m_string))
{
spec_destroy (&s);
return 1;
}
eat_spaces (&t);
s->m_spec_type = st_identifier;
}
if (get_error (&t, &s->m_errtext, maps))
{
spec_destroy (&s);
return 1;
}
if (get_emits (&t, &s->m_emits, mapb))
{
spec_destroy (&s);
return 1;
}
*text = t;
*sp = s;
return 0;
}
/*
returns 0 on success,
returns 1 otherwise,
*/
static int get_rule (const byte **text, rule **ru, map_str *maps, map_byte *mapb)
{
const byte *t = *text;
rule *r = NULL;
rule_create (&r);
if (r == NULL)
return 1;
if (get_spec (&t, &r->m_specs, maps, mapb))
{
rule_destroy (&r);
return 1;
}
while (*t != ';')
{
byte *op = NULL;
spec *sp = NULL;
/* skip the dot that precedes "and" or "or" */
t++;
/* read "and" or "or" keyword */
if (get_identifier (&t, &op))
{
rule_destroy (&r);
return 1;
}
eat_spaces (&t);
if (r->m_oper == op_none)
{
/* .and */
if (str_equal ((byte *) "and", op))
r->m_oper = op_and;
/* .or */
else
r->m_oper = op_or;
}
mem_free ((void **) (void *) &op);
if (get_spec (&t, &sp, maps, mapb))
{
rule_destroy (&r);
return 1;
}
spec_append (&r->m_specs, sp);
}
/* skip the semicolon */
t++;
eat_spaces (&t);
*text = t;
*ru = r;
return 0;
}
/*
returns 0 on success,
returns 1 otherwise,
*/
static int update_dependency (map_rule *mapr, byte *symbol, rule **ru)
{
if (map_rule_find (&mapr, symbol, ru))
return 1;
(**ru).m_referenced = 1;
return 0;
}
/*
returns 0 on success,
returns 1 otherwise,
*/
static int update_dependencies (dict *di, map_rule *mapr, byte **syntax_symbol,
byte **string_symbol, map_byte *regbytes)
{
rule *rulez = di->m_rulez;
/* update dependecies for the root and lexer symbols */
if (update_dependency (mapr, *syntax_symbol, &di->m_syntax) ||
(*string_symbol != NULL && update_dependency (mapr, *string_symbol, &di->m_string)))
return 1;
mem_free ((void **) syntax_symbol);
mem_free ((void **) string_symbol);
/* update dependecies for the rest of the rules */
while (rulez)
{
spec *sp = rulez->m_specs;
/* iterate through all the specifiers */
while (sp)
{
/* update dependency for identifier */
if (sp->m_spec_type == st_identifier || sp->m_spec_type == st_identifier_loop)
{
if (update_dependency (mapr, sp->m_string, &sp->m_rule))
return 1;
mem_free ((void **) &sp->m_string);
}
/* some errtexts reference to a rule */
if (sp->m_errtext && sp->m_errtext->m_token_name)
{
if (update_dependency (mapr, sp->m_errtext->m_token_name, &sp->m_errtext->m_token))
return 1;
mem_free ((void **) &sp->m_errtext->m_token_name);
}
/* update dependency for condition */
if (sp->m_cond)
{
int i;
for (i = 0; i < 2; i++)
if (sp->m_cond->m_operands[i].m_type == cot_regbyte)
{
sp->m_cond->m_operands[i].m_regbyte = map_byte_locate (®bytes,
sp->m_cond->m_operands[i].m_regname);
if (sp->m_cond->m_operands[i].m_regbyte == NULL)
return 1;
mem_free ((void **) &sp->m_cond->m_operands[i].m_regname);
}
}
/* update dependency for all .load instructions */
if (sp->m_emits)
{
emit *em = sp->m_emits;
while (em != NULL)
{
if (em->m_emit_dest == ed_regbyte)
{
em->m_regbyte = map_byte_locate (®bytes, em->m_regname);
if (em->m_regbyte == NULL)
return 1;
mem_free ((void **) &em->m_regname);
}
em = em->m_next;
}
}
sp = sp->next;
}
rulez = rulez->next;
}
/* check for unreferenced symbols */
rulez = di->m_rulez;
