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
|
/*
* awkgram.y --- yacc/bison parser
*/
/*
* Copyright (C) 1986, 1988, 1989, 1991-2003 the Free Software Foundation, Inc.
*
* This file is part of GAWK, the GNU implementation of the
* AWK Programming Language.
*
* GAWK is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* GAWK is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
*/
%{
#ifdef GAWKDEBUG
#define YYDEBUG 12
#endif
#include "awk.h"
#define CAN_FREE TRUE
#define DONT_FREE FALSE
#if defined(HAVE_STDARG_H) && defined(__STDC__) && __STDC__
static void yyerror(const char *m, ...) ATTRIBUTE_PRINTF_1;
#else
static void yyerror(); /* va_alist */
#endif
static char *get_src_buf P((void));
static int yylex P((void));
static NODE *node_common P((NODETYPE op));
static NODE *snode P((NODE *subn, NODETYPE op, int sindex));
static NODE *make_for_loop P((NODE *init, NODE *cond, NODE *incr));
static NODE *append_right P((NODE *list, NODE *new));
static inline NODE *append_pattern P((NODE **list, NODE *patt));
static void func_install P((NODE *params, NODE *def));
static void pop_var P((NODE *np, int freeit));
static void pop_params P((NODE *params));
static NODE *make_param P((char *name));
static NODE *mk_rexp P((NODE *exp));
static int dup_parms P((NODE *func));
static void param_sanity P((NODE *arglist));
static int parms_shadow P((const char *fname, NODE *func));
static int isnoeffect P((NODETYPE t));
static int isassignable P((NODE *n));
static void dumpintlstr P((const char *str, size_t len));
static void dumpintlstr2 P((const char *str1, size_t len1, const char *str2, size_t len2));
static void count_args P((NODE *n));
enum defref { FUNC_DEFINE, FUNC_USE };
static void func_use P((const char *name, enum defref how));
static void check_funcs P((void));
static int want_regexp; /* lexical scanning kludge */
static int can_return; /* parsing kludge */
static int begin_or_end_rule = FALSE; /* parsing kludge */
static int parsing_end_rule = FALSE; /* for warnings */
static int in_print = FALSE; /* lexical scanning kludge for print */
static int in_parens = 0; /* lexical scanning kludge for print */
static char *lexptr; /* pointer to next char during parsing */
static char *lexend;
static char *lexptr_begin; /* keep track of where we were for error msgs */
static char *lexeme; /* beginning of lexeme for debugging */
static char *thisline = NULL;
#define YYDEBUG_LEXER_TEXT (lexeme)
static int param_counter;
static char *tokstart = NULL;
static char *tok = NULL;
static char *tokend;
static long func_count; /* total number of functions */
#define HASHSIZE 1021 /* this constant only used here */
NODE *variables[HASHSIZE];
static int var_count; /* total number of global variables */
extern char *source;
extern int sourceline;
extern struct src *srcfiles;
extern int numfiles;
extern int errcount;
extern NODE *begin_block;
extern NODE *end_block;
/*
* This string cannot occur as a real awk identifier.
* Use it as a special token to make function parsing
* uniform, but if it's seen, don't install the function.
* e.g.
* function split(x) { return x }
* function x(a) { return a }
* should only produce one error message, and not core dump.
*/
static char builtin_func[] = "@builtin";
%}
%union {
long lval;
AWKNUM fval;
NODE *nodeval;
NODETYPE nodetypeval;
char *sval;
NODE *(*ptrval) P((void));
}
%type <nodeval> function_prologue pattern action variable param_list
%type <nodeval> exp common_exp
%type <nodeval> simp_exp non_post_simp_exp
%type <nodeval> expression_list opt_expression_list print_expression_list
%type <nodeval> statements statement if_statement opt_param_list
%type <nodeval> simple_stmt opt_simple_stmt
%type <nodeval> opt_exp opt_variable regexp
%type <nodeval> input_redir output_redir
%type <nodetypeval> print
%type <nodetypeval> assign_operator a_relop relop_or_less
%type <sval> func_name
%type <lval> lex_builtin
%token <sval> FUNC_CALL NAME REGEXP
%token <lval> ERROR
%token <nodeval> YNUMBER YSTRING
%token <nodetypeval> RELOP IO_OUT IO_IN
%token <nodetypeval> ASSIGNOP ASSIGN MATCHOP CONCAT_OP
%token <nodetypeval> LEX_BEGIN LEX_END LEX_IF LEX_ELSE LEX_RETURN LEX_DELETE
%token <nodetypeval> LEX_WHILE LEX_DO LEX_FOR LEX_BREAK LEX_CONTINUE
%token <nodetypeval> LEX_PRINT LEX_PRINTF LEX_NEXT LEX_EXIT LEX_FUNCTION
%token <nodetypeval> LEX_GETLINE LEX_NEXTFILE
%token <nodetypeval> LEX_IN
%token <lval> LEX_AND LEX_OR INCREMENT DECREMENT
%token <lval> LEX_BUILTIN LEX_LENGTH
%token NEWLINE
/* these are just yylval numbers */
/* Lowest to highest */
%right ASSIGNOP ASSIGN SLASH_BEFORE_EQUAL
%right '?' ':'
%left LEX_OR
%left LEX_AND
%left LEX_GETLINE
%nonassoc LEX_IN
%left FUNC_CALL LEX_BUILTIN LEX_LENGTH
%nonassoc ','
%nonassoc MATCHOP
%nonassoc RELOP '<' '>' IO_IN IO_OUT
%left CONCAT_OP
%left YSTRING YNUMBER
%left '+' '-'
%left '*' '/' '%'
%right '!' UNARY
%right '^'
%left INCREMENT DECREMENT
%left '$'
%left '(' ')'
%%
start
: opt_nls program opt_nls
{
check_funcs();
}
;
program
: /* empty */
| program rule
{
begin_or_end_rule = parsing_end_rule = FALSE;
yyerrok;
}
| program error
{
begin_or_end_rule = parsing_end_rule = FALSE;
yyerrok;
/*
* If errors, give up, don't produce an infinite
* stream of syntax error message.
*/
return;
}
;
rule
: pattern action
{
$1->rnode = $2;
}
| pattern statement_term
{
if ($1->lnode != NULL) {
/* pattern rule with non-empty pattern */
$1->rnode = node(NULL, Node_K_print_rec, NULL);
} else {
/* an error */
if (begin_or_end_rule)
warning(_("%s blocks must have an action part"),
(parsing_end_rule ? "END" : "BEGIN"));
else
warning(_("each rule must have a pattern or an action part"));
errcount++;
}
}
| function_prologue action
{
can_return = FALSE;
if ($1)
func_install($1, $2);
yyerrok;
}
;
pattern
: /* empty */
{
$$ = append_pattern(&expression_value, (NODE *) NULL);
}
| exp
{
$$ = append_pattern(&expression_value, $1);
}
| exp ',' exp
{
NODE *r;
getnode(r);
r->type = Node_line_range;
r->condpair = node($1, Node_cond_pair, $3);
r->triggered = FALSE;
$$ = append_pattern(&expression_value, r);
}
| LEX_BEGIN
{
begin_or_end_rule = TRUE;
$$ = append_pattern(&begin_block, (NODE *) NULL);
}
| LEX_END
{
begin_or_end_rule = parsing_end_rule = TRUE;
$$ = append_pattern(&end_block, (NODE *) NULL);
}
;
action
: l_brace statements r_brace opt_semi opt_nls
{ $$ = $2; }
;
func_name
: NAME
{ $$ = $1; }
| FUNC_CALL
{ $$ = $1; }
| lex_builtin
{
yyerror(_("`%s' is a built-in function, it cannot be redefined"),
tokstart);
errcount++;
$$ = builtin_func;
/* yyerrok; */
}
;
lex_builtin
: LEX_BUILTIN
| LEX_LENGTH
;
function_prologue
: LEX_FUNCTION
{
param_counter = 0;
}
func_name '(' opt_param_list r_paren opt_nls
{
NODE *t;
t = make_param($3);
t->flags |= FUNC;
$$ = append_right(t, $5);
can_return = TRUE;
/* check for duplicate parameter names */
if (dup_parms($$))
errcount++;
}
;
regexp
/*
* In this rule, want_regexp tells yylex that the next thing
* is a regexp so it should read up to the closing slash.
*/
: a_slash
{ ++want_regexp; }
REGEXP /* The terminating '/' is consumed by yylex(). */
{
NODE *n;
size_t len = strlen($3);
if (do_lint && ($3)[0] == '*') {
/* possible C comment */
if (($3)[len-1] == '*')
lintwarn(_("regexp constant `/%s/' looks like a C comment, but is not"), tokstart);
}
getnode(n);
n->type = Node_regex;
n->re_exp = make_string($3, len);
n->re_reg = make_regexp($3, len, FALSE);
n->re_text = NULL;
n->re_flags = CONST;
$$ = n;
}
;
a_slash
: '/'
| SLASH_BEFORE_EQUAL
;
statements
: /* empty */
{ $$ = NULL; }
| statements statement
{
if ($2 == NULL)
$$ = $1;
else {
if (do_lint && isnoeffect($2->type))
lintwarn(_("statement may have no effect"));
if ($1 == NULL)
$$ = $2;
else
$$ = append_right(
($1->type == Node_statement_list ? $1
: node($1, Node_statement_list, (NODE *) NULL)),
($2->type == Node_statement_list ? $2
: node($2, Node_statement_list, (NODE *) NULL)));
}
yyerrok;
}
| statements error
{ $$ = NULL; }
;
statement_term
: nls
| semi opt_nls
;
statement
: semi opt_nls
{ $$ = NULL; }
| l_brace statements r_brace
{ $$ = $2; }
| if_statement
{ $$ = $1; }
| LEX_WHILE '(' exp r_paren opt_nls statement
{ $$ = node($3, Node_K_while, $6); }
| LEX_DO opt_nls statement LEX_WHILE '(' exp r_paren opt_nls
{ $$ = node($6, Node_K_do, $3); }
| LEX_FOR '(' NAME LEX_IN NAME r_paren opt_nls statement
{
/*
* Efficiency hack. Recognize the special case of
*
* for (iggy in foo)
* delete foo[iggy]
*
* and treat it as if it were
*
* delete foo
*
* Check that the body is a `delete a[i]' statement,
* and that both the loop var and array names match.
