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
| //===--- PPDirectives.cpp - Directive Handling for Preprocessor -----------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
///
/// \file
/// Implements # directive processing for the Preprocessor.
///
//===----------------------------------------------------------------------===//
#include "clang/Basic/CharInfo.h"
#include "clang/Basic/FileManager.h"
#include "clang/Basic/IdentifierTable.h"
#include "clang/Basic/LangOptions.h"
#include "clang/Basic/Module.h"
#include "clang/Basic/SourceLocation.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Basic/TokenKinds.h"
#include "clang/Lex/CodeCompletionHandler.h"
#include "clang/Lex/HeaderSearch.h"
#include "clang/Lex/LexDiagnostic.h"
#include "clang/Lex/LiteralSupport.h"
#include "clang/Lex/MacroInfo.h"
#include "clang/Lex/ModuleLoader.h"
#include "clang/Lex/ModuleMap.h"
#include "clang/Lex/PPCallbacks.h"
#include "clang/Lex/Pragma.h"
#include "clang/Lex/Preprocessor.h"
#include "clang/Lex/PreprocessorOptions.h"
#include "clang/Lex/Token.h"
#include "clang/Lex/VariadicMacroSupport.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/ScopeExit.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Support/AlignOf.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/Path.h"
#include <algorithm>
#include <cassert>
#include <cstring>
#include <new>
#include <string>
#include <utility>
using namespace clang;
//===----------------------------------------------------------------------===//
// Utility Methods for Preprocessor Directive Handling.
//===----------------------------------------------------------------------===//
MacroInfo *Preprocessor::AllocateMacroInfo(SourceLocation L) {
auto *MIChain = new (BP) MacroInfoChain{L, MIChainHead};
MIChainHead = MIChain;
return &MIChain->MI;
}
DefMacroDirective *Preprocessor::AllocateDefMacroDirective(MacroInfo *MI,
SourceLocation Loc) {
return new (BP) DefMacroDirective(MI, Loc);
}
UndefMacroDirective *
Preprocessor::AllocateUndefMacroDirective(SourceLocation UndefLoc) {
return new (BP) UndefMacroDirective(UndefLoc);
}
VisibilityMacroDirective *
Preprocessor::AllocateVisibilityMacroDirective(SourceLocation Loc,
bool isPublic) {
return new (BP) VisibilityMacroDirective(Loc, isPublic);
}
/// Read and discard all tokens remaining on the current line until
/// the tok::eod token is found.
SourceRange Preprocessor::DiscardUntilEndOfDirective() {
Token Tmp;
SourceRange Res;
LexUnexpandedToken(Tmp);
Res.setBegin(Tmp.getLocation());
while (Tmp.isNot(tok::eod)) {
assert(Tmp.isNot(tok::eof) && "EOF seen while discarding directive tokens");
LexUnexpandedToken(Tmp);
}
Res.setEnd(Tmp.getLocation());
return Res;
}
/// Enumerates possible cases of #define/#undef a reserved identifier.
enum MacroDiag {
MD_NoWarn, //> Not a reserved identifier
MD_KeywordDef, //> Macro hides keyword, enabled by default
MD_ReservedMacro //> #define of #undef reserved id, disabled by default
};
/// Checks if the specified identifier is reserved in the specified
/// language.
/// This function does not check if the identifier is a keyword.
static bool isReservedId(StringRef Text, const LangOptions &Lang) {
// C++ [macro.names], C11 7.1.3:
// All identifiers that begin with an underscore and either an uppercase
// letter or another underscore are always reserved for any use.
if (Text.size() >= 2 && Text[0] == '_' &&
(isUppercase(Text[1]) || Text[1] == '_'))
return true;
// C++ [global.names]
// Each name that contains a double underscore ... is reserved to the
// implementation for any use.
if (Lang.CPlusPlus) {
if (Text.find("__") != StringRef::npos)
return true;
}
return false;
}
// The -fmodule-name option tells the compiler to textually include headers in
// the specified module, meaning clang won't build the specified module. This is
// useful in a number of situations, for instance, when building a library that
// vends a module map, one might want to avoid hitting intermediate build
// products containimg the the module map or avoid finding the system installed
// modulemap for that library.
static bool isForModuleBuilding(Module *M, StringRef CurrentModule,
StringRef ModuleName) {
StringRef TopLevelName = M->getTopLevelModuleName();
// When building framework Foo, we wanna make sure that Foo *and* Foo_Private
// are textually included and no modules are built for both.
if (M->getTopLevelModule()->IsFramework && CurrentModule == ModuleName &&
!CurrentModule.endswith("_Private") && TopLevelName.endswith("_Private"))
TopLevelName = TopLevelName.drop_back(8);
return TopLevelName == CurrentModule;
}
static MacroDiag shouldWarnOnMacroDef(Preprocessor &PP, IdentifierInfo *II) {
const LangOptions &Lang = PP.getLangOpts();
StringRef Text = II->getName();
if (isReservedId(Text, Lang))
return MD_ReservedMacro;
if (II->isKeyword(Lang))
return MD_KeywordDef;
if (Lang.CPlusPlus11 && (Text.equals("override") || Text.equals("final")))
return MD_KeywordDef;
return MD_NoWarn;
}
static MacroDiag shouldWarnOnMacroUndef(Preprocessor &PP, IdentifierInfo *II) {
const LangOptions &Lang = PP.getLangOpts();
StringRef Text = II->getName();
// Do not warn on keyword undef. It is generally harmless and widely used.
if (isReservedId(Text, Lang))
return MD_ReservedMacro;
return MD_NoWarn;
}
// Return true if we want to issue a diagnostic by default if we
// encounter this name in a #include with the wrong case. For now,
// this includes the standard C and C++ headers, Posix headers,
// and Boost headers. Improper case for these #includes is a
// potential portability issue.
static bool warnByDefaultOnWrongCase(StringRef Include) {
// If the first component of the path is "boost", treat this like a standard header
// for the purposes of diagnostics.
if (::llvm::sys::path::begin(Include)->equals_lower("boost"))
return true;
// "condition_variable" is the longest standard header name at 18 characters.
// If the include file name is longer than that, it can't be a standard header.
static const size_t MaxStdHeaderNameLen = 18u;
if (Include.size() > MaxStdHeaderNameLen)
return false;
// Lowercase and normalize the search string.
SmallString<32> LowerInclude{Include};
for (char &Ch : LowerInclude) {
// In the ASCII range?
if (static_cast<unsigned char>(Ch) > 0x7f)
return false; // Can't be a standard header
// ASCII lowercase:
if (Ch >= 'A' && Ch <= 'Z')
Ch += 'a' - 'A';
// Normalize path separators for comparison purposes.
else if (::llvm::sys::path::is_separator(Ch))
Ch = '/';
}
// The standard C/C++ and Posix headers
return llvm::StringSwitch<bool>(LowerInclude)
// C library headers
.Cases("assert.h", "complex.h", "ctype.h", "errno.h", "fenv.h", true)
.Cases("float.h", "inttypes.h", "iso646.h", "limits.h", "locale.h", true)
.Cases("math.h", "setjmp.h", "signal.h", "stdalign.h", "stdarg.h", true)
.Cases("stdatomic.h", "stdbool.h", "stddef.h", "stdint.h", "stdio.h", true)
.Cases("stdlib.h", "stdnoreturn.h", "string.h", "tgmath.h", "threads.h", true)
.Cases("time.h", "uchar.h", "wchar.h", "wctype.h", true)
// C++ headers for C library facilities
.Cases("cassert", "ccomplex", "cctype", "cerrno", "cfenv", true)
.Cases("cfloat", "cinttypes", "ciso646", "climits", "clocale", true)
.Cases("cmath", "csetjmp", "csignal", "cstdalign", "cstdarg", true)
.Cases("cstdbool", "cstddef", "cstdint", "cstdio", "cstdlib", true)
.Cases("cstring", "ctgmath", "ctime", "cuchar", "cwchar", true)
.Case("cwctype", true)
// C++ library headers
.Cases("algorithm", "fstream", "list", "regex", "thread", true)
.Cases("array", "functional", "locale", "scoped_allocator", "tuple", true)
.Cases("atomic", "future", "map", "set", "type_traits", true)
.Cases("bitset", "initializer_list", "memory", "shared_mutex", "typeindex", true)
.Cases("chrono", "iomanip", "mutex", "sstream", "typeinfo", true)
.Cases("codecvt", "ios", "new", "stack", "unordered_map", true)
.Cases("complex", "iosfwd", "numeric", "stdexcept", "unordered_set", true)
.Cases("condition_variable", "iostream", "ostream", "streambuf", "utility", true)
.Cases("deque", "istream", "queue", "string", "valarray", true)
.Cases("exception", "iterator", "random", "strstream", "vector", true)
.Cases("forward_list", "limits", "ratio", "system_error", true)
// POSIX headers (which aren't also C headers)
.Cases("aio.h", "arpa/inet.h", "cpio.h", "dirent.h", "dlfcn.h", true)
.Cases("fcntl.h", "fmtmsg.h", "fnmatch.h", "ftw.h", "glob.h", true)
.Cases("grp.h", "iconv.h", "langinfo.h", "libgen.h", "monetary.h", true)
.Cases("mqueue.h", "ndbm.h", "net/if.h", "netdb.h", "netinet/in.h", true)
.Cases("netinet/tcp.h", "nl_types.h", "poll.h", "pthread.h", "pwd.h", true)
.Cases("regex.h", "sched.h", "search.h", "semaphore.h", "spawn.h", true)
.Cases("strings.h", "stropts.h", "sys/ipc.h", "sys/mman.h", "sys/msg.h", true)
.Cases("sys/resource.h", "sys/select.h", "sys/sem.h", "sys/shm.h", "sys/socket.h", true)
.Cases("sys/stat.h", "sys/statvfs.h", "sys/time.h", "sys/times.h", "sys/types.h", true)
.Cases("sys/uio.h", "sys/un.h", "sys/utsname.h", "sys/wait.h", "syslog.h", true)
.Cases("tar.h", "termios.h", "trace.h", "ulimit.h", true)
.Cases("unistd.h", "utime.h", "utmpx.h", "wordexp.h", true)
.Default(false);
}
bool Preprocessor::CheckMacroName(Token &MacroNameTok, MacroUse isDefineUndef,
bool *ShadowFlag) {
// Missing macro name?
if (MacroNameTok.is(tok::eod))
return Diag(MacroNameTok, diag::err_pp_missing_macro_name);
IdentifierInfo *II = MacroNameTok.getIdentifierInfo();
if (!II)
return Diag(MacroNameTok, diag::err_pp_macro_not_identifier);
if (II->isCPlusPlusOperatorKeyword()) {
// C++ 2.5p2: Alternative tokens behave the same as its primary token
// except for their spellings.
Diag(MacroNameTok, getLangOpts().MicrosoftExt
? diag::ext_pp_operator_used_as_macro_name
: diag::err_pp_operator_used_as_macro_name)
<< II << MacroNameTok.getKind();
// Allow #defining |and| and friends for Microsoft compatibility or
// recovery when legacy C headers are included in C++.