while (rulez != NULL)
{
if (!rulez->m_referenced)
{
map_rule *ma = mapr;
while (ma)
{
if (ma->data == rulez)
{
set_last_error (UNREFERENCED_IDENTIFIER, str_duplicate (ma->key), -1);
return 1;
}
ma = ma->next;
}
}
rulez = rulez->next;
}
return 0;
}
static int satisfies_condition (cond *co, regbyte_ctx *ctx)
{
byte values[2];
int i;
if (co == NULL)
return 1;
for (i = 0; i < 2; i++)
switch (co->m_operands[i].m_type)
{
case cot_byte:
values[i] = co->m_operands[i].m_byte;
break;
case cot_regbyte:
values[i] = regbyte_ctx_extract (&ctx, co->m_operands[i].m_regbyte);
break;
}
switch (co->m_type)
{
case ct_equal:
return values[0] == values[1];
case ct_not_equal:
return values[0] != values[1];
}
return 0;
}
static void free_regbyte_ctx_stack (regbyte_ctx *top, regbyte_ctx *limit)
{
while (top != limit)
{
regbyte_ctx *rbc = top->m_prev;
regbyte_ctx_destroy (&top);
top = rbc;
}
}
typedef enum match_result_
{
mr_not_matched, /* the examined string does not match */
mr_matched, /* the examined string matches */
mr_error_raised, /* mr_not_matched + error has been raised */
mr_dont_emit, /* used by identifier loops only */
mr_internal_error /* an internal error has occured such as out of memory */
} match_result;
/*
* This function does the main job. It parses the text and generates output data.
*/
static match_result
match (dict *di, const byte *text, int *index, rule *ru, barray **ba, int filtering_string,
regbyte_ctx **rbc)
{
int ind = *index;
match_result status = mr_not_matched;
spec *sp = ru->m_specs;
regbyte_ctx *ctx = *rbc;
/* for every specifier in the rule */
while (sp)
{
int i, len, save_ind = ind;
barray *array = NULL;
if (satisfies_condition (sp->m_cond, ctx))
{
switch (sp->m_spec_type)
{
case st_identifier:
barray_create (&array);
if (array == NULL)
{
free_regbyte_ctx_stack (ctx, *rbc);
return mr_internal_error;
}
status = match (di, text, &ind, sp->m_rule, &array, filtering_string, &ctx);
if (status == mr_internal_error)
{
free_regbyte_ctx_stack (ctx, *rbc);
barray_destroy (&array);
return mr_internal_error;
}
break;
case st_string:
len = str_length (sp->m_string);
/* prefilter the stream */
if (!filtering_string && di->m_string)
{
barray *ba;
int filter_index = 0;
match_result result;
regbyte_ctx *null_ctx = NULL;
barray_create (&ba);
if (ba == NULL)
{
free_regbyte_ctx_stack (ctx, *rbc);
return mr_internal_error;
}
result = match (di, text + ind, &filter_index, di->m_string, &ba, 1, &null_ctx);
if (result == mr_internal_error)
{
free_regbyte_ctx_stack (ctx, *rbc);
barray_destroy (&ba);
return mr_internal_error;
}
if (result != mr_matched)
{
barray_destroy (&ba);
status = mr_not_matched;
break;
}
barray_destroy (&ba);
if (filter_index != len || !str_equal_n (sp->m_string, text + ind, len))
{
status = mr_not_matched;
break;
}
status = mr_matched;
ind += len;
}
else
{
status = mr_matched;
for (i = 0; status == mr_matched && i < len; i++)
if (text[ind + i] != sp->m_string[i])
status = mr_not_matched;
if (status == mr_matched)
ind += len;
}
break;
case st_byte:
status = text[ind] == *sp->m_byte ? mr_matched : mr_not_matched;
if (status == mr_matched)
ind++;
break;
case st_byte_range:
status = (text[ind] >= sp->m_byte[0] && text[ind] <= sp->m_byte[1]) ?