*/
if ($8 != NULL && $8->type == Node_K_delete) {
NODE *arr, *sub;
assert($8->rnode->type == Node_expression_list);
arr = $8->lnode; /* array var */
sub = $8->rnode->lnode; /* index var */
if ( (arr->type == Node_var
|| arr->type == Node_var_array
|| arr->type == Node_param_list)
&& (sub->type == Node_var || sub->type == Node_param_list)
&& strcmp($3, sub->vname) == 0
&& strcmp($5, arr->vname) == 0) {
$8->type = Node_K_delete_loop;
$$ = $8;
}
else
goto regular_loop;
} else {
regular_loop:
$$ = node($8, Node_K_arrayfor,
make_for_loop(variable($3, CAN_FREE, Node_var),
(NODE *) NULL, variable($5, CAN_FREE, Node_var_array)));
}
}
| LEX_FOR '(' opt_simple_stmt semi opt_nls exp semi opt_nls opt_simple_stmt r_paren opt_nls statement
{
$$ = node($12, Node_K_for, (NODE *) make_for_loop($3, $6, $9));
}
| LEX_FOR '(' opt_simple_stmt semi opt_nls semi opt_nls opt_simple_stmt r_paren opt_nls statement
{
$$ = node($11, Node_K_for,
(NODE *) make_for_loop($3, (NODE *) NULL, $8));
}
| LEX_BREAK statement_term
/* for break, maybe we'll have to remember where to break to */
{ $$ = node((NODE *) NULL, Node_K_break, (NODE *) NULL); }
| LEX_CONTINUE statement_term
/* similarly */
{ $$ = node((NODE *) NULL, Node_K_continue, (NODE *) NULL); }
| LEX_NEXT statement_term
{ NODETYPE type;
if (begin_or_end_rule)
yyerror(_("`%s' used in %s action"), "next",
(parsing_end_rule ? "END" : "BEGIN"));
type = Node_K_next;
$$ = node((NODE *) NULL, type, (NODE *) NULL);
}
| LEX_NEXTFILE statement_term
{
if (do_traditional) {
/*
* can't use yyerror, since may have overshot
* the source line
*/
errcount++;
error(_("`nextfile' is a gawk extension"));
}
if (do_lint)
lintwarn(_("`nextfile' is a gawk extension"));
if (begin_or_end_rule) {
/* same thing */
errcount++;
error(_("`%s' used in %s action"), "nextfile",
(parsing_end_rule ? "END" : "BEGIN"));
}
$$ = node((NODE *) NULL, Node_K_nextfile, (NODE *) NULL);
}
| LEX_EXIT opt_exp statement_term
{ $$ = node($2, Node_K_exit, (NODE *) NULL); }
| LEX_RETURN
{
if (! can_return)
yyerror(_("`return' used outside function context"));
}
opt_exp statement_term
{ $$ = node($3, Node_K_return, (NODE *) NULL); }
| simple_stmt statement_term
;
/*
* A simple_stmt exists to satisfy a constraint in the POSIX
* grammar allowing them to occur as the 1st and 3rd parts
* in a `for (...;...;...)' loop. This is a historical oddity
* inherited from Unix awk, not at all documented in the AK&W
* awk book. We support it, as this was reported as a bug.
* We don't bother to document it though. So there.
*/
simple_stmt
: print { in_print = TRUE; in_parens = 0; } print_expression_list output_redir
{
/*
* Optimization: plain `print' has no expression list, so $3 is null.
* If $3 is an expression list with one element (rnode == null)
* and lnode is a field spec for field 0, we have `print $0'.
* For both, use Node_K_print_rec, which is faster for these two cases.
*/
if ($1 == Node_K_print &&
($3 == NULL
|| ($3->type == Node_expression_list
&& $3->rnode == NULL
&& $3->lnode->type == Node_field_spec
&& $3->lnode->lnode->type == Node_val
&& $3->lnode->lnode->numbr == 0.0))
) {
static int warned = FALSE;
$$ = node(NULL, Node_K_print_rec, $4);
if (do_lint && $3 == NULL && begin_or_end_rule && ! warned) {
warned = TRUE;
lintwarn(
_("plain `print' in BEGIN or END rule should probably be `print \"\"'"));
}
} else {
$$ = node($3, $1, $4);
if ($$->type == Node_K_printf)
count_args($$);
}
}
| LEX_DELETE NAME '[' expression_list ']'
{ $$ = node(variable($2, CAN_FREE, Node_var_array), Node_K_delete, $4); }
| LEX_DELETE NAME
{
if (do_lint)
lintwarn(_("`delete array' is a gawk extension"));
if (do_traditional) {
/*
* can't use yyerror, since may have overshot
* the source line
*/
errcount++;
error(_("`delete array' is a gawk extension"));
}
$$ = node(variable($2, CAN_FREE, Node_var_array), Node_K_delete, (NODE *) NULL);
}
| LEX_DELETE '(' NAME ')'
{
/* this is for tawk compatibility. maybe the warnings should always be done. */
if (do_lint)
lintwarn(_("`delete(array)' is a non-portable tawk extension"));
if (do_traditional) {
/*
* can't use yyerror, since may have overshot
* the source line
*/
errcount++;
error(_("`delete(array)' is a non-portable tawk extension"));
}
$$ = node(variable($3, CAN_FREE, Node_var_array), Node_K_delete, (NODE *) NULL);
}
| exp
{ $$ = $1; }
;
opt_simple_stmt
: /* empty */
{ $$ = NULL; }
| simple_stmt
{ $$ = $1; }
;
print
: LEX_PRINT
| LEX_PRINTF
;
/*
* Note: ``print(x)'' is already parsed by the first rule,
* so there is no good in covering it by the second one too.
*/
print_expression_list
: opt_expression_list
| '(' exp comma expression_list r_paren
{ $$ = node($2, Node_expression_list, $4); }
;
output_redir
: /* empty */
{
in_print = FALSE;
in_parens = 0;
$$ = NULL;
}
| IO_OUT { in_print = FALSE; in_parens = 0; } common_exp
{
$$ = node($3, $1, (NODE *) NULL);
if ($1 == Node_redirect_twoway
&& $3->type == Node_K_getline
&& $3->rnode->type == Node_redirect_twoway)
yyerror(_("multistage two-way pipelines don't work"));
}
;
if_statement
: LEX_IF '(' exp r_paren opt_nls statement
{
$$ = node($3, Node_K_if,
node($6, Node_if_branches, (NODE *) NULL));
}
| LEX_IF '(' exp r_paren opt_nls statement
LEX_ELSE opt_nls statement
{ $$ = node($3, Node_K_if,
node($6, Node_if_branches, $9)); }
;
nls
: NEWLINE
| nls NEWLINE
;
opt_nls
: /* empty */
| nls
;
input_redir
: /* empty */
{ $$ = NULL; }
| '<' simp_exp
{ $$ = node($2, Node_redirect_input, (NODE *) NULL); }
;
opt_param_list
: /* empty */
{ $$ = NULL; }
| param_list
{ $$ = $1; }
;
param_list
: NAME
{ $$ = make_param($1); }
| param_list comma NAME
{ $$ = append_right($1, make_param($3)); yyerrok; }
| error
{ $$ = NULL; }
| param_list error
{ $$ = NULL; }
| param_list comma error
{ $$ = NULL; }
;
/* optional expression, as in for loop */
opt_exp
: /* empty */
{ $$ = NULL; }
| exp
{ $$ = $1; }
;
opt_expression_list
: /* empty */
{ $$ = NULL; }
| expression_list
{ $$ = $1; }
;
expression_list
: exp
{ $$ = node($1, Node_expression_list, (NODE *) NULL); }
| expression_list comma exp
{
$$ = append_right($1,
node($3, Node_expression_list, (NODE *) NULL));
yyerrok;
}
| error
{ $$ = NULL; }
| expression_list error
{ $$ = NULL; }
| expression_list error exp
{ $$ = NULL; }
| expression_list comma error
{ $$ = NULL; }
;
/* Expressions, not including the comma operator. */
exp : variable assign_operator exp %prec ASSIGNOP
{
if (do_lint && $3->type == Node_regex)
lintwarn(_("regular expression on right of assignment"));
$$ = node($1, $2, $3);
}
| exp LEX_AND exp
{ $$ = node($1, Node_and, $3); }
| exp LEX_OR exp
{ $$ = node($1, Node_or, $3); }
| exp MATCHOP exp
{
if ($1->type == Node_regex)
warning(_("regular expression on left of `~' or `!~' operator"));
$$ = node($1, $2, mk_rexp($3));
}
| exp LEX_IN NAME
{ $$ = node(variable($3, CAN_FREE, Node_var_array), Node_in_array, $1); }
| exp a_relop exp %prec RELOP
{
if (do_lint && $3->type == Node_regex)
lintwarn(_("regular expression on right of comparison"));
$$ = node($1, $2, $3);
}
| exp '?' exp ':' exp
{ $$ = node($1, Node_cond_exp, node($3, Node_if_branches, $5));}
| common_exp
{ $$ = $1; }
;
assign_operator
: ASSIGN
{ $$ = $1; }
| ASSIGNOP
{ $$ = $1; }
| SLASH_BEFORE_EQUAL ASSIGN /* `/=' */
{ $$ = Node_assign_quotient; }
;
relop_or_less
: RELOP
{ $$ = $1; }
| '<'
{ $$ = Node_less; }
;
a_relop
: relop_or_less
| '>'
{ $$ = Node_greater; }
;
common_exp
: regexp
{ $$ = $1; }
| '!' regexp %prec UNARY
{
$$ = node(node(make_number(0.0),
Node_field_spec,
(NODE *) NULL),
Node_nomatch,
$2);
}
| '(' expression_list r_paren LEX_IN NAME
{ $$ = node(variable($5, CAN_FREE, Node_var_array), Node_in_array, $2); }
| simp_exp
{ $$ = $1; }
| common_exp simp_exp %prec CONCAT_OP
{ $$ = node($1, Node_concat, $2); }
;
simp_exp
: non_post_simp_exp
/* Binary operators in order of decreasing precedence. */
| simp_exp '^' simp_exp
{ $$ = node($1, Node_exp, $3); }
| simp_exp '*' simp_exp
{ $$ = node($1, Node_times, $3); }
| simp_exp '/' simp_exp
{ $$ = node($1, Node_quotient, $3); }