}
if ((isDefineUndef != MU_Other) && II->getPPKeywordID() == tok::pp_defined) {
// Error if defining "defined": C99 6.10.8/4, C++ [cpp.predefined]p4.
return Diag(MacroNameTok, diag::err_defined_macro_name);
}
if (isDefineUndef == MU_Undef) {
auto *MI = getMacroInfo(II);
if (MI && MI->isBuiltinMacro()) {
// Warn if undefining "__LINE__" and other builtins, per C99 6.10.8/4
// and C++ [cpp.predefined]p4], but allow it as an extension.
Diag(MacroNameTok, diag::ext_pp_undef_builtin_macro);
}
}
// If defining/undefining reserved identifier or a keyword, we need to issue
// a warning.
SourceLocation MacroNameLoc = MacroNameTok.getLocation();
if (ShadowFlag)
*ShadowFlag = false;
if (!SourceMgr.isInSystemHeader(MacroNameLoc) &&
(SourceMgr.getBufferName(MacroNameLoc) != "<built-in>")) {
MacroDiag D = MD_NoWarn;
if (isDefineUndef == MU_Define) {
D = shouldWarnOnMacroDef(*this, II);
}
else if (isDefineUndef == MU_Undef)
D = shouldWarnOnMacroUndef(*this, II);
if (D == MD_KeywordDef) {
// We do not want to warn on some patterns widely used in configuration
// scripts. This requires analyzing next tokens, so do not issue warnings
// now, only inform caller.
if (ShadowFlag)
*ShadowFlag = true;
}
if (D == MD_ReservedMacro)
Diag(MacroNameTok, diag::warn_pp_macro_is_reserved_id);
}
// Okay, we got a good identifier.
return false;
}
/// Lex and validate a macro name, which occurs after a
/// \#define or \#undef.
///
/// This sets the token kind to eod and discards the rest of the macro line if
/// the macro name is invalid.
///
/// \param MacroNameTok Token that is expected to be a macro name.
/// \param isDefineUndef Context in which macro is used.
/// \param ShadowFlag Points to a flag that is set if macro shadows a keyword.
void Preprocessor::ReadMacroName(Token &MacroNameTok, MacroUse isDefineUndef,
bool *ShadowFlag) {
// Read the token, don't allow macro expansion on it.
LexUnexpandedToken(MacroNameTok);
if (MacroNameTok.is(tok::code_completion)) {
if (CodeComplete)
CodeComplete->CodeCompleteMacroName(isDefineUndef == MU_Define);
setCodeCompletionReached();
LexUnexpandedToken(MacroNameTok);
}
if (!CheckMacroName(MacroNameTok, isDefineUndef, ShadowFlag))
return;
// Invalid macro name, read and discard the rest of the line and set the
// token kind to tok::eod if necessary.
if (MacroNameTok.isNot(tok::eod)) {
MacroNameTok.setKind(tok::eod);
DiscardUntilEndOfDirective();
}
}
/// Ensure that the next token is a tok::eod token.
///
/// If not, emit a diagnostic and consume up until the eod. If EnableMacros is
/// true, then we consider macros that expand to zero tokens as being ok.
///
/// Returns the location of the end of the directive.
SourceLocation Preprocessor::CheckEndOfDirective(const char *DirType,
bool EnableMacros) {
Token Tmp;
// Lex unexpanded tokens for most directives: macros might expand to zero
// tokens, causing us to miss diagnosing invalid lines. Some directives (like
// #line) allow empty macros.
if (EnableMacros)
Lex(Tmp);
else
LexUnexpandedToken(Tmp);
// There should be no tokens after the directive, but we allow them as an
// extension.
while (Tmp.is(tok::comment)) // Skip comments in -C mode.
LexUnexpandedToken(Tmp);
if (Tmp.is(tok::eod))
return Tmp.getLocation();
// Add a fixit in GNU/C99/C++ mode. Don't offer a fixit for strict-C89,
// or if this is a macro-style preprocessing directive, because it is more
// trouble than it is worth to insert /**/ and check that there is no /**/
// in the range also.
FixItHint Hint;
if ((LangOpts.GNUMode || LangOpts.C99 || LangOpts.CPlusPlus) &&
!CurTokenLexer)
Hint = FixItHint::CreateInsertion(Tmp.getLocation(),"//");
Diag(Tmp, diag::ext_pp_extra_tokens_at_eol) << DirType << Hint;
return DiscardUntilEndOfDirective().getEnd();
}
Optional<unsigned> Preprocessor::getSkippedRangeForExcludedConditionalBlock(
SourceLocation HashLoc) {
if (!ExcludedConditionalDirectiveSkipMappings)
return None;
if (!HashLoc.isFileID())
return None;
std::pair<FileID, unsigned> HashFileOffset =
SourceMgr.getDecomposedLoc(HashLoc);
const llvm::MemoryBuffer *Buf = SourceMgr.getBuffer(HashFileOffset.first);
auto It = ExcludedConditionalDirectiveSkipMappings->find(Buf);
if (It == ExcludedConditionalDirectiveSkipMappings->end())
return None;
const PreprocessorSkippedRangeMapping &SkippedRanges = *It->getSecond();
// Check if the offset of '#' is mapped in the skipped ranges.
auto MappingIt = SkippedRanges.find(HashFileOffset.second);
if (MappingIt == SkippedRanges.end())
return None;
unsigned BytesToSkip = MappingIt->getSecond();
unsigned CurLexerBufferOffset = CurLexer->getCurrentBufferOffset();
assert(CurLexerBufferOffset >= HashFileOffset.second &&
"lexer is before the hash?");
// Take into account the fact that the lexer has already advanced, so the
// number of bytes to skip must be adjusted.
unsigned LengthDiff = CurLexerBufferOffset - HashFileOffset.second;
assert(BytesToSkip >= LengthDiff && "lexer is after the skipped range?");
return BytesToSkip - LengthDiff;
}
/// SkipExcludedConditionalBlock - We just read a \#if or related directive and
/// decided that the subsequent tokens are in the \#if'd out portion of the
/// file. Lex the rest of the file, until we see an \#endif. If
/// FoundNonSkipPortion is true, then we have already emitted code for part of
/// this \#if directive, so \#else/\#elif blocks should never be entered.
/// If ElseOk is true, then \#else directives are ok, if not, then we have
/// already seen one so a \#else directive is a duplicate. When this returns,
/// the caller can lex the first valid token.
void Preprocessor::SkipExcludedConditionalBlock(SourceLocation HashTokenLoc,
SourceLocation IfTokenLoc,
bool FoundNonSkipPortion,
bool FoundElse,
SourceLocation ElseLoc) {
++NumSkipped;
assert(!CurTokenLexer && CurPPLexer && "Lexing a macro, not a file?");
if (PreambleConditionalStack.reachedEOFWhileSkipping())
PreambleConditionalStack.clearSkipInfo();
else
CurPPLexer->pushConditionalLevel(IfTokenLoc, /*isSkipping*/ false,
FoundNonSkipPortion, FoundElse);
// Enter raw mode to disable identifier lookup (and thus macro expansion),
// disabling warnings, etc.
CurPPLexer->LexingRawMode = true;
Token Tok;
if (auto SkipLength =
getSkippedRangeForExcludedConditionalBlock(HashTokenLoc)) {
// Skip to the next '#endif' / '#else' / '#elif'.
CurLexer->skipOver(*SkipLength);
}
while (true) {
CurLexer->Lex(Tok);
if (Tok.is(tok::code_completion)) {
if (CodeComplete)
CodeComplete->CodeCompleteInConditionalExclusion();
setCodeCompletionReached();
continue;
}
// If this is the end of the buffer, we have an error.
if (Tok.is(tok::eof)) {
// We don't emit errors for unterminated conditionals here,
// Lexer::LexEndOfFile can do that properly.
// Just return and let the caller lex after this #include.
if (PreambleConditionalStack.isRecording())
PreambleConditionalStack.SkipInfo.emplace(
HashTokenLoc, IfTokenLoc, FoundNonSkipPortion, FoundElse, ElseLoc);
break;
}
// If this token is not a preprocessor directive, just skip it.
if (Tok.isNot(tok::hash) || !Tok.isAtStartOfLine())
continue;
// We just parsed a # character at the start of a line, so we're in
// directive mode. Tell the lexer this so any newlines we see will be
// converted into an EOD token (this terminates the macro).
CurPPLexer->ParsingPreprocessorDirective = true;
if (CurLexer) CurLexer->SetKeepWhitespaceMode(false);
// Read the next token, the directive flavor.
LexUnexpandedToken(Tok);
// If this isn't an identifier directive (e.g. is "# 1\n" or "#\n", or
// something bogus), skip it.
if (Tok.isNot(tok::raw_identifier)) {
CurPPLexer->ParsingPreprocessorDirective = false;
// Restore comment saving mode.
if (CurLexer) CurLexer->resetExtendedTokenMode();
continue;
}
// If the first letter isn't i or e, it isn't intesting to us. We know that
// this is safe in the face of spelling differences, because there is no way
// to spell an i/e in a strange way that is another letter. Skipping this
// allows us to avoid looking up the identifier info for #define/#undef and
// other common directives.
StringRef RI = Tok.getRawIdentifier();
char FirstChar = RI[0];
if (FirstChar >= 'a' && FirstChar <= 'z' &&
FirstChar != 'i' && FirstChar != 'e') {
CurPPLexer->ParsingPreprocessorDirective = false;
// Restore comment saving mode.
if (CurLexer) CurLexer->resetExtendedTokenMode();
continue;
}
// Get the identifier name without trigraphs or embedded newlines. Note
// that we can't use Tok.getIdentifierInfo() because its lookup is disabled
// when skipping.
char DirectiveBuf[20];
StringRef Directive;
if (!Tok.needsCleaning() && RI.size() < 20) {
Directive = RI;
} else {
std::string DirectiveStr = getSpelling(Tok);
size_t IdLen = DirectiveStr.size();
if (IdLen >= 20) {
CurPPLexer->ParsingPreprocessorDirective = false;
// Restore comment saving mode.
if (CurLexer) CurLexer->resetExtendedTokenMode();
continue;
}
memcpy(DirectiveBuf, &DirectiveStr[0], IdLen);
Directive = StringRef(DirectiveBuf, IdLen);
}
if (Directive.startswith("if")) {
StringRef Sub = Directive.substr(2);
if (Sub.empty() || // "if"
Sub == "def" || // "ifdef"
Sub == "ndef") { // "ifndef"
// We know the entire #if/#ifdef/#ifndef block will be skipped, don't
// bother parsing the condition.
DiscardUntilEndOfDirective();
CurPPLexer->pushConditionalLevel(Tok.getLocation(), /*wasskipping*/true,
/*foundnonskip*/false,
/*foundelse*/false);
}
} else if (Directive[0] == 'e') {
StringRef Sub = Directive.substr(1);
if (Sub == "ndif") { // "endif"
PPConditionalInfo CondInfo;
CondInfo.WasSkipping = true; // Silence bogus warning.
bool InCond = CurPPLexer->popConditionalLevel(CondInfo);
(void)InCond; // Silence warning in no-asserts mode.
assert(!InCond && "Can't be skipping if not in a conditional!");
// If we popped the outermost skipping block, we're done skipping!
if (!CondInfo.WasSkipping) {
// Restore the value of LexingRawMode so that trailing comments
// are handled correctly, if we've reached the outermost block.