mr_matched : mr_not_matched;
if (status == mr_matched)
ind++;
break;
case st_true:
status = mr_matched;
break;
case st_false:
status = mr_not_matched;
break;
case st_debug:
status = ru->m_oper == op_and ? mr_matched : mr_not_matched;
break;
case st_identifier_loop:
barray_create (&array);
if (array == NULL)
{
free_regbyte_ctx_stack (ctx, *rbc);
return mr_internal_error;
}
status = mr_dont_emit;
for (;;)
{
match_result result;
save_ind = ind;
result = match (di, text, &ind, sp->m_rule, &array, filtering_string, &ctx);
if (result == mr_error_raised)
{
status = result;
break;
}
else if (result == mr_matched)
{
if (barray_push (ba, sp->m_emits, text[ind - 1], save_ind, &ctx) ||
barray_append (ba, &array))
{
free_regbyte_ctx_stack (ctx, *rbc);
barray_destroy (&array);
return mr_internal_error;
}
barray_destroy (&array);
barray_create (&array);
if (array == NULL)
{
free_regbyte_ctx_stack (ctx, *rbc);
return mr_internal_error;
}
}
else if (result == mr_internal_error)
{
free_regbyte_ctx_stack (ctx, *rbc);
barray_destroy (&array);
return mr_internal_error;
}
else
break;
}
break;
}
}
else
{
status = mr_not_matched;
}
if (status == mr_error_raised)
{
free_regbyte_ctx_stack (ctx, *rbc);
barray_destroy (&array);
return mr_error_raised;
}
if (ru->m_oper == op_and && status != mr_matched && status != mr_dont_emit)
{
free_regbyte_ctx_stack (ctx, *rbc);
barray_destroy (&array);
if (sp->m_errtext)
{
set_last_error (sp->m_errtext->m_text, error_get_token (sp->m_errtext, di, text,
ind), ind);
return mr_error_raised;
}
return mr_not_matched;
}
if (status == mr_matched)
{
if (sp->m_emits)
if (barray_push (ba, sp->m_emits, text[ind - 1], save_ind, &ctx))
{
free_regbyte_ctx_stack (ctx, *rbc);
barray_destroy (&array);
return mr_internal_error;
}
if (array)
if (barray_append (ba, &array))
{
free_regbyte_ctx_stack (ctx, *rbc);
barray_destroy (&array);
return mr_internal_error;
}
}
barray_destroy (&array);
/* if the rule operator is a logical or, we pick up the first matching specifier */
if (ru->m_oper == op_or && (status == mr_matched || status == mr_dont_emit))
{
*index = ind;
*rbc = ctx;
return mr_matched;
}
sp = sp->next;
}
/* everything went fine - all specifiers match up */
if (ru->m_oper == op_and && (status == mr_matched || status == mr_dont_emit))
{
*index = ind;
*rbc = ctx;
return mr_matched;
}
free_regbyte_ctx_stack (ctx, *rbc);
return mr_not_matched;
}
static match_result
fast_match(dict *di,
const struct sl_pp_token_info *tokens,
int *index,
rule *ru,
int *_PP,
bytepool *_BP,
regbyte_ctx **rbc,
struct sl_pp_context *context)
{
int ind = *index;
int _P = *_PP;
int _P2;
match_result status = mr_not_matched;
spec *sp = ru->m_specs;
regbyte_ctx *ctx = *rbc;
/* for every specifier in the rule */
while (sp)
{
int save_ind = ind;
_P2 = _P + (sp->m_emits ? emit_size(sp->m_emits, sl_pp_context_cstr(context, tokens[ind].data.identifier)) : 0);
if (bytepool_reserve (_BP, _P2))
{
free_regbyte_ctx_stack (ctx, *rbc);
return mr_internal_error;
}
if (satisfies_condition (sp->m_cond, ctx))
{
switch (sp->m_spec_type)
{
case st_identifier:
status = fast_match(di, tokens, &ind, sp->m_rule, &_P2, _BP, &ctx, context);
if (status == mr_internal_error)
{
free_regbyte_ctx_stack (ctx, *rbc);
return mr_internal_error;
}
break;
case st_token:
if (tokens[ind].token == sp->m_token) {
status = mr_matched;
ind++;
} else {
status = mr_not_matched;
}
break;
case st_string:
if (tokens[ind].token != SL_PP_IDENTIFIER) {
status = mr_not_matched;
break;
}
if (!strcmp(sl_pp_context_cstr(context, tokens[ind].data.identifier), sp->m_string)) {
status = mr_matched;
ind++;
} else {
status = mr_not_matched;
}
break;
case st_byte:
/**status = text[ind] == *sp->m_byte ? mr_matched : mr_not_matched;**/
if (status == mr_matched)
ind++;
break;
case st_byte_range:
/**status = (text[ind] >= sp->m_byte[0] && text[ind] <= sp->m_byte[1]) ?