| simp_exp '%' simp_exp
{ $$ = node($1, Node_mod, $3); }
| simp_exp '+' simp_exp
{ $$ = node($1, Node_plus, $3); }
| simp_exp '-' simp_exp
{ $$ = node($1, Node_minus, $3); }
| LEX_GETLINE opt_variable input_redir
{
if (do_lint && parsing_end_rule && $3 == NULL)
lintwarn(_("non-redirected `getline' undefined inside END action"));
$$ = node($2, Node_K_getline, $3);
}
| simp_exp IO_IN LEX_GETLINE opt_variable
{
$$ = node($4, Node_K_getline,
node($1, $2, (NODE *) NULL));
}
| variable INCREMENT
{ $$ = node($1, Node_postincrement, (NODE *) NULL); }
| variable DECREMENT
{ $$ = node($1, Node_postdecrement, (NODE *) NULL); }
;
non_post_simp_exp
: '!' simp_exp %prec UNARY
{ $$ = node($2, Node_not, (NODE *) NULL); }
| '(' exp r_paren
{ $$ = $2; }
| LEX_BUILTIN
'(' opt_expression_list r_paren
{ $$ = snode($3, Node_builtin, (int) $1); }
| LEX_LENGTH '(' opt_expression_list r_paren
{ $$ = snode($3, Node_builtin, (int) $1); }
| LEX_LENGTH
{
if (do_lint)
lintwarn(_("call of `length' without parentheses is not portable"));
$$ = snode((NODE *) NULL, Node_builtin, (int) $1);
if (do_posix)
warning(_("call of `length' without parentheses is deprecated by POSIX"));
}
| FUNC_CALL '(' opt_expression_list r_paren
{
$$ = node($3, Node_func_call, make_string($1, strlen($1)));
$$->funcbody = NULL;
func_use($1, FUNC_USE);
param_sanity($3);
free($1);
}
| variable
| INCREMENT variable
{ $$ = node($2, Node_preincrement, (NODE *) NULL); }
| DECREMENT variable
{ $$ = node($2, Node_predecrement, (NODE *) NULL); }
| YNUMBER
{ $$ = $1; }
| YSTRING
{ $$ = $1; }
| '-' simp_exp %prec UNARY
{
if ($2->type == Node_val && ($2->flags & (STRCUR|STRING)) == 0) {
$2->numbr = -(force_number($2));
$$ = $2;
} else
$$ = node($2, Node_unary_minus, (NODE *) NULL);
}
| '+' simp_exp %prec UNARY
{
/*
* was: $$ = $2
* POSIX semantics: force a conversion to numeric type
*/
$$ = node (make_number(0.0), Node_plus, $2);
}
;
opt_variable
: /* empty */
{ $$ = NULL; }
| variable
{ $$ = $1; }
;
variable
: NAME
{ $$ = variable($1, CAN_FREE, Node_var); }
| NAME '[' expression_list ']'
{
if ($3 == NULL) {
fatal(_("invalid subscript expression"));
} else if ($3->rnode == NULL) {
$$ = node(variable($1, CAN_FREE, Node_var_array), Node_subscript, $3->lnode);
freenode($3);
} else
$$ = node(variable($1, CAN_FREE, Node_var_array), Node_subscript, $3);
}
| '$' non_post_simp_exp
{ $$ = node($2, Node_field_spec, (NODE *) NULL); }
;
l_brace
: '{' opt_nls
;
r_brace
: '}' opt_nls { yyerrok; }
;
r_paren
: ')' { yyerrok; }
;
opt_semi
: /* empty */
| semi
;
semi
: ';' { yyerrok; }
;
comma : ',' opt_nls { yyerrok; }
;
%%
struct token {
const char *operator; /* text to match */
NODETYPE value; /* node type */
int class; /* lexical class */
unsigned flags; /* # of args. allowed and compatability */
# define ARGS 0xFF /* 0, 1, 2, 3 args allowed (any combination */
# define A(n) (1<<(n))
# define VERSION_MASK 0xFF00 /* old awk is zero */
# define NOT_OLD 0x0100 /* feature not in old awk */
# define NOT_POSIX 0x0200 /* feature not in POSIX */
# define GAWKX 0x0400 /* gawk extension */
# define RESX 0x0800 /* Bell Labs Research extension */
NODE *(*ptr) P((NODE *)); /* function that implements this keyword */
};
/* Tokentab is sorted ascii ascending order, so it can be binary searched. */
/* Function pointers come from declarations in awk.h. */
static const struct token tokentab[] = {
{"BEGIN", Node_illegal, LEX_BEGIN, 0, 0},
{"END", Node_illegal, LEX_END, 0, 0},
#ifdef ARRAYDEBUG
{"adump", Node_builtin, LEX_BUILTIN, GAWKX|A(1), do_adump},
#endif
{"and", Node_builtin, LEX_BUILTIN, GAWKX|A(2), do_and},
{"asort", Node_builtin, LEX_BUILTIN, GAWKX|A(1)|A(2), do_asort},
{"asorti", Node_builtin, LEX_BUILTIN, GAWKX|A(1)|A(2), do_asorti},
{"atan2", Node_builtin, LEX_BUILTIN, NOT_OLD|A(2), do_atan2},
{"bindtextdomain", Node_builtin, LEX_BUILTIN, GAWKX|A(1)|A(2), do_bindtextdomain},
{"break", Node_K_break, LEX_BREAK, 0, 0},
{"close", Node_builtin, LEX_BUILTIN, NOT_OLD|A(1)|A(2), do_close},
{"compl", Node_builtin, LEX_BUILTIN, GAWKX|A(1), do_compl},
{"continue", Node_K_continue, LEX_CONTINUE, 0, 0},
{"cos", Node_builtin, LEX_BUILTIN, NOT_OLD|A(1), do_cos},
{"dcgettext", Node_builtin, LEX_BUILTIN, GAWKX|A(1)|A(2)|A(3), do_dcgettext},
{"dcngettext", Node_builtin, LEX_BUILTIN, GAWKX|A(1)|A(2)|A(3)|A(4)|A(5), do_dcngettext},
{"delete", Node_K_delete, LEX_DELETE, NOT_OLD, 0},
{"do", Node_K_do, LEX_DO, NOT_OLD, 0},
{"else", Node_illegal, LEX_ELSE, 0, 0},
{"exit", Node_K_exit, LEX_EXIT, 0, 0},
{"exp", Node_builtin, LEX_BUILTIN, A(1), do_exp},
{"extension", Node_builtin, LEX_BUILTIN, GAWKX|A(2), do_ext},
{"fflush", Node_builtin, LEX_BUILTIN, RESX|A(0)|A(1), do_fflush},
{"for", Node_K_for, LEX_FOR, 0, 0},
{"func", Node_K_function, LEX_FUNCTION, NOT_POSIX|NOT_OLD, 0},
{"function", Node_K_function, LEX_FUNCTION, NOT_OLD, 0},
{"gensub", Node_builtin, LEX_BUILTIN, GAWKX|A(3)|A(4), do_gensub},
{"getline", Node_K_getline, LEX_GETLINE, NOT_OLD, 0},
{"gsub", Node_builtin, LEX_BUILTIN, NOT_OLD|A(2)|A(3), do_gsub},
{"if", Node_K_if, LEX_IF, 0, 0},
{"in", Node_illegal, LEX_IN, 0, 0},
{"index", Node_builtin, LEX_BUILTIN, A(2), do_index},
{"int", Node_builtin, LEX_BUILTIN, A(1), do_int},
{"length", Node_builtin, LEX_LENGTH, A(0)|A(1), do_length},
{"log", Node_builtin, LEX_BUILTIN, A(1), do_log},
{"lshift", Node_builtin, LEX_BUILTIN, GAWKX|A(2), do_lshift},
{"match", Node_builtin, LEX_BUILTIN, NOT_OLD|A(2)|A(3), do_match},
{"mktime", Node_builtin, LEX_BUILTIN, GAWKX|A(1), do_mktime},
{"next", Node_K_next, LEX_NEXT, 0, 0},
{"nextfile", Node_K_nextfile, LEX_NEXTFILE, GAWKX, 0},
{"or", Node_builtin, LEX_BUILTIN, GAWKX|A(2), do_or},
{"print", Node_K_print, LEX_PRINT, 0, 0},
{"printf", Node_K_printf, LEX_PRINTF, 0, 0},
{"rand", Node_builtin, LEX_BUILTIN, NOT_OLD|A(0), do_rand},
{"return", Node_K_return, LEX_RETURN, NOT_OLD, 0},
{"rshift", Node_builtin, LEX_BUILTIN, GAWKX|A(2), do_rshift},
{"sin", Node_builtin, LEX_BUILTIN, NOT_OLD|A(1), do_sin},
{"split", Node_builtin, LEX_BUILTIN, A(2)|A(3), do_split},
{"sprintf", Node_builtin, LEX_BUILTIN, 0, do_sprintf},
{"sqrt", Node_builtin, LEX_BUILTIN, A(1), do_sqrt},
{"srand", Node_builtin, LEX_BUILTIN, NOT_OLD|A(0)|A(1), do_srand},
#if defined(GAWKDEBUG) || defined(ARRAYDEBUG) /* || ... */
{"stopme", Node_builtin, LEX_BUILTIN, GAWKX|A(0), stopme},
#endif
{"strftime", Node_builtin, LEX_BUILTIN, GAWKX|A(0)|A(1)|A(2), do_strftime},
{"strtonum", Node_builtin, LEX_BUILTIN, GAWKX|A(1), do_strtonum},
{"sub", Node_builtin, LEX_BUILTIN, NOT_OLD|A(2)|A(3), do_sub},
{"substr", Node_builtin, LEX_BUILTIN, A(2)|A(3), do_substr},
{"system", Node_builtin, LEX_BUILTIN, NOT_OLD|A(1), do_system},
{"systime", Node_builtin, LEX_BUILTIN, GAWKX|A(0), do_systime},
{"tolower", Node_builtin, LEX_BUILTIN, NOT_OLD|A(1), do_tolower},
{"toupper", Node_builtin, LEX_BUILTIN, NOT_OLD|A(1), do_toupper},
{"while", Node_K_while, LEX_WHILE, 0, 0},
{"xor", Node_builtin, LEX_BUILTIN, GAWKX|A(2), do_xor},
};
#ifdef MBS_SUPPORT
/* Variable containing the current shift state. */
static mbstate_t cur_mbstate;
/* Ring buffer containing current characters. */
#define MAX_CHAR_IN_RING_BUFFER 8
#define RING_BUFFER_SIZE (MAX_CHAR_IN_RING_BUFFER * MB_LEN_MAX)
static char cur_char_ring[RING_BUFFER_SIZE];
/* Index for ring buffers. */
static int cur_ring_idx;
/* This macro means that last nextc() return a singlebyte character
or 1st byte of a multibyte character. */
#define nextc_is_1stbyte (cur_char_ring[cur_ring_idx] == 1)
#endif /* MBS_SUPPORT */
/* getfname --- return name of a builtin function (for pretty printing) */
const char *
getfname(register NODE *(*fptr)(NODE *))
{
register int i, j;
j = sizeof(tokentab) / sizeof(tokentab[0]);
/* linear search, no other way to do it */
for (i = 0; i < j; i++)
if (tokentab[i].ptr == fptr)
return tokentab[i].operator;
return NULL;
}
/* yyerror --- print a syntax error message, show where */
/*
* Function identifier purposely indented to avoid mangling
* by ansi2knr. Sigh.