CurPPLexer->LexingRawMode = false;
CheckEndOfDirective("endif");
CurPPLexer->LexingRawMode = true;
if (Callbacks)
Callbacks->Endif(Tok.getLocation(), CondInfo.IfLoc);
break;
} else {
DiscardUntilEndOfDirective();
}
} else if (Sub == "lse") { // "else".
// #else directive in a skipping conditional. If not in some other
// skipping conditional, and if #else hasn't already been seen, enter it
// as a non-skipping conditional.
PPConditionalInfo &CondInfo = CurPPLexer->peekConditionalLevel();
// If this is a #else with a #else before it, report the error.
if (CondInfo.FoundElse) Diag(Tok, diag::pp_err_else_after_else);
// Note that we've seen a #else in this conditional.
CondInfo.FoundElse = true;
// If the conditional is at the top level, and the #if block wasn't
// entered, enter the #else block now.
if (!CondInfo.WasSkipping && !CondInfo.FoundNonSkip) {
CondInfo.FoundNonSkip = true;
// Restore the value of LexingRawMode so that trailing comments
// are handled correctly.
CurPPLexer->LexingRawMode = false;
CheckEndOfDirective("else");
CurPPLexer->LexingRawMode = true;
if (Callbacks)
Callbacks->Else(Tok.getLocation(), CondInfo.IfLoc);
break;
} else {
DiscardUntilEndOfDirective(); // C99 6.10p4.
}
} else if (Sub == "lif") { // "elif".
PPConditionalInfo &CondInfo = CurPPLexer->peekConditionalLevel();
// If this is a #elif with a #else before it, report the error.
if (CondInfo.FoundElse) Diag(Tok, diag::pp_err_elif_after_else);
// If this is in a skipping block or if we're already handled this #if
// block, don't bother parsing the condition.
if (CondInfo.WasSkipping || CondInfo.FoundNonSkip) {
DiscardUntilEndOfDirective();
} else {
// Restore the value of LexingRawMode so that identifiers are
// looked up, etc, inside the #elif expression.
assert(CurPPLexer->LexingRawMode && "We have to be skipping here!");
CurPPLexer->LexingRawMode = false;
IdentifierInfo *IfNDefMacro = nullptr;
DirectiveEvalResult DER = EvaluateDirectiveExpression(IfNDefMacro);
const bool CondValue = DER.Conditional;
CurPPLexer->LexingRawMode = true;
if (Callbacks) {
Callbacks->Elif(
Tok.getLocation(), DER.ExprRange,
(CondValue ? PPCallbacks::CVK_True : PPCallbacks::CVK_False),
CondInfo.IfLoc);
}
// If this condition is true, enter it!
if (CondValue) {
CondInfo.FoundNonSkip = true;
break;
}
}
}
}
CurPPLexer->ParsingPreprocessorDirective = false;
// Restore comment saving mode.
if (CurLexer) CurLexer->resetExtendedTokenMode();
}
// Finally, if we are out of the conditional (saw an #endif or ran off the end
// of the file, just stop skipping and return to lexing whatever came after
// the #if block.
CurPPLexer->LexingRawMode = false;
// The last skipped range isn't actually skipped yet if it's truncated
// by the end of the preamble; we'll resume parsing after the preamble.
if (Callbacks && (Tok.isNot(tok::eof) || !isRecordingPreamble()))
Callbacks->SourceRangeSkipped(
SourceRange(HashTokenLoc, CurPPLexer->getSourceLocation()),
Tok.getLocation());
}
Module *Preprocessor::getModuleForLocation(SourceLocation Loc) {
if (!SourceMgr.isInMainFile(Loc)) {
// Try to determine the module of the include directive.
// FIXME: Look into directly passing the FileEntry from LookupFile instead.
FileID IDOfIncl = SourceMgr.getFileID(SourceMgr.getExpansionLoc(Loc));
if (const FileEntry *EntryOfIncl = SourceMgr.getFileEntryForID(IDOfIncl)) {
// The include comes from an included file.
return HeaderInfo.getModuleMap()
.findModuleForHeader(EntryOfIncl)
.getModule();
}
}
// This is either in the main file or not in a file at all. It belongs
// to the current module, if there is one.
return getLangOpts().CurrentModule.empty()
? nullptr
: HeaderInfo.lookupModule(getLangOpts().CurrentModule);
}
const FileEntry *
Preprocessor::getModuleHeaderToIncludeForDiagnostics(SourceLocation IncLoc,
Module *M,
SourceLocation Loc) {
assert(M && "no module to include");
// If the context is the global module fragment of some module, we never
// want to return that file; instead, we want the innermost include-guarded
// header that it included.
bool InGlobalModuleFragment = M->Kind == Module::GlobalModuleFragment;
// If we have a module import syntax, we shouldn't include a header to
// make a particular module visible.
if ((getLangOpts().ObjC || getLangOpts().CPlusPlusModules ||
getLangOpts().ModulesTS) &&
!InGlobalModuleFragment)
return nullptr;
Module *TopM = M->getTopLevelModule();
Module *IncM = getModuleForLocation(IncLoc);
// Walk up through the include stack, looking through textual headers of M
// until we hit a non-textual header that we can #include. (We assume textual
// headers of a module with non-textual headers aren't meant to be used to
// import entities from the module.)
auto &SM = getSourceManager();
while (!Loc.isInvalid() && !SM.isInMainFile(Loc)) {
auto ID = SM.getFileID(SM.getExpansionLoc(Loc));
auto *FE = SM.getFileEntryForID(ID);
if (!FE)
break;
if (InGlobalModuleFragment) {
if (getHeaderSearchInfo().isFileMultipleIncludeGuarded(FE))
return FE;
Loc = SM.getIncludeLoc(ID);
continue;
}
bool InTextualHeader = false;
for (auto Header : HeaderInfo.getModuleMap().findAllModulesForHeader(FE)) {
if (!Header.getModule()->isSubModuleOf(TopM))
continue;
if (!(Header.getRole() & ModuleMap::TextualHeader)) {
// If this is an accessible, non-textual header of M's top-level module
// that transitively includes the given location and makes the
// corresponding module visible, this is the thing to #include.
if (Header.isAccessibleFrom(IncM))
return FE;
// It's in a private header; we can't #include it.
// FIXME: If there's a public header in some module that re-exports it,
// then we could suggest including that, but it's not clear that's the
// expected way to make this entity visible.
continue;
}
InTextualHeader = true;
}
if (!InTextualHeader)
break;
Loc = SM.getIncludeLoc(ID);
}
return nullptr;
}
Optional<FileEntryRef> Preprocessor::LookupFile(
SourceLocation FilenameLoc, StringRef Filename, bool isAngled,
const DirectoryLookup *FromDir, const FileEntry *FromFile,
const DirectoryLookup *&CurDir, SmallVectorImpl<char> *SearchPath,
SmallVectorImpl<char> *RelativePath,
ModuleMap::KnownHeader *SuggestedModule, bool *IsMapped,
bool *IsFrameworkFound, bool SkipCache) {
Module *RequestingModule = getModuleForLocation(FilenameLoc);
bool RequestingModuleIsModuleInterface = !SourceMgr.isInMainFile(FilenameLoc);
// If the header lookup mechanism may be relative to the current inclusion
// stack, record the parent #includes.
SmallVector<std::pair<const FileEntry *, const DirectoryEntry *>, 16>
Includers;
bool BuildSystemModule = false;
if (!FromDir && !FromFile) {
FileID FID = getCurrentFileLexer()->getFileID();
const FileEntry *FileEnt = SourceMgr.getFileEntryForID(FID);
// If there is no file entry associated with this file, it must be the
// predefines buffer or the module includes buffer. Any other file is not
// lexed with a normal lexer, so it won't be scanned for preprocessor
// directives.
//
// If we have the predefines buffer, resolve #include references (which come
// from the -include command line argument) from the current working
// directory instead of relative to the main file.
//
// If we have the module includes buffer, resolve #include references (which
// come from header declarations in the module map) relative to the module
// map file.
if (!FileEnt) {
if (FID == SourceMgr.getMainFileID() && MainFileDir) {
Includers.push_back(std::make_pair(nullptr, MainFileDir));
BuildSystemModule = getCurrentModule()->IsSystem;
} else if ((FileEnt =
SourceMgr.getFileEntryForID(SourceMgr.getMainFileID())))
Includers.push_back(std::make_pair(FileEnt, *FileMgr.getDirectory(".")));
} else {
Includers.push_back(std::make_pair(FileEnt, FileEnt->getDir()));
}
// MSVC searches the current include stack from top to bottom for
// headers included by quoted include directives.
// See: http://msdn.microsoft.com/en-us/library/36k2cdd4.aspx
if (LangOpts.MSVCCompat && !isAngled) {
for (IncludeStackInfo &ISEntry : llvm::reverse(IncludeMacroStack)) {
if (IsFileLexer(ISEntry))
if ((FileEnt = ISEntry.ThePPLexer->getFileEntry()))
Includers.push_back(std::make_pair(FileEnt, FileEnt->getDir()));
}
}
}
CurDir = CurDirLookup;
if (FromFile) {
// We're supposed to start looking from after a particular file. Search
// the include path until we find that file or run out of files.
const DirectoryLookup *TmpCurDir = CurDir;
const DirectoryLookup *TmpFromDir = nullptr;
while (Optional<FileEntryRef> FE = HeaderInfo.LookupFile(
Filename, FilenameLoc, isAngled, TmpFromDir, TmpCurDir,
Includers, SearchPath, RelativePath, RequestingModule,
SuggestedModule, /*IsMapped=*/nullptr,
/*IsFrameworkFound=*/nullptr, SkipCache)) {
// Keep looking as if this file did a #include_next.
TmpFromDir = TmpCurDir;
++TmpFromDir;
if (&FE->getFileEntry() == FromFile) {
// Found it.
FromDir = TmpFromDir;
CurDir = TmpCurDir;
break;
}
}
}
// Do a standard file entry lookup.