mr_matched : mr_not_matched;**/
if (status == mr_matched)
ind++;
break;
case st_true:
status = mr_matched;
break;
case st_false:
status = mr_not_matched;
break;
case st_debug:
status = ru->m_oper == op_and ? mr_matched : mr_not_matched;
break;
case st_identifier_loop:
status = mr_dont_emit;
for (;;)
{
match_result result;
save_ind = ind;
result = fast_match(di, tokens, &ind, sp->m_rule, &_P2, _BP, &ctx, context);
if (result == mr_error_raised)
{
status = result;
break;
}
else if (result == mr_matched)
{
if (sp->m_emits != NULL)
{
if (emit_push (sp->m_emits, _BP->_F + _P, sl_pp_context_cstr(context, tokens[ind - 1].data.identifier), save_ind, &ctx))
{
free_regbyte_ctx_stack (ctx, *rbc);
return mr_internal_error;
}
}
_P = _P2;
_P2 += sp->m_emits ? emit_size(sp->m_emits, sl_pp_context_cstr(context, tokens[ind].data.identifier)) : 0;
if (bytepool_reserve (_BP, _P2))
{
free_regbyte_ctx_stack (ctx, *rbc);
return mr_internal_error;
}
}
else if (result == mr_internal_error)
{
free_regbyte_ctx_stack (ctx, *rbc);
return mr_internal_error;
}
else
break;
}
break;
}
}
else
{
status = mr_not_matched;
}
if (status == mr_error_raised)
{
free_regbyte_ctx_stack (ctx, *rbc);
return mr_error_raised;
}
if (ru->m_oper == op_and && status != mr_matched && status != mr_dont_emit)
{
free_regbyte_ctx_stack (ctx, *rbc);
if (sp->m_errtext)
{
/**set_last_error (sp->m_errtext->m_text, error_get_token (sp->m_errtext, di, text,
ind), ind);**/
return mr_error_raised;
}
return mr_not_matched;
}
if (status == mr_matched)
{
if (sp->m_emits != NULL) {
const char *str = (ind <= 0) ? "" : sl_pp_context_cstr(context, tokens[ind - 1].data.identifier);
if (emit_push (sp->m_emits, _BP->_F + _P, str, save_ind, &ctx))
{
free_regbyte_ctx_stack (ctx, *rbc);
return mr_internal_error;
}
}
_P = _P2;
}
/* if the rule operator is a logical or, we pick up the first matching specifier */
if (ru->m_oper == op_or && (status == mr_matched || status == mr_dont_emit))
{
*index = ind;
*rbc = ctx;
*_PP = _P;
return mr_matched;
}
sp = sp->next;
}
/* everything went fine - all specifiers match up */
if (ru->m_oper == op_and && (status == mr_matched || status == mr_dont_emit))
{
*index = ind;
*rbc = ctx;
*_PP = _P;
return mr_matched;
}
free_regbyte_ctx_stack (ctx, *rbc);
return mr_not_matched;
}
static byte *
error_get_token (error *er, dict *di, const byte *text, int ind)
{
byte *str = NULL;
if (er->m_token)
{
barray *ba;
int filter_index = 0;
regbyte_ctx *ctx = NULL;
barray_create (&ba);
if (ba != NULL)
{
if (match (di, text + ind, &filter_index, er->m_token, &ba, 0, &ctx) == mr_matched &&
filter_index)
{
str = (byte *) mem_alloc (filter_index + 1);
if (str != NULL)
{
str_copy_n (str, text + ind, filter_index);
str[filter_index] = '\0';
}
}
barray_destroy (&ba);
}
}
return str;
}
typedef struct grammar_load_state_
{
dict *di;
byte *syntax_symbol;
byte *string_symbol;
map_str *maps;
map_byte *mapb;