*/
static void
#if defined(HAVE_STDARG_H) && defined(__STDC__) && __STDC__
yyerror(const char *m, ...)
#else
/* VARARGS0 */
yyerror(va_alist)
va_dcl
#endif
{
va_list args;
const char *mesg = NULL;
register char *bp, *cp;
char *scan;
char *buf;
int count;
static char end_of_file_line[] = "(END OF FILE)";
char save;
errcount++;
/* Find the current line in the input file */
if (lexptr && lexeme) {
if (thisline == NULL) {
cp = lexeme;
if (*cp == '\n') {
cp--;
mesg = _("unexpected newline or end of string");
}
for (; cp != lexptr_begin && *cp != '\n'; --cp)
continue;
if (*cp == '\n')
cp++;
thisline = cp;
}
/* NL isn't guaranteed */
bp = lexeme;
while (bp < lexend && *bp && *bp != '\n')
bp++;
} else {
thisline = end_of_file_line;
bp = thisline + strlen(thisline);
}
/*
* Saving and restoring *bp keeps valgrind happy,
* since the guts of glibc uses strlen, even though
* we're passing an explict precision. Sigh.
*/
save = *bp;
*bp = '\0';
msg("%.*s", (int) (bp - thisline), thisline);
*bp = save;
#if defined(HAVE_STDARG_H) && defined(__STDC__) && __STDC__
va_start(args, m);
if (mesg == NULL)
mesg = m;
#else
va_start(args);
if (mesg == NULL)
mesg = va_arg(args, char *);
#endif
count = (bp - thisline) + strlen(mesg) + 2 + 1;
emalloc(buf, char *, count, "yyerror");
bp = buf;
if (lexptr != NULL) {
scan = thisline;
while (scan < lexeme)
if (*scan++ == '\t')
*bp++ = '\t';
else
*bp++ = ' ';
*bp++ = '^';
*bp++ = ' ';
}
strcpy(bp, mesg);
err("", buf, args);
va_end(args);
free(buf);
}
/* get_src_buf --- read the next buffer of source program */
static char *
get_src_buf()
{
static int samefile = FALSE;
static int nextfile = 0;
static char *buf = NULL;
static int fd;
int n;
register char *scan;
static size_t len = 0;
static int did_newline = FALSE;
int newfile;
struct stat sbuf;
# define SLOP 128 /* enough space to hold most source lines */
again:
newfile = FALSE;
if (nextfile > numfiles)
return NULL;
if (srcfiles[nextfile].stype == CMDLINE) {
if (len == 0) {
len = strlen(srcfiles[nextfile].val);
if (len == 0) {
/*
* Yet Another Special case:
* gawk '' /path/name
* Sigh.
*/
static int warned = FALSE;
if (do_lint && ! warned) {
warned = TRUE;
lintwarn(_("empty program text on command line"));
}
++nextfile;
goto again;
}
sourceline = 1;
lexptr = lexptr_begin = srcfiles[nextfile].val;
lexend = lexptr + len;
} else if (! did_newline && *(lexptr-1) != '\n') {
/*
* The following goop is to ensure that the source
* ends with a newline and that the entire current
* line is available for error messages.
*/
int offset;
did_newline = TRUE;
offset = lexptr - lexeme;
for (scan = lexeme; scan > lexptr_begin; scan--)
if (*scan == '\n') {
scan++;
break;
}
len = lexptr - scan;
emalloc(buf, char *, len+1, "get_src_buf");
memcpy(buf, scan, len);
thisline = buf;
lexptr = buf + len;
*lexptr = '\n';
lexeme = lexptr - offset;
lexptr_begin = buf;
lexend = lexptr + 1;
} else {
len = 0;
lexeme = lexptr = lexptr_begin = NULL;
}
if (lexptr == NULL && ++nextfile <= numfiles)
goto again;
return lexptr;
}
if (! samefile) {
source = srcfiles[nextfile].val;
if (source == NULL) {
if (buf != NULL) {
free(buf);
buf = NULL;
}
len = 0;
return lexeme = lexptr = lexptr_begin = NULL;
}
fd = pathopen(source);
if (fd <= INVALID_HANDLE) {
char *in;
/* suppress file name and line no. in error mesg */
in = source;
source = NULL;
fatal(_("can't open source file `%s' for reading (%s)"),
in, strerror(errno));
}
len = optimal_bufsize(fd, & sbuf);
newfile = TRUE;
if (buf != NULL)
free(buf);
emalloc(buf, char *, len + SLOP, "get_src_buf");
lexptr_begin = buf + SLOP;
samefile = TRUE;
sourceline = 1;
} else {
/*
* Here, we retain the current source line (up to length SLOP)
* in the beginning of the buffer that was overallocated above
*/
int offset;
int linelen;
offset = lexptr - lexeme;
for (scan = lexeme; scan > lexptr_begin; scan--)
if (*scan == '\n') {
scan++;
break;
}
linelen = lexptr - scan;
if (linelen > SLOP)
linelen = SLOP;
thisline = buf + SLOP - linelen;
memcpy(thisline, scan, linelen);
lexeme = buf + SLOP - offset;
lexptr_begin = thisline;
}
n = read(fd, buf + SLOP, len);
if (n == -1)
fatal(_("can't read sourcefile `%s' (%s)"),
source, strerror(errno));
if (n == 0) {
if (newfile) {
static int warned = FALSE;
if (do_lint && ! warned) {
warned = TRUE;
lintwarn(_("source file `%s' is empty"), source);
}
}
if (fd != fileno(stdin)) /* safety */
close(fd);
samefile = FALSE;
nextfile++;
if (lexeme)
*lexeme = '\0';
len = 0;
goto again;
}
lexptr = buf + SLOP;
lexend = lexptr + n;
return buf;
}
/* tokadd --- add a character to the token buffer */
#define tokadd(x) (*tok++ = (x), tok == tokend ? tokexpand() : tok)
/* tokexpand --- grow the token buffer */
char *
tokexpand()
{
static int toksize = 60;
int tokoffset;
tokoffset = tok - tokstart;
toksize *= 2;
if (tokstart != NULL)
erealloc(tokstart, char *, toksize, "tokexpand");
else
emalloc(tokstart, char *, toksize, "tokexpand");
tokend = tokstart + toksize;
tok = tokstart + tokoffset;
return tok;
}
/* nextc --- get the next input character */
#ifdef MBS_SUPPORT
static int
nextc(void)
{
if (gawk_mb_cur_max > 1) {
/* Update the buffer index. */
cur_ring_idx = (cur_ring_idx == RING_BUFFER_SIZE - 1)? 0 :
cur_ring_idx + 1;
/* Did we already check the current character? */
if (cur_char_ring[cur_ring_idx] == 0) {
/* No, we need to check the next character on the buffer. */
int idx, work_ring_idx = cur_ring_idx;
mbstate_t tmp_state;
size_t mbclen;
if (!lexptr || lexptr >= lexend)
if (!get_src_buf()) {
return EOF;
}
for (idx = 0 ; lexptr + idx < lexend ; idx++) {
tmp_state = cur_mbstate;
mbclen = mbrlen(lexptr, idx + 1, &tmp_state);
if (mbclen == 1 || mbclen == (size_t)-1 || mbclen == 0) {
/* It is a singlebyte character, non-complete multibyte
character or EOF. We treat it as a singlebyte
character. */
cur_char_ring[work_ring_idx] = 1;
break;
} else if (mbclen == (size_t)-2) {
/* It is not a complete multibyte character. */
cur_char_ring[work_ring_idx] = idx + 1;
} else {
/* mbclen > 1 */
cur_char_ring[work_ring_idx] = mbclen;
break;
}
work_ring_idx = (work_ring_idx == RING_BUFFER_SIZE - 1)?
0 : work_ring_idx + 1;
}
cur_mbstate = tmp_state;
/* Put a mark on the position on which we write next character. */
work_ring_idx = (work_ring_idx == RING_BUFFER_SIZE - 1)?
0 : work_ring_idx + 1;
cur_char_ring[work_ring_idx] = 0;
}
return (int) (unsigned char) *lexptr++;
}
else {
int c;
if (lexptr && lexptr < lexend)
c = (int) (unsigned char) *lexptr++;
else if (get_src_buf())
c = (int) (unsigned char) *lexptr++;
else
c = EOF;
return c;
}
}
#else /* MBS_SUPPORT */
#if GAWKDEBUG
int
nextc(void)
{
int c;
if (lexptr && lexptr < lexend)
c = (int) (unsigned char) *lexptr++;
else if (get_src_buf())
c = (int) (unsigned char) *lexptr++;
else
c = EOF;
return c;
}
#else
#define nextc() ((lexptr && lexptr < lexend) ? \
((int) (unsigned char) *lexptr++) : \
(get_src_buf() ? ((int) (unsigned char) *lexptr++) : EOF) \
)
#endif
#endif /* MBS_SUPPORT */
/* pushback --- push a character back on the input */
#ifdef MBS_SUPPORT
static void
pushback(void)
{
if (gawk_mb_cur_max > 1) {
cur_ring_idx = (cur_ring_idx == 0)? RING_BUFFER_SIZE - 1 :
cur_ring_idx - 1;
(lexptr && lexptr > lexptr_begin ? lexptr-- : lexptr);
} else
(lexptr && lexptr > lexptr_begin ? lexptr-- : lexptr);
}
#else
#define pushback() (lexptr && lexptr > lexptr_begin ? lexptr-- : lexptr)
#endif /* MBS_SUPPORT */
/* allow_newline --- allow newline after &&, ||, ? and : */
static void
allow_newline(void)
{
int c;
for (;;) {
c = nextc();
if (c == EOF)
break;
if (c == '#') {
while ((c = nextc()) != '\n' && c != EOF)
continue;
if (c == EOF)
break;
}
if (c == '\n')
sourceline++;
if (! ISSPACE(c)) {
pushback();
break;
}
}
}
/* yylex --- Read the input and turn it into tokens. */
static int
yylex(void)
{
register int c;
int seen_e = FALSE; /* These are for numbers */
int seen_point = FALSE;
int esc_seen; /* for literal strings */
int low, mid, high;
static int did_newline = FALSE;
char *tokkey;
static int lasttok = 0, eof_warned = FALSE;
int inhex = FALSE;
int intlstr = FALSE;
if (nextc() == EOF) {
if (lasttok != NEWLINE) {
lasttok = NEWLINE;
if (do_lint && ! eof_warned) {
lintwarn(_("source file does not end in newline"));
eof_warned = TRUE;
}
return NEWLINE; /* fake it */
}
return 0;
}
pushback();
#if defined OS2 || defined __EMX__
/*
* added for OS/2's extproc feature of cmd.exe
* (like #! in BSD sh)
*/
if (strncasecmp(lexptr, "extproc ", 8) == 0) {
while (*lexptr && *lexptr != '\n')
lexptr++;
}
#endif
lexeme = lexptr;
thisline = NULL;
if (want_regexp) {
int in_brack = 0; /* count brackets, [[:alnum:]] allowed */
/*
* Counting brackets is non-trivial. [[] is ok,
* and so is [\]], with a point being that /[/]/ as a regexp
* constant has to work.