Optional<FileEntryRef> FE = HeaderInfo.LookupFile(
Filename, FilenameLoc, isAngled, FromDir, CurDir, Includers, SearchPath,
RelativePath, RequestingModule, SuggestedModule, IsMapped,
IsFrameworkFound, SkipCache, BuildSystemModule);
if (FE) {
if (SuggestedModule && !LangOpts.AsmPreprocessor)
HeaderInfo.getModuleMap().diagnoseHeaderInclusion(
RequestingModule, RequestingModuleIsModuleInterface, FilenameLoc,
Filename, &FE->getFileEntry());
return FE;
}
const FileEntry *CurFileEnt;
// Otherwise, see if this is a subframework header. If so, this is relative
// to one of the headers on the #include stack. Walk the list of the current
// headers on the #include stack and pass them to HeaderInfo.
if (IsFileLexer()) {
if ((CurFileEnt = CurPPLexer->getFileEntry())) {
if (Optional<FileEntryRef> FE = HeaderInfo.LookupSubframeworkHeader(
Filename, CurFileEnt, SearchPath, RelativePath, RequestingModule,
SuggestedModule)) {
if (SuggestedModule && !LangOpts.AsmPreprocessor)
HeaderInfo.getModuleMap().diagnoseHeaderInclusion(
RequestingModule, RequestingModuleIsModuleInterface, FilenameLoc,
Filename, &FE->getFileEntry());
return FE;
}
}
}
for (IncludeStackInfo &ISEntry : llvm::reverse(IncludeMacroStack)) {
if (IsFileLexer(ISEntry)) {
if ((CurFileEnt = ISEntry.ThePPLexer->getFileEntry())) {
if (Optional<FileEntryRef> FE = HeaderInfo.LookupSubframeworkHeader(
Filename, CurFileEnt, SearchPath, RelativePath,
RequestingModule, SuggestedModule)) {
if (SuggestedModule && !LangOpts.AsmPreprocessor)
HeaderInfo.getModuleMap().diagnoseHeaderInclusion(
RequestingModule, RequestingModuleIsModuleInterface,
FilenameLoc, Filename, &FE->getFileEntry());
return FE;
}
}
}
}
// Otherwise, we really couldn't find the file.
return None;
}
//===----------------------------------------------------------------------===//
// Preprocessor Directive Handling.
//===----------------------------------------------------------------------===//
class Preprocessor::ResetMacroExpansionHelper {
public:
ResetMacroExpansionHelper(Preprocessor *pp)
: PP(pp), save(pp->DisableMacroExpansion) {
if (pp->MacroExpansionInDirectivesOverride)
pp->DisableMacroExpansion = false;
}
~ResetMacroExpansionHelper() {
PP->DisableMacroExpansion = save;
}
private:
Preprocessor *PP;
bool save;
};
/// Process a directive while looking for the through header or a #pragma
/// hdrstop. The following directives are handled:
/// #include (to check if it is the through header)
/// #define (to warn about macros that don't match the PCH)
/// #pragma (to check for pragma hdrstop).
/// All other directives are completely discarded.
void Preprocessor::HandleSkippedDirectiveWhileUsingPCH(Token &Result,
SourceLocation HashLoc) {
if (const IdentifierInfo *II = Result.getIdentifierInfo()) {
if (II->getPPKeywordID() == tok::pp_define) {
return HandleDefineDirective(Result,
/*ImmediatelyAfterHeaderGuard=*/false);
}
if (SkippingUntilPCHThroughHeader &&
II->getPPKeywordID() == tok::pp_include) {
return HandleIncludeDirective(HashLoc, Result);
}
if (SkippingUntilPragmaHdrStop && II->getPPKeywordID() == tok::pp_pragma) {
Lex(Result);
auto *II = Result.getIdentifierInfo();
if (II && II->getName() == "hdrstop")
return HandlePragmaHdrstop(Result);
}
}
DiscardUntilEndOfDirective();
}
/// HandleDirective - This callback is invoked when the lexer sees a # token
/// at the start of a line. This consumes the directive, modifies the
/// lexer/preprocessor state, and advances the lexer(s) so that the next token
/// read is the correct one.
void Preprocessor::HandleDirective(Token &Result) {
// FIXME: Traditional: # with whitespace before it not recognized by K&R?
// We just parsed a # character at the start of a line, so we're in directive
// mode. Tell the lexer this so any newlines we see will be converted into an
// EOD token (which terminates the directive).
CurPPLexer->ParsingPreprocessorDirective = true;
if (CurLexer) CurLexer->SetKeepWhitespaceMode(false);
bool ImmediatelyAfterTopLevelIfndef =
CurPPLexer->MIOpt.getImmediatelyAfterTopLevelIfndef();
CurPPLexer->MIOpt.resetImmediatelyAfterTopLevelIfndef();
++NumDirectives;
// We are about to read a token. For the multiple-include optimization FA to
// work, we have to remember if we had read any tokens *before* this
// pp-directive.
bool ReadAnyTokensBeforeDirective =CurPPLexer->MIOpt.getHasReadAnyTokensVal();
// Save the '#' token in case we need to return it later.
Token SavedHash = Result;
// Read the next token, the directive flavor. This isn't expanded due to
// C99 6.10.3p8.
LexUnexpandedToken(Result);
// C99 6.10.3p11: Is this preprocessor directive in macro invocation? e.g.:
// #define A(x) #x
// A(abc
// #warning blah
// def)
// If so, the user is relying on undefined behavior, emit a diagnostic. Do
// not support this for #include-like directives, since that can result in
// terrible diagnostics, and does not work in GCC.
if (InMacroArgs) {
if (IdentifierInfo *II = Result.getIdentifierInfo()) {
switch (II->getPPKeywordID()) {
case tok::pp_include:
case tok::pp_import:
case tok::pp_include_next:
case tok::pp___include_macros:
case tok::pp_pragma:
Diag(Result, diag::err_embedded_directive) << II->getName();
Diag(*ArgMacro, diag::note_macro_expansion_here)
<< ArgMacro->getIdentifierInfo();
DiscardUntilEndOfDirective();
return;
default:
break;
}
}
Diag(Result, diag::ext_embedded_directive);
}
// Temporarily enable macro expansion if set so
// and reset to previous state when returning from this function.
ResetMacroExpansionHelper helper(this);
if (SkippingUntilPCHThroughHeader || SkippingUntilPragmaHdrStop)
return HandleSkippedDirectiveWhileUsingPCH(Result, SavedHash.getLocation());
switch (Result.getKind()) {
case tok::eod:
return; // null directive.
case tok::code_completion:
if (CodeComplete)
CodeComplete->CodeCompleteDirective(
CurPPLexer->getConditionalStackDepth() > 0);
setCodeCompletionReached();
return;
case tok::numeric_constant: // # 7 GNU line marker directive.
if (getLangOpts().AsmPreprocessor)
break; // # 4 is not a preprocessor directive in .S files.
return HandleDigitDirective(Result);
default:
IdentifierInfo *II = Result.getIdentifierInfo();
if (!II) break; // Not an identifier.
// Ask what the preprocessor keyword ID is.
switch (II->getPPKeywordID()) {
default: break;
// C99 6.10.1 - Conditional Inclusion.
case tok::pp_if:
return HandleIfDirective(Result, SavedHash, ReadAnyTokensBeforeDirective);
case tok::pp_ifdef:
return HandleIfdefDirective(Result, SavedHash, false,
true /*not valid for miopt*/);
case tok::pp_ifndef:
return HandleIfdefDirective(Result, SavedHash, true,
ReadAnyTokensBeforeDirective);
case tok::pp_elif:
return HandleElifDirective(Result, SavedHash);
case tok::pp_else:
return HandleElseDirective(Result, SavedHash);
case tok::pp_endif:
return HandleEndifDirective(Result);
// C99 6.10.2 - Source File Inclusion.
case tok::pp_include:
// Handle #include.
return HandleIncludeDirective(SavedHash.getLocation(), Result);
case tok::pp___include_macros:
// Handle -imacros.
return HandleIncludeMacrosDirective(SavedHash.getLocation(), Result);
// C99 6.10.3 - Macro Replacement.
case tok::pp_define:
return HandleDefineDirective(Result, ImmediatelyAfterTopLevelIfndef);
case tok::pp_undef:
return HandleUndefDirective();
// C99 6.10.4 - Line Control.
case tok::pp_line:
return HandleLineDirective();
// C99 6.10.5 - Error Directive.
case tok::pp_error:
return HandleUserDiagnosticDirective(Result, false);
// C99 6.10.6 - Pragma Directive.
case tok::pp_pragma:
return HandlePragmaDirective({PIK_HashPragma, SavedHash.getLocation()});
// GNU Extensions.
case tok::pp_import:
return HandleImportDirective(SavedHash.getLocation(), Result);
case tok::pp_include_next:
return HandleIncludeNextDirective(SavedHash.getLocation(), Result);
case tok::pp_warning:
Diag(Result, diag::ext_pp_warning_directive);
return HandleUserDiagnosticDirective(Result, true);
case tok::pp_ident:
return HandleIdentSCCSDirective(Result);
case tok::pp_sccs:
return HandleIdentSCCSDirective(Result);
case tok::pp_assert:
//isExtension = true; // FIXME: implement #assert
break;
case tok::pp_unassert:
//isExtension = true; // FIXME: implement #unassert
break;
case tok::pp___public_macro:
if (getLangOpts().Modules)
return HandleMacroPublicDirective(Result);
break;
case tok::pp___private_macro:
if (getLangOpts().Modules)
return HandleMacroPrivateDirective();
break;
}
break;
}
// If this is a .S file, treat unknown # directives as non-preprocessor
// directives. This is important because # may be a comment or introduce
// various pseudo-ops. Just return the # token and push back the following
// token to be lexed next time.
if (getLangOpts().AsmPreprocessor) {
auto Toks = std::make_unique<Token[]>(2);
// Return the # and the token after it.
Toks[0] = SavedHash;
Toks[1] = Result;
// If the second token is a hashhash token, then we need to translate it to
// unknown so the token lexer doesn't try to perform token pasting.
if (Result.is(tok::hashhash))
Toks[1].setKind(tok::unknown);
// Enter this token stream so that we re-lex the tokens. Make sure to
// enable macro expansion, in case the token after the # is an identifier
// that is expanded.
EnterTokenStream(std::move(Toks), 2, false, /*IsReinject*/false);
return;
}
// If we reached here, the preprocessing token is not valid!
Diag(Result, diag::err_pp_invalid_directive);
// Read the rest of the PP line.
DiscardUntilEndOfDirective();
// Okay, we're done parsing the directive.
}
/// GetLineValue - Convert a numeric token into an unsigned value, emitting
/// Diagnostic DiagID if it is invalid, and returning the value in Val.
static bool GetLineValue(Token &DigitTok, unsigned &Val,
unsigned DiagID, Preprocessor &PP,
bool IsGNULineDirective=false) {
if (DigitTok.isNot(tok::numeric_constant)) {
PP.Diag(DigitTok, DiagID);
if (DigitTok.isNot(tok::eod))
PP.DiscardUntilEndOfDirective();
return true;
}
SmallString<64> IntegerBuffer;
IntegerBuffer.resize(DigitTok.getLength());
const char *DigitTokBegin = &IntegerBuffer[0];
bool Invalid = false;
unsigned ActualLength = PP.getSpelling(DigitTok, DigitTokBegin, &Invalid);
if (Invalid)
return true;
// Verify that we have a simple digit-sequence, and compute the value. This
// is always a simple digit string computed in decimal, so we do this manually
// here.
Val = 0;
for (unsigned i = 0; i != ActualLength; ++i) {
// C++1y [lex.fcon]p1:
// Optional separating single quotes in a digit-sequence are ignored
if (DigitTokBegin[i] == '\'')
continue;
if (!isDigit(DigitTokBegin[i])) {
PP.Diag(PP.AdvanceToTokenCharacter(DigitTok.getLocation(), i),
diag::err_pp_line_digit_sequence) << IsGNULineDirective;
PP.DiscardUntilEndOfDirective();
return true;
}
unsigned NextVal = Val*10+(DigitTokBegin[i]-'0');
if (NextVal < Val) { // overflow.