map_rule *mapr;
} grammar_load_state;
static void grammar_load_state_create (grammar_load_state **gr)
{
*gr = (grammar_load_state *) mem_alloc (sizeof (grammar_load_state));
if (*gr)
{
(**gr).di = NULL;
(**gr).syntax_symbol = NULL;
(**gr).string_symbol = NULL;
(**gr).maps = NULL;
(**gr).mapb = NULL;
(**gr).mapr = NULL;
}
}
static void grammar_load_state_destroy (grammar_load_state **gr)
{
if (*gr)
{
dict_destroy (&(**gr).di);
mem_free ((void **) &(**gr).syntax_symbol);
mem_free ((void **) &(**gr).string_symbol);
map_str_destroy (&(**gr).maps);
map_byte_destroy (&(**gr).mapb);
map_rule_destroy (&(**gr).mapr);
mem_free ((void **) gr);
}
}
static void error_msg(int line, const char *msg)
{
fprintf(stderr, "Error in grammar_load_from_text() at line %d: %s\n", line, msg);
}
/*
the API
*/
grammar grammar_load_from_text (const byte *text)
{
grammar_load_state *g = NULL;
grammar id = 0;
clear_last_error ();
grammar_load_state_create (&g);
if (g == NULL) {
error_msg(__LINE__, "");
return 0;
}
dict_create (&g->di);
if (g->di == NULL)
{
grammar_load_state_destroy (&g);
error_msg(__LINE__, "");
return 0;
}
eat_spaces (&text);
/* skip ".syntax" keyword */
text += 7;
eat_spaces (&text);
/* retrieve root symbol */
if (get_identifier (&text, &g->syntax_symbol))
{
grammar_load_state_destroy (&g);
error_msg(__LINE__, "");
return 0;
}
eat_spaces (&text);
/* skip semicolon */
text++;
eat_spaces (&text);
while (*text)
{
byte *symbol = NULL;
int is_dot = *text == '.';
if (is_dot)
text++;
if (get_identifier (&text, &symbol))
{
grammar_load_state_destroy (&g);
error_msg(__LINE__, "");
return 0;
}
eat_spaces (&text);
/* .emtcode */
if (is_dot && str_equal (symbol, (byte *) "emtcode"))
{
map_byte *ma = NULL;
mem_free ((void **) (void *) &symbol);
if (get_emtcode (&text, &ma))
{
grammar_load_state_destroy (&g);
error_msg(__LINE__, "");
return 0;
}
map_byte_append (&g->mapb, ma);
}
/* .regbyte */
else if (is_dot && str_equal (symbol, (byte *) "regbyte"))
{
map_byte *ma = NULL;
mem_free ((void **) (void *) &symbol);
if (get_regbyte (&text, &ma))
{
grammar_load_state_destroy (&g);
error_msg(__LINE__, "");
return 0;
}
map_byte_append (&g->di->m_regbytes, ma);
}
/* .errtext */
else if (is_dot && str_equal (symbol, (byte *) "errtext"))
{
map_str *ma = NULL;
mem_free ((void **) (void *) &symbol);
if (get_errtext (&text, &ma))
{
grammar_load_state_destroy (&g);
error_msg(__LINE__, "");
return 0;
}
map_str_append (&g->maps, ma);
}
/* .string */
else if (is_dot && str_equal (symbol, (byte *) "string"))
{
mem_free ((void **) (void *) &symbol);
if (g->di->m_string != NULL)
{
grammar_load_state_destroy (&g);
error_msg(__LINE__, "");
return 0;
}
if (get_identifier (&text, &g->string_symbol))
{
grammar_load_state_destroy (&g);
error_msg(__LINE__, "");
return 0;
}
/* skip semicolon */
eat_spaces (&text);
text++;
eat_spaces (&text);
}
else
{
rule *ru = NULL;