*
* Do not count [ or ] if either one is preceded by a \.
* A `[' should be counted if
* a) it is the first one so far (in_brack == 0)
* b) it is the `[' in `[:'
* A ']' should be counted if not preceded by a \, since
* it is either closing `:]' or just a plain list.
* According to POSIX, []] is how you put a ] into a set.
* Try to handle that too.
*
* The code for \ handles \[ and \].
*/
want_regexp = FALSE;
tok = tokstart;
for (;;) {
c = nextc();
#ifdef MBS_SUPPORT
if (gawk_mb_cur_max == 1 || nextc_is_1stbyte)
#endif
switch (c) {
case '[':
/* one day check for `.' and `=' too */
if (nextc() == ':' || in_brack == 0)
in_brack++;
pushback();
break;
case ']':
if (tokstart[0] == '['
&& (tok == tokstart + 1
|| (tok == tokstart + 2
&& tokstart[1] == '^')))
/* do nothing */;
else
in_brack--;
break;
case '\\':
if ((c = nextc()) == EOF) {
yyerror(_("unterminated regexp ends with `\\' at end of file"));
return lasttok = REGEXP; /* kludge */
} else if (c == '\n') {
sourceline++;
continue;
} else {
tokadd('\\');
tokadd(c);
continue;
}
break;
case '/': /* end of the regexp */
if (in_brack > 0)
break;
tokadd('\0');
yylval.sval = tokstart;
return lasttok = REGEXP;
case '\n':
pushback();
yyerror(_("unterminated regexp"));
return lasttok = REGEXP; /* kludge */
case EOF:
yyerror(_("unterminated regexp at end of file"));
return lasttok = REGEXP; /* kludge */
}
tokadd(c);
}
}
retry:
while ((c = nextc()) == ' ' || c == '\t')
continue;
lexeme = lexptr ? lexptr - 1 : lexptr;
thisline = NULL;
tok = tokstart;
yylval.nodetypeval = Node_illegal;
#ifdef MBS_SUPPORT
if (gawk_mb_cur_max == 1 || nextc_is_1stbyte)
#endif
switch (c) {
case EOF:
if (lasttok != NEWLINE) {
lasttok = NEWLINE;
if (do_lint && ! eof_warned) {
lintwarn(_("source file does not end in newline"));
eof_warned = TRUE;
}
return NEWLINE; /* fake it */
}
return 0;
case '\n':
sourceline++;
return lasttok = NEWLINE;
case '#': /* it's a comment */
while ((c = nextc()) != '\n') {
if (c == EOF) {
if (lasttok != NEWLINE) {
lasttok = NEWLINE;
if (do_lint && ! eof_warned) {
lintwarn(
_("source file does not end in newline"));
eof_warned = TRUE;
}
return NEWLINE; /* fake it */
}
return 0;
}
}
sourceline++;
return lasttok = NEWLINE;
case '\\':
#ifdef RELAXED_CONTINUATION
/*
* This code puports to allow comments and/or whitespace
* after the `\' at the end of a line used for continuation.
* Use it at your own risk. We think it's a bad idea, which
* is why it's not on by default.
*/
if (! do_traditional) {
/* strip trailing white-space and/or comment */
while ((c = nextc()) == ' ' || c == '\t')
continue;
if (c == '#') {
if (do_lint)
lintwarn(
_("use of `\\ #...' line continuation is not portable"));
while ((c = nextc()) != '\n')
if (c == EOF)
break;
}
pushback();
}
#endif /* RELAXED_CONTINUATION */
if (nextc() == '\n') {
sourceline++;
goto retry;
} else {
yyerror(_("backslash not last character on line"));
exit(1);
}
break;
case ':':
case '?':
if (! do_posix)
allow_newline();
return lasttok = c;
/*
* in_parens is undefined unless we are parsing a print
* statement (in_print), but why bother with a check?
*/
case ')':
in_parens--;
return lasttok = c;
case '(':
in_parens++;
/* FALL THROUGH */
case '$':
case ';':
case '{':
case ',':
case '[':
case ']':
return lasttok = c;
case '*':
if ((c = nextc()) == '=') {
yylval.nodetypeval = Node_assign_times;
return lasttok = ASSIGNOP;
} else if (do_posix) {
pushback();
return lasttok = '*';
} else if (c == '*') {
/* make ** and **= aliases for ^ and ^= */
static int did_warn_op = FALSE, did_warn_assgn = FALSE;
if (nextc() == '=') {
if (! did_warn_assgn) {
did_warn_assgn = TRUE;
if (do_lint)
lintwarn(_("POSIX does not allow operator `**='"));
if (do_lint_old)
warning(_("old awk does not support operator `**='"));
}
yylval.nodetypeval = Node_assign_exp;
return ASSIGNOP;
} else {
pushback();
if (! did_warn_op) {
did_warn_op = TRUE;
if (do_lint)
lintwarn(_("POSIX does not allow operator `**'"));
if (do_lint_old)
warning(_("old awk does not support operator `**'"));
}
return lasttok = '^';
}
}
pushback();
return lasttok = '*';
case '/':
if (nextc() == '=') {
pushback();
return lasttok = SLASH_BEFORE_EQUAL;
}
pushback();
return lasttok = '/';
case '%':
if (nextc() == '=') {
yylval.nodetypeval = Node_assign_mod;
return lasttok = ASSIGNOP;
}
pushback();
return lasttok = '%';
case '^':
{
static int did_warn_op = FALSE, did_warn_assgn = FALSE;
if (nextc() == '=') {
if (do_lint_old && ! did_warn_assgn) {
did_warn_assgn = TRUE;
warning(_("operator `^=' is not supported in old awk"));
}
yylval.nodetypeval = Node_assign_exp;
return lasttok = ASSIGNOP;
}
pushback();
if (do_lint_old && ! did_warn_op) {
did_warn_op = TRUE;
warning(_("operator `^' is not supported in old awk"));
}
return lasttok = '^';
}
case '+':
if ((c = nextc()) == '=') {
yylval.nodetypeval = Node_assign_plus;
return lasttok = ASSIGNOP;
}
if (c == '+')
return lasttok = INCREMENT;
pushback();
return lasttok = '+';
case '!':
if ((c = nextc()) == '=') {
yylval.nodetypeval = Node_notequal;
return lasttok = RELOP;
}
if (c == '~') {
yylval.nodetypeval = Node_nomatch;
return lasttok = MATCHOP;
}
pushback();
return lasttok = '!';
case '<':
if (nextc() == '=') {
yylval.nodetypeval = Node_leq;
return lasttok = RELOP;
}
yylval.nodetypeval = Node_less;
pushback();
return lasttok = '<';
case '=':
if (nextc() == '=') {
yylval.nodetypeval = Node_equal;
return lasttok = RELOP;
}
yylval.nodetypeval = Node_assign;
pushback();
return lasttok = ASSIGN;
case '>':
if ((c = nextc()) == '=') {
yylval.nodetypeval = Node_geq;
return lasttok = RELOP;
} else if (c == '>') {
yylval.nodetypeval = Node_redirect_append;
return lasttok = IO_OUT;
}
pushback();
if (in_print && in_parens == 0) {
yylval.nodetypeval = Node_redirect_output;
return lasttok = IO_OUT;
}
yylval.nodetypeval = Node_greater;
return lasttok = '>';
case '~':
yylval.nodetypeval = Node_match;
return lasttok = MATCHOP;
case '}':
/*
* Added did newline stuff. Easier than
* hacking the grammar.