PP.Diag(DigitTok, DiagID);
PP.DiscardUntilEndOfDirective();
return true;
}
Val = NextVal;
}
if (DigitTokBegin[0] == '0' && Val)
PP.Diag(DigitTok.getLocation(), diag::warn_pp_line_decimal)
<< IsGNULineDirective;
return false;
}
/// Handle a \#line directive: C99 6.10.4.
///
/// The two acceptable forms are:
/// \verbatim
/// # line digit-sequence
/// # line digit-sequence "s-char-sequence"
/// \endverbatim
void Preprocessor::HandleLineDirective() {
// Read the line # and string argument. Per C99 6.10.4p5, these tokens are
// expanded.
Token DigitTok;
Lex(DigitTok);
// Validate the number and convert it to an unsigned.
unsigned LineNo;
if (GetLineValue(DigitTok, LineNo, diag::err_pp_line_requires_integer,*this))
return;
if (LineNo == 0)
Diag(DigitTok, diag::ext_pp_line_zero);
// Enforce C99 6.10.4p3: "The digit sequence shall not specify ... a
// number greater than 2147483647". C90 requires that the line # be <= 32767.
unsigned LineLimit = 32768U;
if (LangOpts.C99 || LangOpts.CPlusPlus11)
LineLimit = 2147483648U;
if (LineNo >= LineLimit)
Diag(DigitTok, diag::ext_pp_line_too_big) << LineLimit;
else if (LangOpts.CPlusPlus11 && LineNo >= 32768U)
Diag(DigitTok, diag::warn_cxx98_compat_pp_line_too_big);
int FilenameID = -1;
Token StrTok;
Lex(StrTok);
// If the StrTok is "eod", then it wasn't present. Otherwise, it must be a
// string followed by eod.
if (StrTok.is(tok::eod))
; // ok
else if (StrTok.isNot(tok::string_literal)) {
Diag(StrTok, diag::err_pp_line_invalid_filename);
DiscardUntilEndOfDirective();
return;
} else if (StrTok.hasUDSuffix()) {
Diag(StrTok, diag::err_invalid_string_udl);
DiscardUntilEndOfDirective();
return;
} else {
// Parse and validate the string, converting it into a unique ID.
StringLiteralParser Literal(StrTok, *this);
assert(Literal.isAscii() && "Didn't allow wide strings in");
if (Literal.hadError) {
DiscardUntilEndOfDirective();
return;
}
if (Literal.Pascal) {
Diag(StrTok, diag::err_pp_linemarker_invalid_filename);
DiscardUntilEndOfDirective();
return;
}
FilenameID = SourceMgr.getLineTableFilenameID(Literal.GetString());
// Verify that there is nothing after the string, other than EOD. Because
// of C99 6.10.4p5, macros that expand to empty tokens are ok.
CheckEndOfDirective("line", true);
}
// Take the file kind of the file containing the #line directive. #line
// directives are often used for generated sources from the same codebase, so
// the new file should generally be classified the same way as the current
// file. This is visible in GCC's pre-processed output, which rewrites #line
// to GNU line markers.
SrcMgr::CharacteristicKind FileKind =
SourceMgr.getFileCharacteristic(DigitTok.getLocation());
SourceMgr.AddLineNote(DigitTok.getLocation(), LineNo, FilenameID, false,
false, FileKind);
if (Callbacks)
Callbacks->FileChanged(CurPPLexer->getSourceLocation(),
PPCallbacks::RenameFile, FileKind);
}
/// ReadLineMarkerFlags - Parse and validate any flags at the end of a GNU line
/// marker directive.
static bool ReadLineMarkerFlags(bool &IsFileEntry, bool &IsFileExit,
SrcMgr::CharacteristicKind &FileKind,
Preprocessor &PP) {
unsigned FlagVal;
Token FlagTok;
PP.Lex(FlagTok);
if (FlagTok.is(tok::eod)) return false;
if (GetLineValue(FlagTok, FlagVal, diag::err_pp_linemarker_invalid_flag, PP))
return true;
if (FlagVal == 1) {
IsFileEntry = true;
PP.Lex(FlagTok);
if (FlagTok.is(tok::eod)) return false;
if (GetLineValue(FlagTok, FlagVal, diag::err_pp_linemarker_invalid_flag,PP))
return true;
} else if (FlagVal == 2) {
IsFileExit = true;
SourceManager &SM = PP.getSourceManager();
// If we are leaving the current presumed file, check to make sure the
// presumed include stack isn't empty!
FileID CurFileID =
SM.getDecomposedExpansionLoc(FlagTok.getLocation()).first;
PresumedLoc PLoc = SM.getPresumedLoc(FlagTok.getLocation());
if (PLoc.isInvalid())
return true;
// If there is no include loc (main file) or if the include loc is in a
// different physical file, then we aren't in a "1" line marker flag region.
SourceLocation IncLoc = PLoc.getIncludeLoc();
if (IncLoc.isInvalid() ||
SM.getDecomposedExpansionLoc(IncLoc).first != CurFileID) {
PP.Diag(FlagTok, diag::err_pp_linemarker_invalid_pop);
PP.DiscardUntilEndOfDirective();
return true;
}
PP.Lex(FlagTok);
if (FlagTok.is(tok::eod)) return false;
if (GetLineValue(FlagTok, FlagVal, diag::err_pp_linemarker_invalid_flag,PP))
return true;
}
// We must have 3 if there are still flags.
if (FlagVal != 3) {
PP.Diag(FlagTok, diag::err_pp_linemarker_invalid_flag);
PP.DiscardUntilEndOfDirective();
return true;
}
FileKind = SrcMgr::C_System;
PP.Lex(FlagTok);
if (FlagTok.is(tok::eod)) return false;
if (GetLineValue(FlagTok, FlagVal, diag::err_pp_linemarker_invalid_flag, PP))
return true;
// We must have 4 if there is yet another flag.
if (FlagVal != 4) {
PP.Diag(FlagTok, diag::err_pp_linemarker_invalid_flag);
PP.DiscardUntilEndOfDirective();
return true;
}
FileKind = SrcMgr::C_ExternCSystem;
PP.Lex(FlagTok);
if (FlagTok.is(tok::eod)) return false;
// There are no more valid flags here.
PP.Diag(FlagTok, diag::err_pp_linemarker_invalid_flag);
PP.DiscardUntilEndOfDirective();
return true;
}
/// HandleDigitDirective - Handle a GNU line marker directive, whose syntax is
/// one of the following forms:
///
/// # 42
/// # 42 "file" ('1' | '2')?
/// # 42 "file" ('1' | '2')? '3' '4'?
///
void Preprocessor::HandleDigitDirective(Token &DigitTok) {
// Validate the number and convert it to an unsigned. GNU does not have a
// line # limit other than it fit in 32-bits.
unsigned LineNo;
if (GetLineValue(DigitTok, LineNo, diag::err_pp_linemarker_requires_integer,
*this, true))
return;
Token StrTok;
Lex(StrTok);
bool IsFileEntry = false, IsFileExit = false;
int FilenameID = -1;
SrcMgr::CharacteristicKind FileKind = SrcMgr::C_User;
// If the StrTok is "eod", then it wasn't present. Otherwise, it must be a
// string followed by eod.
if (StrTok.is(tok::eod)) {
// Treat this like "#line NN", which doesn't change file characteristics.
FileKind = SourceMgr.getFileCharacteristic(DigitTok.getLocation());
} else if (StrTok.isNot(tok::string_literal)) {
Diag(StrTok, diag::err_pp_linemarker_invalid_filename);
DiscardUntilEndOfDirective();
return;
} else if (StrTok.hasUDSuffix()) {
Diag(StrTok, diag::err_invalid_string_udl);
DiscardUntilEndOfDirective();
return;
} else {
// Parse and validate the string, converting it into a unique ID.
StringLiteralParser Literal(StrTok, *this);
assert(Literal.isAscii() && "Didn't allow wide strings in");
if (Literal.hadError) {
DiscardUntilEndOfDirective();
return;
}
if (Literal.Pascal) {
Diag(StrTok, diag::err_pp_linemarker_invalid_filename);
DiscardUntilEndOfDirective();
return;
}
FilenameID = SourceMgr.getLineTableFilenameID(Literal.GetString());
// If a filename was present, read any flags that are present.
if (ReadLineMarkerFlags(IsFileEntry, IsFileExit, FileKind, *this))
return;
}
// Create a line note with this information.
SourceMgr.AddLineNote(DigitTok.getLocation(), LineNo, FilenameID, IsFileEntry,
IsFileExit, FileKind);
// If the preprocessor has callbacks installed, notify them of the #line
// change. This is used so that the line marker comes out in -E mode for
// example.
if (Callbacks) {
PPCallbacks::FileChangeReason Reason = PPCallbacks::RenameFile;
if (IsFileEntry)
Reason = PPCallbacks::EnterFile;
else if (IsFileExit)
Reason = PPCallbacks::ExitFile;
Callbacks->FileChanged(CurPPLexer->getSourceLocation(), Reason, FileKind);
}
}
/// HandleUserDiagnosticDirective - Handle a #warning or #error directive.
///
void Preprocessor::HandleUserDiagnosticDirective(Token &Tok,
bool isWarning) {
// Read the rest of the line raw. We do this because we don't want macros
// to be expanded and we don't require that the tokens be valid preprocessing
// tokens. For example, this is allowed: "#warning ` 'foo". GCC does
// collapse multiple consecutive white space between tokens, but this isn't
// specified by the standard.
SmallString<128> Message;
CurLexer->ReadToEndOfLine(&Message);
// Find the first non-whitespace character, so that we can make the
// diagnostic more succinct.
StringRef Msg = StringRef(Message).ltrim(' ');
if (isWarning)
Diag(Tok, diag::pp_hash_warning) << Msg;
else
Diag(Tok, diag::err_pp_hash_error) << Msg;
}
/// HandleIdentSCCSDirective - Handle a #ident/#sccs directive.
///
void Preprocessor::HandleIdentSCCSDirective(Token &Tok) {
// Yes, this directive is an extension.
Diag(Tok, diag::ext_pp_ident_directive);
// Read the string argument.
Token StrTok;
Lex(StrTok);
// If the token kind isn't a string, it's a malformed directive.
if (StrTok.isNot(tok::string_literal) &&
StrTok.isNot(tok::wide_string_literal)) {
Diag(StrTok, diag::err_pp_malformed_ident);
if (StrTok.isNot(tok::eod))
DiscardUntilEndOfDirective();
return;
}
if (StrTok.hasUDSuffix()) {
Diag(StrTok, diag::err_invalid_string_udl);
DiscardUntilEndOfDirective();
return;
}
// Verify that there is nothing after the string, other than EOD.