map_rule *ma = NULL;
if (get_rule (&text, &ru, g->maps, g->mapb))
{
grammar_load_state_destroy (&g);
error_msg(__LINE__, "");
return 0;
}
rule_append (&g->di->m_rulez, ru);
/* if a rule consist of only one specifier, give it an ".and" operator */
if (ru->m_oper == op_none)
ru->m_oper = op_and;
map_rule_create (&ma);
if (ma == NULL)
{
grammar_load_state_destroy (&g);
error_msg(__LINE__, "");
return 0;
}
ma->key = symbol;
ma->data = ru;
map_rule_append (&g->mapr, ma);
}
}
if (update_dependencies (g->di, g->mapr, &g->syntax_symbol, &g->string_symbol,
g->di->m_regbytes))
{
grammar_load_state_destroy (&g);
error_msg(__LINE__, "update_dependencies() failed");
return 0;
}
dict_append (&g_dicts, g->di);
id = g->di->m_id;
g->di = NULL;
grammar_load_state_destroy (&g);
return id;
}
int grammar_set_reg8 (grammar id, const byte *name, byte value)
{
dict *di = NULL;
map_byte *reg = NULL;
clear_last_error ();
dict_find (&g_dicts, id, &di);
if (di == NULL)
{
set_last_error (INVALID_GRAMMAR_ID, NULL, -1);
return 0;
}
reg = map_byte_locate (&di->m_regbytes, name);
if (reg == NULL)
{
set_last_error (INVALID_REGISTER_NAME, str_duplicate (name), -1);
return 0;
}
reg->data = value;
return 1;
}
int
grammar_fast_check (grammar id,
struct sl_pp_context *context,
struct sl_pp_token_info *tokens,
byte **prod,
unsigned int *size,
unsigned int estimate_prod_size)
{
dict *di = NULL;
int index = 0;
regbyte_ctx *rbc = NULL;
bytepool *bp = NULL;
int _P = 0;
clear_last_error ();
dict_find (&g_dicts, id, &di);
if (di == NULL)
{
set_last_error (INVALID_GRAMMAR_ID, NULL, -1);
return 0;
}
*prod = NULL;
*size = 0;
bytepool_create(&bp, estimate_prod_size);
if (bp == NULL) {
return 0;
}
if (fast_match(di, tokens, &index, di->m_syntax, &_P, bp, &rbc, context) != mr_matched) {
bytepool_destroy (&bp);
free_regbyte_ctx_stack (rbc, NULL);
return 0;
}
free_regbyte_ctx_stack(rbc, NULL);
*prod = bp->_F;
*size = _P;
bp->_F = NULL;
bytepool_destroy(&bp);
return 1;
}
int grammar_destroy (grammar id)
{
dict **di = &g_dicts;
clear_last_error ();
while (*di != NULL)
{
if ((**di).m_id == id)
{
dict *tmp = *di;
*di = (**di).next;
dict_destroy (&tmp);
return 1;
}
di = &(**di).next;
}
set_last_error (INVALID_GRAMMAR_ID, NULL, -1);
return 0;
}
static void append_character (const char x, byte *text, int *dots_made, int *len, int size)
{
if (*dots_made == 0)
{
if (*len < size - 1)
{
text[(*len)++] = x;
text[*len] = '\0';
}
else
{
int i;
for (i = 0; i < 3; i++)
if (--(*len) >= 0)
text[*len] = '.';
*dots_made = 1;
}
}
}
void grammar_get_last_error (byte *text, unsigned int size, int *pos)
{
int len = 0, dots_made = 0;
const byte *p = error_message;
*text = '\0';
if (p)
{
while (*p)
{
if (*p == '$')
{
const byte *r = error_param;
while (*r)
{
append_character (*r++, text, &dots_made, &len, (int) size);
}
p++;
}
else
{
append_character (*p++, text, &dots_made, &len, size);
}
}
}
*pos = error_position;
}
|