*/
if (did_newline) {
did_newline = FALSE;
return lasttok = c;
}
did_newline++;
--lexptr; /* pick up } next time */
return lasttok = NEWLINE;
case '"':
string:
esc_seen = FALSE;
while ((c = nextc()) != '"') {
if (c == '\n') {
pushback();
yyerror(_("unterminated string"));
exit(1);
}
#ifdef MBS_SUPPORT
if (gawk_mb_cur_max == 1 || nextc_is_1stbyte)
#endif
if (c == '\\') {
c = nextc();
if (c == '\n') {
sourceline++;
continue;
}
esc_seen = TRUE;
tokadd('\\');
}
if (c == EOF) {
pushback();
yyerror(_("unterminated string"));
exit(1);
}
tokadd(c);
}
yylval.nodeval = make_str_node(tokstart,
tok - tokstart, esc_seen ? SCAN : 0);
yylval.nodeval->flags |= PERM;
if (intlstr) {
yylval.nodeval->flags |= INTLSTR;
intlstr = FALSE;
if (do_intl)
dumpintlstr(yylval.nodeval->stptr,
yylval.nodeval->stlen);
}
return lasttok = YSTRING;
case '-':
if ((c = nextc()) == '=') {
yylval.nodetypeval = Node_assign_minus;
return lasttok = ASSIGNOP;
}
if (c == '-')
return lasttok = DECREMENT;
pushback();
return lasttok = '-';
case '.':
c = nextc();
pushback();
if (! ISDIGIT(c))
return lasttok = '.';
else
c = '.';
/* FALL THROUGH */
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
/* It's a number */
for (;;) {
int gotnumber = FALSE;
tokadd(c);
switch (c) {
case 'x':
case 'X':
if (do_traditional)
goto done;
if (tok == tokstart + 2)
inhex = TRUE;
break;
case '.':
if (seen_point) {
gotnumber = TRUE;
break;
}
seen_point = TRUE;
break;
case 'e':
case 'E':
if (inhex)
break;
if (seen_e) {
gotnumber = TRUE;
break;
}
seen_e = TRUE;
if ((c = nextc()) == '-' || c == '+')
tokadd(c);
else
pushback();
break;
case 'a':
case 'A':
case 'b':
case 'B':
case 'c':
case 'C':
case 'D':
case 'd':
case 'f':
case 'F':
if (do_traditional || ! inhex)
goto done;
/* fall through */
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
break;
default:
done:
gotnumber = TRUE;
}
if (gotnumber)
break;
c = nextc();
}
if (c != EOF)
pushback();
else if (do_lint && ! eof_warned) {
lintwarn(_("source file does not end in newline"));
eof_warned = TRUE;
}
tokadd('\0');
if (! do_traditional && isnondecimal(tokstart)) {
static short warned = FALSE;
if (do_lint && ! warned) {
warned = TRUE;
lintwarn("numeric constant `%.*s' treated as octal or hexadecimal",
strlen(tokstart)-1, tokstart);
}
yylval.nodeval = make_number(nondec2awknum(tokstart, strlen(tokstart)));
} else
yylval.nodeval = make_number(atof(tokstart));
yylval.nodeval->flags |= PERM;
return lasttok = YNUMBER;
case '&':
if ((c = nextc()) == '&') {
yylval.nodetypeval = Node_and;
allow_newline();
return lasttok = LEX_AND;
}
pushback();
return lasttok = '&';
case '|':
if ((c = nextc()) == '|') {
yylval.nodetypeval = Node_or;
allow_newline();
return lasttok = LEX_OR;
} else if (! do_traditional && c == '&') {
yylval.nodetypeval = Node_redirect_twoway;
return lasttok = (in_print && in_parens == 0 ? IO_OUT : IO_IN);
}
pushback();
if (in_print && in_parens == 0) {
yylval.nodetypeval = Node_redirect_pipe;
return lasttok = IO_OUT;
} else {
yylval.nodetypeval = Node_redirect_pipein;
return lasttok = IO_IN;
}
}
if (c != '_' && ! ISALPHA(c)) {
yyerror(_("invalid char '%c' in expression"), c);
exit(1);
}
/*
* Lots of fog here. Consider:
*
* print "xyzzy"$_"foo"
*
* Without the check for ` lasttok != '$'' ', this is parsed as
*
* print "xxyzz" $(_"foo")
*
* With the check, it is "correctly" parsed as three
* string concatenations. Sigh. This seems to be
* "more correct", but this is definitely one of those
* occasions where the interactions are funny.
*/
if (! do_traditional && c == '_' && lasttok != '$') {
if ((c = nextc()) == '"') {
intlstr = TRUE;
goto string;
}
pushback();
c = '_';
}
/* it's some type of name-type-thing. Find its length. */
tok = tokstart;
while (is_identchar(c)) {
tokadd(c);
c = nextc();
}
tokadd('\0');
emalloc(tokkey, char *, tok - tokstart, "yylex");
memcpy(tokkey, tokstart, tok - tokstart);
if (c != EOF)
pushback();
else if (do_lint && ! eof_warned) {
lintwarn(_("source file does not end in newline"));
eof_warned = TRUE;
}
/* See if it is a special token. */
low = 0;
high = (sizeof(tokentab) / sizeof(tokentab[0])) - 1;
while (low <= high) {
int i;
mid = (low + high) / 2;
c = *tokstart - tokentab[mid].operator[0];
i = c ? c : strcmp(tokstart, tokentab[mid].operator);
if (i < 0) /* token < mid */
high = mid - 1;
else if (i > 0) /* token > mid */
low = mid + 1;
else {
if (do_lint) {
if (tokentab[mid].flags & GAWKX)
lintwarn(_("`%s' is a gawk extension"),
tokentab[mid].operator);
if (tokentab[mid].flags & RESX)
lintwarn(_("`%s' is a Bell Labs extension"),
tokentab[mid].operator);
if (tokentab[mid].flags & NOT_POSIX)
lintwarn(_("POSIX does not allow `%s'"),
tokentab[mid].operator);
}
if (do_lint_old && (tokentab[mid].flags & NOT_OLD))
warning(_("`%s' is not supported in old awk"),
tokentab[mid].operator);
if ((do_traditional && (tokentab[mid].flags & GAWKX))
|| (do_posix && (tokentab[mid].flags & NOT_POSIX)))
break;
if (tokentab[mid].class == LEX_BUILTIN
|| tokentab[mid].class == LEX_LENGTH
)
yylval.lval = mid;
else
yylval.nodetypeval = tokentab[mid].value;
free(tokkey);
return lasttok = tokentab[mid].class;
}
}
yylval.sval = tokkey;
if (*lexptr == '(')
return lasttok = FUNC_CALL;
else {
static short goto_warned = FALSE;
#define SMART_ALECK 1
if (SMART_ALECK && do_lint
&& ! goto_warned && strcasecmp(tokkey, "goto") == 0) {
goto_warned = TRUE;
lintwarn(_("`goto' considered harmful!\n"));
}
return lasttok = NAME;
}
}
/* node_common --- common code for allocating a new node */
static NODE *
node_common(NODETYPE op)
{
register NODE *r;
getnode(r);
r->type = op;
r->flags = MALLOC;
if (r->type == Node_var)
r->flags |= UNINITIALIZED;
/* if lookahead is NL, lineno is 1 too high */
if (lexeme && *lexeme == '\n')
r->source_line = sourceline - 1;
else
r->source_line = sourceline;
r->source_file = source;
return r;
}
/* node --- allocates a node with defined lnode and rnode. */
NODE *
node(NODE *left, NODETYPE op, NODE *right)
{
register NODE *r;
r = node_common(op);
r->lnode = left;
r->rnode = right;
return r;
}
/* snode --- allocate a node with defined subnode and builtin for builtin
functions. Checks for arg. count and supplies defaults where
possible. */
static NODE *
snode(NODE *subn, NODETYPE op, int idx)
{
register NODE *r;
register NODE *n;
int nexp = 0;
int args_allowed;
r = node_common(op);
/* traverse expression list to see how many args. given */
for (n = subn; n != NULL; n = n->rnode) {
nexp++;
if (nexp > 5)
break;
}
/* check against how many args. are allowed for this builtin */
args_allowed = tokentab[idx].flags & ARGS;
if (args_allowed && (args_allowed & A(nexp)) == 0)
fatal(_("%d is invalid as number of arguments for %s"),
nexp, tokentab[idx].operator);
r->builtin = tokentab[idx].ptr;
/* special case processing for a few builtins */
if (nexp == 0 && r->builtin == do_length) {
subn = node(node(make_number(0.0), Node_field_spec, (NODE *) NULL),
Node_expression_list,
(NODE *) NULL);
} else if (r->builtin == do_match) {
static short warned = FALSE;
if (subn->rnode->lnode->type != Node_regex)
subn->rnode->lnode = mk_rexp(subn->rnode->lnode);
if (subn->rnode->rnode != NULL) { /* 3rd argument there */
if (do_lint && ! warned) {
warned = TRUE;
lintwarn(_("match: third argument is a gawk extension"));
}
if (do_traditional)
fatal(_("match: third argument is a gawk extension"));
}
} else if (r->builtin == do_sub || r->builtin == do_gsub) {
if (subn->lnode->type != Node_regex)
subn->lnode = mk_rexp(subn->lnode);
if (nexp == 2)
append_right(subn, node(node(make_number(0.0),
Node_field_spec,
(NODE *) NULL),
Node_expression_list,
(NODE *) NULL));
else if (subn->rnode->rnode->lnode->type == Node_val) {
if (do_lint)
lintwarn(_("%s: string literal as last arg of substitute has no effect"),
(r->builtin == do_sub) ? "sub" : "gsub");
} else if (! isassignable(subn->rnode->rnode->lnode)) {
yyerror(_("%s third parameter is not a changeable object"),
(r->builtin == do_sub) ? "sub" : "gsub");
}
} else if (r->builtin == do_gensub) {
if (subn->lnode->type != Node_regex)
subn->lnode = mk_rexp(subn->lnode);
if (nexp == 3)
append_right(subn, node(node(make_number(0.0),
Node_field_spec,
(NODE *) NULL),
Node_expression_list,
(NODE *) NULL));
} else if (r->builtin == do_split) {
if (nexp == 2)
append_right(subn,
node(FS_node, Node_expression_list, (NODE *) NULL));
n = subn->rnode->rnode->lnode;
if (n->type != Node_regex)
subn->rnode->rnode->lnode = mk_rexp(n);
if (nexp == 2)
subn->rnode->rnode->lnode->re_flags |= FS_DFLT;
} else if (r->builtin == do_close) {
static short warned = FALSE;
if ( nexp == 2) {
if (do_lint && nexp == 2 && ! warned) {
warned = TRUE;
lintwarn(_("close: second argument is a gawk extension"));
}
if (do_traditional)
fatal(_("close: second argument is a gawk extension"));
}
} else if (do_intl /* --gen-po */
&& r->builtin == do_dcgettext /* dcgettext(...) */
&& subn->lnode->type == Node_val /* 1st arg is constant */
&& (subn->lnode->flags & STRCUR) != 0) { /* it's a string constant */
/* ala xgettext, dcgettext("some string" ...) dumps the string */
NODE *str = subn->lnode;
if ((str->flags & INTLSTR) != 0)
warning(_("use of dcgettext(_\"...\") is incorrect: remove leading underscore"));
/* don't dump it, the lexer already did */
else
dumpintlstr(str->stptr, str->stlen);
} else if (do_intl /* --gen-po */
&& r->builtin == do_dcngettext /* dcngettext(...) */
&& subn->lnode->type == Node_val /* 1st arg is constant */
&& (subn->lnode->flags & STRCUR) != 0 /* it's a string constant */
&& subn->rnode->lnode->type == Node_val /* 2nd arg is constant too */
&& (subn->rnode->lnode->flags & STRCUR) != 0) { /* it's a string constant */
/* ala xgettext, dcngettext("some string", "some plural" ...) dumps the string */
NODE *str1 = subn->lnode;
NODE *str2 = subn->rnode->lnode;
if (((str1->flags | str2->flags) & INTLSTR) != 0)
warning(_("use of dcngettext(_\"...\") is incorrect: remove leading underscore"));
else
dumpintlstr2(str1->stptr, str1->stlen, str2->stptr, str2->stlen);
}
r->subnode = subn;
if (r->builtin == do_sprintf) {
count_args(r);
r->lnode->printf_count = r->printf_count; /* hack */
}
return r;
}
/* make_for_loop --- build a for loop */
static NODE *
make_for_loop(NODE *init, NODE *cond, NODE *incr)
{
register FOR_LOOP_HEADER *r;
NODE *n;
emalloc(r, FOR_LOOP_HEADER *, sizeof(FOR_LOOP_HEADER), "make_for_loop");
getnode(n);
n->type = Node_illegal;
r->init = init;
r->cond = cond;
r->incr = incr;
n->sub.nodep.r.hd = r;
return n;
}
/* dup_parms --- return TRUE if there are duplicate parameters */
static int
dup_parms(NODE *func)
{
register NODE *np;
const char *fname, **names;
int count, i, j, dups;
NODE *params;
if (func == NULL) /* error earlier */
return TRUE;
fname = func->param;
count = func->param_cnt;
params = func->rnode;
if (count == 0) /* no args, no problem */
return FALSE;
if (params == NULL) /* error earlier */
return TRUE;
emalloc(names, const char **, count * sizeof(char *), "dup_parms");
i = 0;
for (np = params; np != NULL; np = np->rnode) {
if (np->param == NULL) { /* error earlier, give up, go home */
free(names);
return TRUE;
}
names[i++] = np->param;
}
dups = 0;
for (i = 1; i < count; i++) {
for (j = 0; j < i; j++) {
if (strcmp(names[i], names[j]) == 0) {
dups++;
error(
_("function `%s': parameter #%d, `%s', duplicates parameter #%d"),
fname, i+1, names[j], j+1);
}
}
}
free(names);
return (dups > 0 ? TRUE : FALSE);
}
/* parms_shadow --- check if parameters shadow globals */
static int
parms_shadow(const char *fname, NODE *func)
{
int count, i;
int ret = FALSE;
if (fname == NULL || func == NULL) /* error earlier */
return FALSE;
count = func->lnode->param_cnt;
if (count == 0) /* no args, no problem */
return FALSE;
/*
* Use warning() and not lintwarn() so that can warn
* about all shadowed parameters.