CheckEndOfDirective("ident");
if (Callbacks) {
bool Invalid = false;
std::string Str = getSpelling(StrTok, &Invalid);
if (!Invalid)
Callbacks->Ident(Tok.getLocation(), Str);
}
}
/// Handle a #public directive.
void Preprocessor::HandleMacroPublicDirective(Token &Tok) {
Token MacroNameTok;
ReadMacroName(MacroNameTok, MU_Undef);
// Error reading macro name? If so, diagnostic already issued.
if (MacroNameTok.is(tok::eod))
return;
// Check to see if this is the last token on the #__public_macro line.
CheckEndOfDirective("__public_macro");
IdentifierInfo *II = MacroNameTok.getIdentifierInfo();
// Okay, we finally have a valid identifier to undef.
MacroDirective *MD = getLocalMacroDirective(II);
// If the macro is not defined, this is an error.
if (!MD) {
Diag(MacroNameTok, diag::err_pp_visibility_non_macro) << II;
return;
}
// Note that this macro has now been exported.
appendMacroDirective(II, AllocateVisibilityMacroDirective(
MacroNameTok.getLocation(), /*isPublic=*/true));
}
/// Handle a #private directive.
void Preprocessor::HandleMacroPrivateDirective() {
Token MacroNameTok;
ReadMacroName(MacroNameTok, MU_Undef);
// Error reading macro name? If so, diagnostic already issued.
if (MacroNameTok.is(tok::eod))
return;
// Check to see if this is the last token on the #__private_macro line.
CheckEndOfDirective("__private_macro");
IdentifierInfo *II = MacroNameTok.getIdentifierInfo();
// Okay, we finally have a valid identifier to undef.
MacroDirective *MD = getLocalMacroDirective(II);
// If the macro is not defined, this is an error.
if (!MD) {
Diag(MacroNameTok, diag::err_pp_visibility_non_macro) << II;
return;
}
// Note that this macro has now been marked private.
appendMacroDirective(II, AllocateVisibilityMacroDirective(
MacroNameTok.getLocation(), /*isPublic=*/false));
}
//===----------------------------------------------------------------------===//
// Preprocessor Include Directive Handling.
//===----------------------------------------------------------------------===//
/// GetIncludeFilenameSpelling - Turn the specified lexer token into a fully
/// checked and spelled filename, e.g. as an operand of \#include. This returns
/// true if the input filename was in <>'s or false if it were in ""'s. The
/// caller is expected to provide a buffer that is large enough to hold the
/// spelling of the filename, but is also expected to handle the case when
/// this method decides to use a different buffer.
bool Preprocessor::GetIncludeFilenameSpelling(SourceLocation Loc,
StringRef &Buffer) {
// Get the text form of the filename.
assert(!Buffer.empty() && "Can't have tokens with empty spellings!");
// FIXME: Consider warning on some of the cases described in C11 6.4.7/3 and
// C++20 [lex.header]/2:
//
// If `"`, `'`, `\`, `/*`, or `//` appears in a header-name, then
// in C: behavior is undefined
// in C++: program is conditionally-supported with implementation-defined
// semantics
// Make sure the filename is <x> or "x".
bool isAngled;
if (Buffer[0] == '<') {
if (Buffer.back() != '>') {
Diag(Loc, diag::err_pp_expects_filename);
Buffer = StringRef();
return true;
}
isAngled = true;
} else if (Buffer[0] == '"') {
if (Buffer.back() != '"') {
Diag(Loc, diag::err_pp_expects_filename);
Buffer = StringRef();
return true;
}
isAngled = false;
} else {
Diag(Loc, diag::err_pp_expects_filename);
Buffer = StringRef();
return true;
}
// Diagnose #include "" as invalid.
if (Buffer.size() <= 2) {
Diag(Loc, diag::err_pp_empty_filename);
Buffer = StringRef();
return true;
}
// Skip the brackets.
Buffer = Buffer.substr(1, Buffer.size()-2);
return isAngled;
}
/// Push a token onto the token stream containing an annotation.
void Preprocessor::EnterAnnotationToken(SourceRange Range,
tok::TokenKind Kind,
void *AnnotationVal) {
// FIXME: Produce this as the current token directly, rather than
// allocating a new token for it.
auto Tok = std::make_unique<Token[]>(1);
Tok[0].startToken();
Tok[0].setKind(Kind);
Tok[0].setLocation(Range.getBegin());
Tok[0].setAnnotationEndLoc(Range.getEnd());
Tok[0].setAnnotationValue(AnnotationVal);
EnterTokenStream(std::move(Tok), 1, true, /*IsReinject*/ false);
}
/// Produce a diagnostic informing the user that a #include or similar
/// was implicitly treated as a module import.
static void diagnoseAutoModuleImport(
Preprocessor &PP, SourceLocation HashLoc, Token &IncludeTok,
ArrayRef<std::pair<IdentifierInfo *, SourceLocation>> Path,
SourceLocation PathEnd) {
StringRef ImportKeyword;
if (PP.getLangOpts().ObjC)
ImportKeyword = "@import";
else if (PP.getLangOpts().ModulesTS || PP.getLangOpts().CPlusPlusModules)
ImportKeyword = "import";
else
return; // no import syntax available
SmallString<128> PathString;
for (size_t I = 0, N = Path.size(); I != N; ++I) {
if (I)
PathString += '.';
PathString += Path[I].first->getName();
}
int IncludeKind = 0;
switch (IncludeTok.getIdentifierInfo()->getPPKeywordID()) {
case tok::pp_include:
IncludeKind = 0;
break;
case tok::pp_import:
IncludeKind = 1;
break;
case tok::pp_include_next:
IncludeKind = 2;
break;
case tok::pp___include_macros:
IncludeKind = 3;
break;
default:
llvm_unreachable("unknown include directive kind");
}
CharSourceRange ReplaceRange(SourceRange(HashLoc, PathEnd),
/*IsTokenRange=*/false);
PP.Diag(HashLoc, diag::warn_auto_module_import)
<< IncludeKind << PathString
<< FixItHint::CreateReplacement(
ReplaceRange, (ImportKeyword + " " + PathString + ";").str());
}
// Given a vector of path components and a string containing the real
// path to the file, build a properly-cased replacement in the vector,
// and return true if the replacement should be suggested.
static bool trySimplifyPath(SmallVectorImpl<StringRef> &Components,
StringRef RealPathName) {
auto RealPathComponentIter = llvm::sys::path::rbegin(RealPathName);
auto RealPathComponentEnd = llvm::sys::path::rend(RealPathName);
int Cnt = 0;
bool SuggestReplacement = false;
// Below is a best-effort to handle ".." in paths. It is admittedly
// not 100% correct in the presence of symlinks.
for (auto &Component : llvm::reverse(Components)) {
if ("." == Component) {
} else if (".." == Component) {
++Cnt;
} else if (Cnt) {
--Cnt;
} else if (RealPathComponentIter != RealPathComponentEnd) {
if (Component != *RealPathComponentIter) {
// If these path components differ by more than just case, then we
// may be looking at symlinked paths. Bail on this diagnostic to avoid
// noisy false positives.
SuggestReplacement = RealPathComponentIter->equals_lower(Component);
if (!SuggestReplacement)
break;
Component = *RealPathComponentIter;
}
++RealPathComponentIter;
}
}
return SuggestReplacement;
}
bool Preprocessor::checkModuleIsAvailable(const LangOptions &LangOpts,
const TargetInfo &TargetInfo,
DiagnosticsEngine &Diags, Module *M) {
Module::Requirement Requirement;
Module::UnresolvedHeaderDirective MissingHeader;
Module *ShadowingModule = nullptr;
if (M->isAvailable(LangOpts, TargetInfo, Requirement, MissingHeader,
ShadowingModule))
return false;
if (MissingHeader.FileNameLoc.isValid()) {
Diags.Report(MissingHeader.FileNameLoc, diag::err_module_header_missing)
<< MissingHeader.IsUmbrella << MissingHeader.FileName;
} else if (ShadowingModule) {
Diags.Report(M->DefinitionLoc, diag::err_module_shadowed) << M->Name;
Diags.Report(ShadowingModule->DefinitionLoc,
diag::note_previous_definition);
} else {
// FIXME: Track the location at which the requirement was specified, and
// use it here.
Diags.Report(M->DefinitionLoc, diag::err_module_unavailable)
<< M->getFullModuleName() << Requirement.second << Requirement.first;
}
return true;
}
/// HandleIncludeDirective - The "\#include" tokens have just been read, read
/// the file to be included from the lexer, then include it! This is a common
/// routine with functionality shared between \#include, \#include_next and
/// \#import. LookupFrom is set when this is a \#include_next directive, it
/// specifies the file to start searching from.
void Preprocessor::HandleIncludeDirective(SourceLocation HashLoc,
Token &IncludeTok,
const DirectoryLookup *LookupFrom,
const FileEntry *LookupFromFile) {
Token FilenameTok;
if (LexHeaderName(FilenameTok))
return;
if (FilenameTok.isNot(tok::header_name)) {
Diag(FilenameTok.getLocation(), diag::err_pp_expects_filename);
if (FilenameTok.isNot(tok::eod))
DiscardUntilEndOfDirective();
return;
}
// Verify that there is nothing after the filename, other than EOD. Note
// that we allow macros that expand to nothing after the filename, because
// this falls into the category of "#include pp-tokens new-line" specified
// in C99 6.10.2p4.
SourceLocation EndLoc =
CheckEndOfDirective(IncludeTok.getIdentifierInfo()->getNameStart(), true);
auto Action = HandleHeaderIncludeOrImport(HashLoc, IncludeTok, FilenameTok,
EndLoc, LookupFrom, LookupFromFile);
switch (Action.Kind) {
case ImportAction::None:
case ImportAction::SkippedModuleImport:
break;
case ImportAction::ModuleBegin:
EnterAnnotationToken(SourceRange(HashLoc, EndLoc),
tok::annot_module_begin, Action.ModuleForHeader);
break;
case ImportAction::ModuleImport:
EnterAnnotationToken(SourceRange(HashLoc, EndLoc),
tok::annot_module_include, Action.ModuleForHeader);
break;
}
}
Optional<FileEntryRef> Preprocessor::LookupHeaderIncludeOrImport(
const DirectoryLookup *&CurDir, StringRef Filename,
SourceLocation FilenameLoc, CharSourceRange FilenameRange,
const Token &FilenameTok, bool &IsFrameworkFound, bool IsImportDecl,
bool &IsMapped, const DirectoryLookup *LookupFrom,
const FileEntry *LookupFromFile, StringRef LookupFilename,
SmallVectorImpl<char> &RelativePath, SmallVectorImpl<char> &SearchPath,
ModuleMap::KnownHeader &SuggestedModule, bool isAngled) {
Optional<FileEntryRef> File = LookupFile(
FilenameLoc, LookupFilename,
isAngled, LookupFrom, LookupFromFile, CurDir,
Callbacks ? &SearchPath : nullptr, Callbacks ? &RelativePath : nullptr,
&SuggestedModule, &IsMapped, &IsFrameworkFound);
if (File)
return File;
if (Callbacks) {
// Give the clients a chance to recover.
SmallString<128> RecoveryPath;
if (Callbacks->FileNotFound(Filename, RecoveryPath)) {
if (auto DE = FileMgr.getOptionalDirectoryRef(RecoveryPath)) {
// Add the recovery path to the list of search paths.