*/
for (i = 0; i < count; i++) {
if (lookup(func->parmlist[i]) != NULL) {
warning(
_("function `%s': parameter `%s' shadows global variable"),
fname, func->parmlist[i]);
ret = TRUE;
}
}
return ret;
}
/*
* install:
* Install a name in the symbol table, even if it is already there.
* Caller must check against redefinition if that is desired.
*/
NODE *
install(char *name, NODE *value)
{
register NODE *hp;
register size_t len;
register int bucket;
var_count++;
len = strlen(name);
bucket = hash(name, len, (unsigned long) HASHSIZE);
getnode(hp);
hp->type = Node_hashnode;
hp->hnext = variables[bucket];
variables[bucket] = hp;
hp->hlength = len;
hp->hvalue = value;
hp->hname = name;
hp->hvalue->vname = name;
return hp->hvalue;
}
/* lookup --- find the most recent hash node for name installed by install */
NODE *
lookup(const char *name)
{
register NODE *bucket;
register size_t len;
len = strlen(name);
for (bucket = variables[hash(name, len, (unsigned long) HASHSIZE)];
bucket != NULL; bucket = bucket->hnext)
if (bucket->hlength == len && STREQN(bucket->hname, name, len))
return bucket->hvalue;
return NULL;
}
/* var_comp --- compare two variable names */
static int
var_comp(const void *v1, const void *v2)
{
const NODE *const *npp1, *const *npp2;
const NODE *n1, *n2;
int minlen;
npp1 = (const NODE *const *) v1;
npp2 = (const NODE *const *) v2;
n1 = *npp1;
n2 = *npp2;
if (n1->hlength > n2->hlength)
minlen = n1->hlength;
else
minlen = n2->hlength;
return strncmp(n1->hname, n2->hname, minlen);
}
/* valinfo --- dump var info */
static void
valinfo(NODE *n, FILE *fp)
{
if (n->flags & STRING) {
fprintf(fp, "string (");
pp_string_fp(fp, n->stptr, n->stlen, '"', FALSE);
fprintf(fp, ")\n");
} else if (n->flags & NUMBER)
fprintf(fp, "number (%.17g)\n", n->numbr);
else if (n->flags & STRCUR) {
fprintf(fp, "string value (");
pp_string_fp(fp, n->stptr, n->stlen, '"', FALSE);
fprintf(fp, ")\n");
} else if (n->flags & NUMCUR)
fprintf(fp, "number value (%.17g)\n", n->numbr);
else
fprintf(fp, "?? flags %s\n", flags2str(n->flags));
}
/* dump_vars --- dump the symbol table */
void
dump_vars(const char *fname)
{
int i, j;
NODE **table;
NODE *p;
FILE *fp;
emalloc(table, NODE **, var_count * sizeof(NODE *), "dump_vars");
if (fname == NULL)
fp = stderr;
else if ((fp = fopen(fname, "w")) == NULL) {
warning(_("could not open `%s' for writing (%s)"), fname, strerror(errno));
warning(_("sending profile to standard error"));
fp = stderr;
}
for (i = j = 0; i < HASHSIZE; i++)
for (p = variables[i]; p != NULL; p = p->hnext)
table[j++] = p;
assert(j == var_count);
/* Shazzam! */
qsort(table, j, sizeof(NODE *), var_comp);
for (i = 0; i < j; i++) {
p = table[i];
if (p->hvalue->type == Node_func)
continue;
fprintf(fp, "%.*s: ", (int) p->hlength, p->hname);
if (p->hvalue->type == Node_var_array)
fprintf(fp, "array, %ld elements\n", p->hvalue->table_size);
else if (p->hvalue->type == Node_var)
valinfo(p->hvalue->var_value, fp);
else {
NODE **lhs = get_lhs(p->hvalue, NULL, FALSE);
valinfo(*lhs, fp);
}
}
if (fp != stderr && fclose(fp) != 0)
warning(_("%s: close failed (%s)"), fname, strerror(errno));
free(table);
}
/* release_all_vars --- free all variable memory */
void
release_all_vars()
{
int i;
NODE *p, *next;
for (i = 0; i < HASHSIZE; i++)
for (p = variables[i]; p != NULL; p = next) {
next = p->hnext;
if (p->hvalue->type == Node_func)
continue;
else if (p->hvalue->type == Node_var_array)
assoc_clear(p->hvalue);
else if (p->hvalue->type == Node_var)
unref(p->hvalue->var_value);
else {
NODE **lhs = get_lhs(p->hvalue, NULL, FALSE);
unref((*lhs)->var_value);
}
unref(p);
}
}
/* finfo --- for use in comparison and sorting of function names */
struct finfo {
const char *name;
size_t nlen;
NODE *func;
};
/* fcompare --- comparison function for qsort */
static int
fcompare(const void *p1, const void *p2)
{
const struct finfo *f1, *f2;
int minlen;
f1 = (const struct finfo *) p1;
f2 = (const struct finfo *) p2;
if (f1->nlen > f2->nlen)
minlen = f2->nlen;
else
minlen = f1->nlen;
return strncmp(f1->name, f2->name, minlen);
}
/* dump_funcs --- print all functions */
void
dump_funcs()
{
int i, j;
NODE *p;
static struct finfo *tab = NULL;
if (func_count == 0)
return;
/*
* Walk through symbol table countng functions.
* Could be more than func_count if there are
* extension functions.
*/
for (i = j = 0; i < HASHSIZE; i++) {
for (p = variables[i]; p != NULL; p = p->hnext) {
if (p->hvalue->type == Node_func) {
j++;
}
}
}
if (tab == NULL)
emalloc(tab, struct finfo *, j * sizeof(struct finfo), "dump_funcs");
/* now walk again, copying info */
for (i = j = 0; i < HASHSIZE; i++) {
for (p = variables[i]; p != NULL; p = p->hnext) {
if (p->hvalue->type == Node_func) {
tab[j].name = p->hname;
tab[j].nlen = p->hlength;
tab[j].func = p->hvalue;
j++;
}
}
}
/* Shazzam! */
qsort(tab, j, sizeof(struct finfo), fcompare);
for (i = 0; i < j; i++)
pp_func(tab[i].name, tab[i].nlen, tab[i].func);
free(tab);
}
/* shadow_funcs --- check all functions for parameters that shadow globals */
void
shadow_funcs()
{
int i, j;
NODE *p;
struct finfo *tab;
static int calls = 0;
int shadow = FALSE;
if (func_count == 0)
return;
if (calls++ != 0)
fatal(_("shadow_funcs() called twice!"));
emalloc(tab, struct finfo *, func_count * sizeof(struct finfo), "shadow_funcs");
for (i = j = 0; i < HASHSIZE; i++) {
for (p = variables[i]; p != NULL; p = p->hnext) {
if (p->hvalue->type == Node_func) {
tab[j].name = p->hname;
tab[j].nlen = p->hlength;
tab[j].func = p->hvalue;
j++;
}
}
}
assert(j == func_count);
/* Shazzam! */
qsort(tab, func_count, sizeof(struct finfo), fcompare);
for (i = 0; i < j; i++)
shadow |= parms_shadow(tab[i].name, tab[i].func);
free(tab);
/* End with fatal if the user requested it. */
if (shadow && lintfunc != warning)
lintwarn(_("there were shadowed variables."));
}
/*
* append_right:
* Add new to the rightmost branch of LIST. This uses n^2 time, so we make
* a simple attempt at optimizing it.
*/
static NODE *
append_right(NODE *list, NODE *new)
{
register NODE *oldlist;
static NODE *savefront = NULL, *savetail = NULL;
if (list == NULL || new == NULL)
return list;
oldlist = list;
if (savefront == oldlist) {
savetail = savetail->rnode = new;
return oldlist;
} else
savefront = oldlist;
while (list->rnode != NULL)
list = list->rnode;
savetail = list->rnode = new;
return oldlist;
}
/*
* append_pattern:
* A wrapper around append_right, used for rule lists.