DirectoryLookup DL(*DE, SrcMgr::C_User, false);
HeaderInfo.AddSearchPath(DL, isAngled);
// Try the lookup again, skipping the cache.
Optional<FileEntryRef> File = LookupFile(
FilenameLoc,
LookupFilename, isAngled,
LookupFrom, LookupFromFile, CurDir, nullptr, nullptr,
&SuggestedModule, &IsMapped, /*IsFrameworkFound=*/nullptr,
/*SkipCache*/ true);
if (File)
return File;
}
}
}
if (SuppressIncludeNotFoundError)
return None;
// If the file could not be located and it was included via angle
// brackets, we can attempt a lookup as though it were a quoted path to
// provide the user with a possible fixit.
if (isAngled) {
Optional<FileEntryRef> File = LookupFile(
FilenameLoc, LookupFilename,
false, LookupFrom, LookupFromFile, CurDir,
Callbacks ? &SearchPath : nullptr, Callbacks ? &RelativePath : nullptr,
&SuggestedModule, &IsMapped,
/*IsFrameworkFound=*/nullptr);
if (File) {
Diag(FilenameTok, diag::err_pp_file_not_found_angled_include_not_fatal)
<< Filename << IsImportDecl
<< FixItHint::CreateReplacement(FilenameRange,
"\"" + Filename.str() + "\"");
return File;
}
}
// Check for likely typos due to leading or trailing non-isAlphanumeric
// characters
StringRef OriginalFilename = Filename;
if (LangOpts.SpellChecking) {
// A heuristic to correct a typo file name by removing leading and
// trailing non-isAlphanumeric characters.
auto CorrectTypoFilename = [](llvm::StringRef Filename) {
Filename = Filename.drop_until(isAlphanumeric);
while (!Filename.empty() && !isAlphanumeric(Filename.back())) {
Filename = Filename.drop_back();
}
return Filename;
};
StringRef TypoCorrectionName = CorrectTypoFilename(Filename);
#ifndef _WIN32
// Normalize slashes when compiling with -fms-extensions on non-Windows.
// This is unnecessary on Windows since the filesystem there handles
// backslashes.
SmallString<128> NormalizedTypoCorrectionPath;
if (LangOpts.MicrosoftExt) {
NormalizedTypoCorrectionPath = TypoCorrectionName;
llvm::sys::path::native(NormalizedTypoCorrectionPath);
TypoCorrectionName = NormalizedTypoCorrectionPath;
}
#endif
Optional<FileEntryRef> File = LookupFile(
FilenameLoc, TypoCorrectionName, isAngled, LookupFrom, LookupFromFile,
CurDir, Callbacks ? &SearchPath : nullptr,
Callbacks ? &RelativePath : nullptr, &SuggestedModule, &IsMapped,
/*IsFrameworkFound=*/nullptr);
if (File) {
auto Hint =
isAngled ? FixItHint::CreateReplacement(
FilenameRange, "<" + TypoCorrectionName.str() + ">")
: FixItHint::CreateReplacement(
FilenameRange, "\"" + TypoCorrectionName.str() + "\"");
Diag(FilenameTok, diag::err_pp_file_not_found_typo_not_fatal)
<< OriginalFilename << TypoCorrectionName << Hint;
// We found the file, so set the Filename to the name after typo
// correction.
Filename = TypoCorrectionName;
return File;
}
}
// If the file is still not found, just go with the vanilla diagnostic
assert(!File.hasValue() && "expected missing file");
Diag(FilenameTok, diag::err_pp_file_not_found)
<< OriginalFilename << FilenameRange;
if (IsFrameworkFound) {
size_t SlashPos = OriginalFilename.find('/');
assert(SlashPos != StringRef::npos &&
"Include with framework name should have '/' in the filename");
StringRef FrameworkName = OriginalFilename.substr(0, SlashPos);
FrameworkCacheEntry &CacheEntry =
HeaderInfo.LookupFrameworkCache(FrameworkName);
assert(CacheEntry.Directory && "Found framework should be in cache");
Diag(FilenameTok, diag::note_pp_framework_without_header)
<< OriginalFilename.substr(SlashPos + 1) << FrameworkName
<< CacheEntry.Directory->getName();
}
return None;
}
/// Handle either a #include-like directive or an import declaration that names
/// a header file.
///
/// \param HashLoc The location of the '#' token for an include, or
/// SourceLocation() for an import declaration.
/// \param IncludeTok The include / include_next / import token.
/// \param FilenameTok The header-name token.
/// \param EndLoc The location at which any imported macros become visible.
/// \param LookupFrom For #include_next, the starting directory for the
/// directory lookup.
/// \param LookupFromFile For #include_next, the starting file for the directory
/// lookup.
Preprocessor::ImportAction Preprocessor::HandleHeaderIncludeOrImport(
SourceLocation HashLoc, Token &IncludeTok, Token &FilenameTok,
SourceLocation EndLoc, const DirectoryLookup *LookupFrom,
const FileEntry *LookupFromFile) {
SmallString<128> FilenameBuffer;
StringRef Filename = getSpelling(FilenameTok, FilenameBuffer);
SourceLocation CharEnd = FilenameTok.getEndLoc();
CharSourceRange FilenameRange
= CharSourceRange::getCharRange(FilenameTok.getLocation(), CharEnd);
StringRef OriginalFilename = Filename;
bool isAngled =
GetIncludeFilenameSpelling(FilenameTok.getLocation(), Filename);
// If GetIncludeFilenameSpelling set the start ptr to null, there was an
// error.
if (Filename.empty())
return {ImportAction::None};
bool IsImportDecl = HashLoc.isInvalid();
SourceLocation StartLoc = IsImportDecl ? IncludeTok.getLocation() : HashLoc;
// Complain about attempts to #include files in an audit pragma.
if (PragmaARCCFCodeAuditedInfo.second.isValid()) {
Diag(StartLoc, diag::err_pp_include_in_arc_cf_code_audited) << IsImportDecl;
Diag(PragmaARCCFCodeAuditedInfo.second, diag::note_pragma_entered_here);
// Immediately leave the pragma.
PragmaARCCFCodeAuditedInfo = {nullptr, SourceLocation()};
}
// Complain about attempts to #include files in an assume-nonnull pragma.
if (PragmaAssumeNonNullLoc.isValid()) {
Diag(StartLoc, diag::err_pp_include_in_assume_nonnull) << IsImportDecl;
Diag(PragmaAssumeNonNullLoc, diag::note_pragma_entered_here);
// Immediately leave the pragma.
PragmaAssumeNonNullLoc = SourceLocation();
}
if (HeaderInfo.HasIncludeAliasMap()) {
// Map the filename with the brackets still attached. If the name doesn't
// map to anything, fall back on the filename we've already gotten the
// spelling for.
StringRef NewName = HeaderInfo.MapHeaderToIncludeAlias(OriginalFilename);
if (!NewName.empty())
Filename = NewName;
}
// Search include directories.
bool IsMapped = false;
bool IsFrameworkFound = false;
const DirectoryLookup *CurDir;
SmallString<1024> SearchPath;
SmallString<1024> RelativePath;
// We get the raw path only if we have 'Callbacks' to which we later pass
// the path.
ModuleMap::KnownHeader SuggestedModule;
SourceLocation FilenameLoc = FilenameTok.getLocation();
StringRef LookupFilename = Filename;
#ifndef _WIN32
// Normalize slashes when compiling with -fms-extensions on non-Windows. This
// is unnecessary on Windows since the filesystem there handles backslashes.
SmallString<128> NormalizedPath;
if (LangOpts.MicrosoftExt) {
NormalizedPath = Filename.str();
llvm::sys::path::native(NormalizedPath);
LookupFilename = NormalizedPath;
}
#endif
Optional<FileEntryRef> File = LookupHeaderIncludeOrImport(
CurDir, Filename, FilenameLoc, FilenameRange, FilenameTok,
IsFrameworkFound, IsImportDecl, IsMapped, LookupFrom, LookupFromFile,
LookupFilename, RelativePath, SearchPath, SuggestedModule, isAngled);
if (usingPCHWithThroughHeader() && SkippingUntilPCHThroughHeader) {
if (File && isPCHThroughHeader(&File->getFileEntry()))
SkippingUntilPCHThroughHeader = false;
return {ImportAction::None};
}
// Check for circular inclusion of the main file.
// We can't generate a consistent preamble with regard to the conditional
// stack if the main file is included again as due to the preamble bounds
// some directives (e.g. #endif of a header guard) will never be seen.
// Since this will lead to confusing errors, avoid the inclusion.
if (File && PreambleConditionalStack.isRecording() &&
SourceMgr.translateFile(&File->getFileEntry()) ==
SourceMgr.getMainFileID()) {
Diag(FilenameTok.getLocation(),
diag::err_pp_including_mainfile_in_preamble);
return {ImportAction::None};
}
// Should we enter the source file? Set to Skip if either the source file is
// known to have no effect beyond its effect on module visibility -- that is,
// if it's got an include guard that is already defined, set to Import if it
// is a modular header we've already built and should import.
enum { Enter, Import, Skip, IncludeLimitReached } Action = Enter;
if (PPOpts->SingleFileParseMode)
Action = IncludeLimitReached;
// If we've reached the max allowed include depth, it is usually due to an
// include cycle. Don't enter already processed files again as it can lead to
// reaching the max allowed include depth again.
if (Action == Enter && HasReachedMaxIncludeDepth && File &&
HeaderInfo.getFileInfo(&File->getFileEntry()).NumIncludes)
Action = IncludeLimitReached;
// Determine whether we should try to import the module for this #include, if
// there is one. Don't do so if precompiled module support is disabled or we
// are processing this module textually (because we're building the module).
if (Action == Enter && File && SuggestedModule && getLangOpts().Modules &&
!isForModuleBuilding(SuggestedModule.getModule(),
getLangOpts().CurrentModule,
getLangOpts().ModuleName)) {
// If this include corresponds to a module but that module is
// unavailable, diagnose the situation and bail out.
// FIXME: Remove this; loadModule does the same check (but produces
// slightly worse diagnostics).
if (checkModuleIsAvailable(getLangOpts(), getTargetInfo(), getDiagnostics(),
SuggestedModule.getModule())) {
Diag(FilenameTok.getLocation(),
diag::note_implicit_top_level_module_import_here)
<< SuggestedModule.getModule()->getTopLevelModuleName();
return {ImportAction::None};
}
// Compute the module access path corresponding to this module.
// FIXME: Should we have a second loadModule() overload to avoid this
// extra lookup step?
SmallVector<std::pair<IdentifierInfo *, SourceLocation>, 2> Path;
for (Module *Mod = SuggestedModule.getModule(); Mod; Mod = Mod->Parent)
Path.push_back(std::make_pair(getIdentifierInfo(Mod->Name),
FilenameTok.getLocation()));
std::reverse(Path.begin(), Path.end());
// Warn that we're replacing the include/import with a module import.
if (!IsImportDecl)
diagnoseAutoModuleImport(*this, StartLoc, IncludeTok, Path, CharEnd);
// Load the module to import its macros. We'll make the declarations
// visible when the parser gets here.