*/
static inline NODE *
append_pattern(NODE **list, NODE *patt)
{
NODE *n = node(patt, Node_rule_node, (NODE *) NULL);
if (*list == NULL)
*list = n;
else {
NODE *n1 = node(n, Node_rule_list, (NODE *) NULL);
if ((*list)->type != Node_rule_list)
*list = node(*list, Node_rule_list, n1);
else
(void) append_right(*list, n1);
}
return n;
}
/*
* func_install:
* check if name is already installed; if so, it had better have Null value,
* in which case def is added as the value. Otherwise, install name with def
* as value.
*
* Extra work, build up and save a list of the parameter names in a table
* and hang it off params->parmlist. This is used to set the `vname' field
* of each function parameter during a function call. See eval.c.
*/
static void
func_install(NODE *params, NODE *def)
{
NODE *r, *n, *thisfunc;
char **pnames, *names, *sp;
size_t pcount = 0, space = 0;
int i;
/* check for function foo(foo) { ... }. bleah. */
for (n = params->rnode; n != NULL; n = n->rnode) {
if (strcmp(n->param, params->param) == 0)
fatal(_("function `%s': can't use function name as parameter name"),
params->param);
}
thisfunc = NULL; /* turn off warnings */
/* symbol table managment */
pop_var(params, FALSE);
r = lookup(params->param);
if (r != NULL) {
fatal(_("function name `%s' previously defined"), params->param);
} else if (params->param == builtin_func) /* not a valid function name */
goto remove_params;
/* install the function */
thisfunc = node(params, Node_func, def);
(void) install(params->param, thisfunc);
/* figure out amount of space to allocate for variable names */
for (n = params->rnode; n != NULL; n = n->rnode) {
pcount++;
space += strlen(n->param) + 1;
}
/* allocate it and fill it in */
if (pcount != 0) {
emalloc(names, char *, space, "func_install");
emalloc(pnames, char **, pcount * sizeof(char *), "func_install");
sp = names;
for (i = 0, n = params->rnode; i < pcount; i++, n = n->rnode) {
pnames[i] = sp;
strcpy(sp, n->param);
sp += strlen(n->param) + 1;
}
thisfunc->parmlist = pnames;
} else {
thisfunc->parmlist = NULL;
}
/* update lint table info */
func_use(params->param, FUNC_DEFINE);
func_count++; /* used by profiling / pretty printer */
remove_params:
/* remove params from symbol table */
pop_params(params->rnode);
}
/* pop_var --- remove a variable from the symbol table */
static void
pop_var(NODE *np, int freeit)
{
register NODE *bucket, **save;
register size_t len;
char *name;
name = np->param;
len = strlen(name);
save = &(variables[hash(name, len, (unsigned long) HASHSIZE)]);
for (bucket = *save; bucket != NULL; bucket = bucket->hnext) {
if (len == bucket->hlength && STREQN(bucket->hname, name, len)) {
var_count--;
*save = bucket->hnext;
freenode(bucket);
if (freeit)
free(np->param);
return;
}
save = &(bucket->hnext);
}
}
/* pop_params --- remove list of function parameters from symbol table */
/*
* pop parameters out of the symbol table. do this in reverse order to
* avoid reading freed memory if there were duplicated parameters.
*/
static void
pop_params(NODE *params)
{
if (params == NULL)
return;
pop_params(params->rnode);
pop_var(params, TRUE);
}
/* make_param --- make NAME into a function parameter */
static NODE *
make_param(char *name)
{
NODE *r;
getnode(r);
r->type = Node_param_list;
r->rnode = NULL;
r->param = name;
r->param_cnt = param_counter++;
return (install(name, r));
}
static struct fdesc {
char *name;
short used;
short defined;
struct fdesc *next;
} *ftable[HASHSIZE];
/* func_use --- track uses and definitions of functions */
static void
func_use(const char *name, enum defref how)
{
struct fdesc *fp;
int len;
int ind;
len = strlen(name);
ind = hash(name, len, HASHSIZE);
for (fp = ftable[ind]; fp != NULL; fp = fp->next) {
if (strcmp(fp->name, name) == 0) {
if (how == FUNC_DEFINE)
fp->defined++;
else
fp->used++;
return;
}
}
/* not in the table, fall through to allocate a new one */
emalloc(fp, struct fdesc *, sizeof(struct fdesc), "func_use");
memset(fp, '\0', sizeof(struct fdesc));
emalloc(fp->name, char *, len + 1, "func_use");
strcpy(fp->name, name);
if (how == FUNC_DEFINE)
fp->defined++;
else
fp->used++;
fp->next = ftable[ind];
ftable[ind] = fp;
}
/* check_funcs --- verify functions that are called but not defined */
static void
check_funcs()
{
struct fdesc *fp, *next;
int i;
for (i = 0; i < HASHSIZE; i++) {
for (fp = ftable[i]; fp != NULL; fp = fp->next) {
#ifdef REALLYMEAN
/* making this the default breaks old code. sigh. */
if (fp->defined == 0) {
error(
_("function `%s' called but never defined"), fp->name);
errcount++;
}
#else
if (do_lint && fp->defined == 0)
lintwarn(
_("function `%s' called but never defined"), fp->name);
#endif
if (do_lint && fp->used == 0) {
lintwarn(_("function `%s' defined but never called"),
fp->name);
}
}
}
/* now let's free all the memory */
for (i = 0; i < HASHSIZE; i++) {
for (fp = ftable[i]; fp != NULL; fp = next) {
next = fp->next;
free(fp->name);
free(fp);
}
}
}
/* param_sanity --- look for parameters that are regexp constants */
static void
param_sanity(NODE *arglist)
{
NODE *argp, *arg;
int i;
for (i = 1, argp = arglist; argp != NULL; argp = argp->rnode, i++) {
arg = argp->lnode;
if (arg->type == Node_regex)
warning(_("regexp constant for parameter #%d yields boolean value"), i);
}
}
/* variable --- make sure NAME is in the symbol table */
NODE *
variable(char *name, int can_free, NODETYPE type)
{
register NODE *r;
if ((r = lookup(name)) != NULL) {
if (r->type == Node_func)
fatal(_("function `%s' called with space between name and `(',\n%s"),
r->vname,
_("or used as a variable or an array"));
} else {
/* not found */
if (! do_traditional && STREQ(name, "PROCINFO"))
r = load_procinfo();
else if (STREQ(name, "ENVIRON"))
r = load_environ();
else {
/*
* This is the only case in which we may not free the string.
*/
return install(name, node(Nnull_string, type, (NODE *) NULL));
}
}
if (can_free)
free(name);
return r;
}
/* mk_rexp --- make a regular expression constant */
static NODE *
mk_rexp(NODE *exp)
{
NODE *n;
if (exp->type == Node_regex)
return exp;
getnode(n);
n->type = Node_dynregex;
n->re_exp = exp;
n->re_text = NULL;
n->re_reg = NULL;
n->re_flags = 0;
return n;
}
/* isnoeffect --- when used as a statement, has no side effects */
/*
* To be completely general, we should recursively walk the parse
* tree, to make sure that all the subexpressions also have no effect.
* Instead, we just weaken the actual warning that's printed, up above
* in the grammar.
*/
static int
isnoeffect(NODETYPE type)
{
switch (type) {
case Node_times:
case Node_quotient:
case Node_mod:
case Node_plus:
case Node_minus:
case Node_subscript:
case Node_concat:
case Node_exp:
case Node_unary_minus:
case Node_field_spec:
case Node_and:
case Node_or:
case Node_equal:
case Node_notequal:
case Node_less:
case Node_greater:
case Node_leq:
case Node_geq:
case Node_match:
case Node_nomatch:
case Node_not:
case Node_val:
case Node_in_array:
case Node_NF:
case Node_NR:
case Node_FNR:
case Node_FS:
case Node_RS:
case Node_FIELDWIDTHS:
case Node_IGNORECASE:
case Node_OFS:
case Node_ORS:
case Node_OFMT:
case Node_CONVFMT:
case Node_BINMODE:
case Node_LINT:
return TRUE;
default:
break; /* keeps gcc -Wall happy */
}
return FALSE;
}
/* isassignable --- can this node be assigned to? */
static int
isassignable(register NODE *n)
{
switch (n->type) {
case Node_var:
case Node_FIELDWIDTHS:
case Node_RS:
case Node_FS:
case Node_FNR:
case Node_NR:
case Node_NF:
case Node_IGNORECASE:
case Node_OFMT:
case Node_CONVFMT:
case Node_ORS:
case Node_OFS:
case Node_LINT:
case Node_BINMODE:
case Node_field_spec:
case Node_subscript:
return TRUE;
case Node_param_list:
return ((n->flags & FUNC) == 0); /* ok if not func name */
default:
break; /* keeps gcc -Wall happy */
}
return FALSE;
}
/* stopme --- for debugging */
NODE *
stopme(NODE *tree ATTRIBUTE_UNUSED)
{
return 0;
}
/* dumpintlstr --- write out an initial .po file entry for the string */
static void
dumpintlstr(const char *str, size_t len)
{
char *cp;
/* See the GNU gettext distribution for details on the file format */
if (source != NULL) {
/* ala the gettext sources, remove leading `./'s */
for (cp = source; cp[0] == '.' && cp[1] == '/'; cp += 2)
continue;
printf("#: %s:%d\n", cp, sourceline);
}
printf("msgid ");
pp_string_fp(stdout, str, len, '"', TRUE);
putchar('\n');
printf("msgstr \"\"\n\n");
fflush(stdout);
}
/* dumpintlstr2 --- write out an initial .po file entry for the string and its plural */
static void
dumpintlstr2(const char *str1, size_t len1, const char *str2, size_t len2)
{
char *cp;
/* See the GNU gettext distribution for details on the file format */
if (source != NULL) {
/* ala the gettext sources, remove leading `./'s */
for (cp = source; cp[0] == '.' && cp[1] == '/'; cp += 2)
continue;
printf("#: %s:%d\n", cp, sourceline);
}
printf("msgid ");
pp_string_fp(stdout, str1, len1, '"', TRUE);
putchar('\n');
printf("msgid_plural ");
pp_string_fp(stdout, str2, len2, '"', TRUE);
putchar('\n');
printf("msgstr[0] \"\"\nmsgstr[1] \"\"\n\n");
fflush(stdout);
}
/* count_args --- count the number of printf arguments */
static void
count_args(NODE *tree)
{
size_t count = 0;
NODE *save_tree;
assert(tree->type == Node_K_printf
|| (tree->type == Node_builtin && tree->builtin == do_sprintf));
save_tree = tree;
tree = tree->lnode; /* printf format string */
for (count = 0; tree != NULL; tree = tree->rnode)
count++;
save_tree->printf_count = count;
}
|