// FIXME: Pass SuggestedModule in here rather than converting it to a path
// and making the module loader convert it back again.
ModuleLoadResult Imported = TheModuleLoader.loadModule(
IncludeTok.getLocation(), Path, Module::Hidden,
/*IsInclusionDirective=*/true);
assert((Imported == nullptr || Imported == SuggestedModule.getModule()) &&
"the imported module is different than the suggested one");
if (Imported) {
Action = Import;
} else if (Imported.isMissingExpected()) {
// We failed to find a submodule that we assumed would exist (because it
// was in the directory of an umbrella header, for instance), but no
// actual module containing it exists (because the umbrella header is
// incomplete). Treat this as a textual inclusion.
SuggestedModule = ModuleMap::KnownHeader();
} else if (Imported.isConfigMismatch()) {
// On a configuration mismatch, enter the header textually. We still know
// that it's part of the corresponding module.
} else {
// We hit an error processing the import. Bail out.
if (hadModuleLoaderFatalFailure()) {
// With a fatal failure in the module loader, we abort parsing.
Token &Result = IncludeTok;
assert(CurLexer && "#include but no current lexer set!");
Result.startToken();
CurLexer->FormTokenWithChars(Result, CurLexer->BufferEnd, tok::eof);
CurLexer->cutOffLexing();
}
return {ImportAction::None};
}
}
// The #included file will be considered to be a system header if either it is
// in a system include directory, or if the #includer is a system include
// header.
SrcMgr::CharacteristicKind FileCharacter =
SourceMgr.getFileCharacteristic(FilenameTok.getLocation());
if (File)
FileCharacter = std::max(HeaderInfo.getFileDirFlavor(&File->getFileEntry()),
FileCharacter);
// If this is a '#import' or an import-declaration, don't re-enter the file.
//
// FIXME: If we have a suggested module for a '#include', and we've already
// visited this file, don't bother entering it again. We know it has no
// further effect.
bool EnterOnce =
IsImportDecl ||
IncludeTok.getIdentifierInfo()->getPPKeywordID() == tok::pp_import;
// Ask HeaderInfo if we should enter this #include file. If not, #including
// this file will have no effect.
if (Action == Enter && File &&
!HeaderInfo.ShouldEnterIncludeFile(*this, &File->getFileEntry(),
EnterOnce, getLangOpts().Modules,
SuggestedModule.getModule())) {
// Even if we've already preprocessed this header once and know that we
// don't need to see its contents again, we still need to import it if it's
// modular because we might not have imported it from this submodule before.
//
// FIXME: We don't do this when compiling a PCH because the AST
// serialization layer can't cope with it. This means we get local
// submodule visibility semantics wrong in that case.
Action = (SuggestedModule && !getLangOpts().CompilingPCH) ? Import : Skip;
}
if (Callbacks && !IsImportDecl) {
// Notify the callback object that we've seen an inclusion directive.
// FIXME: Use a different callback for a pp-import?
Callbacks->InclusionDirective(
HashLoc, IncludeTok, LookupFilename, isAngled, FilenameRange,
File ? &File->getFileEntry() : nullptr, SearchPath, RelativePath,
Action == Import ? SuggestedModule.getModule() : nullptr,
FileCharacter);
if (Action == Skip && File)
Callbacks->FileSkipped(*File, FilenameTok, FileCharacter);
}
if (!File)
return {ImportAction::None};
// If this is a C++20 pp-import declaration, diagnose if we didn't find any
// module corresponding to the named header.
if (IsImportDecl && !SuggestedModule) {
Diag(FilenameTok, diag::err_header_import_not_header_unit)
<< OriginalFilename << File->getName();
return {ImportAction::None};
}
// Issue a diagnostic if the name of the file on disk has a different case
// than the one we're about to open.
const bool CheckIncludePathPortability =
!IsMapped && !File->getFileEntry().tryGetRealPathName().empty();
if (CheckIncludePathPortability) {
StringRef Name = LookupFilename;
StringRef RealPathName = File->getFileEntry().tryGetRealPathName();
SmallVector<StringRef, 16> Components(llvm::sys::path::begin(Name),
llvm::sys::path::end(Name));
if (trySimplifyPath(Components, RealPathName)) {
SmallString<128> Path;
Path.reserve(Name.size()+2);
Path.push_back(isAngled ? '<' : '"');
bool isLeadingSeparator = llvm::sys::path::is_absolute(Name);
for (auto Component : Components) {
if (isLeadingSeparator)
isLeadingSeparator = false;
else
Path.append(Component);
// Append the separator the user used, or the close quote
Path.push_back(
Path.size() <= Filename.size() ? Filename[Path.size()-1] :
(isAngled ? '>' : '"'));
}
// For user files and known standard headers, by default we issue a diagnostic.
// For other system headers, we don't. They can be controlled separately.
auto DiagId = (FileCharacter == SrcMgr::C_User || warnByDefaultOnWrongCase(Name)) ?
diag::pp_nonportable_path : diag::pp_nonportable_system_path;
Diag(FilenameTok, DiagId) << Path <<
FixItHint::CreateReplacement(FilenameRange, Path);
}
}
switch (Action) {
case Skip:
// If we don't need to enter the file, stop now.
if (Module *M = SuggestedModule.getModule())
return {ImportAction::SkippedModuleImport, M};
return {ImportAction::None};
case IncludeLimitReached:
// If we reached our include limit and don't want to enter any more files,
// don't go any further.
return {ImportAction::None};
case Import: {
// If this is a module import, make it visible if needed.
Module *M = SuggestedModule.getModule();
assert(M && "no module to import");
makeModuleVisible(M, EndLoc);
if (IncludeTok.getIdentifierInfo()->getPPKeywordID() ==
tok::pp___include_macros)
return {ImportAction::None};
return {ImportAction::ModuleImport, M};
}
case Enter:
break;
}
// Check that we don't have infinite #include recursion.
if (IncludeMacroStack.size() == MaxAllowedIncludeStackDepth-1) {
Diag(FilenameTok, diag::err_pp_include_too_deep);
HasReachedMaxIncludeDepth = true;
return {ImportAction::None};
}
// Look up the file, create a File ID for it.
SourceLocation IncludePos = FilenameTok.getLocation();
// If the filename string was the result of macro expansions, set the include
// position on the file where it will be included and after the expansions.
if (IncludePos.isMacroID())
IncludePos = SourceMgr.getExpansionRange(IncludePos).getEnd();
FileID FID = SourceMgr.createFileID(*File, IncludePos, FileCharacter);
assert(FID.isValid() && "Expected valid file ID");
// If all is good, enter the new file!
if (EnterSourceFile(FID, CurDir, FilenameTok.getLocation()))
return {ImportAction::None};
// Determine if we're switching to building a new submodule, and which one.
if (auto *M = SuggestedModule.getModule()) {
if (M->getTopLevelModule()->ShadowingModule) {
// We are building a submodule that belongs to a shadowed module. This
// means we find header files in the shadowed module.
Diag(M->DefinitionLoc, diag::err_module_build_shadowed_submodule)
<< M->getFullModuleName();
Diag(M->getTopLevelModule()->ShadowingModule->DefinitionLoc,
diag::note_previous_definition);
return {ImportAction::None};
}
// When building a pch, -fmodule-name tells the compiler to textually
// include headers in the specified module. We are not building the
// specified module.
//
// FIXME: This is the wrong way to handle this. We should produce a PCH
// that behaves the same as the header would behave in a compilation using
// that PCH, which means we should enter the submodule. We need to teach
// the AST serialization layer to deal with the resulting AST.
if (getLangOpts().CompilingPCH &&
isForModuleBuilding(M, getLangOpts().CurrentModule,
getLangOpts().ModuleName))
return {ImportAction::None};
assert(!CurLexerSubmodule && "should not have marked this as a module yet");
CurLexerSubmodule = M;
// Let the macro handling code know that any future macros are within
// the new submodule.
EnterSubmodule(M, EndLoc, /*ForPragma*/false);
// Let the parser know that any future declarations are within the new
// submodule.
// FIXME: There's no point doing this if we're handling a #__include_macros
// directive.
return {ImportAction::ModuleBegin, M};
}
assert(!IsImportDecl && "failed to diagnose missing module for import decl");
return {ImportAction::None};
}
/// HandleIncludeNextDirective - Implements \#include_next.
///
void Preprocessor::HandleIncludeNextDirective(SourceLocation HashLoc,
Token &IncludeNextTok) {
Diag(IncludeNextTok, diag::ext_pp_include_next_directive);
// #include_next is like #include, except that we start searching after
// the current found directory. If we can't do this, issue a
// diagnostic.
const DirectoryLookup *Lookup = CurDirLookup;
const FileEntry *LookupFromFile = nullptr;
if (isInPrimaryFile() && LangOpts.IsHeaderFile) {
// If the main file is a header, then it's either for PCH/AST generation,
// or libclang opened it. Either way, handle it as a normal include below
// and do not complain about include_next.
} else if (isInPrimaryFile()) {
Lookup = nullptr;
Diag(IncludeNextTok, diag::pp_include_next_in_primary);
} else if (CurLexerSubmodule) {
// Start looking up in the directory *after* the one in which the current
// file would be found, if any.
assert(CurPPLexer && "#include_next directive in macro?");
LookupFromFile = CurPPLexer->getFileEntry();
Lookup = nullptr;
} else if (!Lookup) {
// The current file was not found by walking the include path. Either it
// is the primary file (handled above), or it was found by absolute path,
// or it was found relative to such a file.
// FIXME: Track enough information so we know which case we're in.
Diag(IncludeNextTok, diag::pp_include_next_absolute_path);
} else {
// Start looking up in the next directory.
++Lookup;
}
return HandleIncludeDirective(HashLoc, IncludeNextTok, Lookup,
LookupFromFile);
}
/// HandleMicrosoftImportDirective - Implements \#import for Microsoft Mode
void Preprocessor::HandleMicrosoftImportDirective(Token &Tok) {
// The Microsoft #import directive takes a type library and generates header
// files from it, and includes those. This is beyond the scope of what clang
// does, so we ignore it and error out. However, #import can optionally have
// trailing attributes that span multiple lines. We're going to eat those
// so we can continue processing from there.
Diag(Tok, diag::err_pp_import_directive_ms );
// Read tokens until we get to the end of the directive. Note that the
// directive can be split over multiple lines using the backslash character.
DiscardUntilEndOfDirective();
}
/// HandleImportDirective - Implements \#import.
///
void Preprocessor::HandleImportDirective(SourceLocation HashLoc,
Token &ImportTok) {
if (!LangOpts.ObjC) { // #import is standard for ObjC.
if (LangOpts.MSVCCompat)
return HandleMicrosoftImportDirective(ImportTok);
Diag(ImportTok, diag::ext_pp_import_directive);
}
return HandleIncludeDirective(HashLoc, ImportTok);
}
/// HandleIncludeMacrosDirective - The -imacros command line option turns into a
/// pseudo directive in the predefines buffer. This handles it by sucking all
/// tokens through the preprocessor and discarding them (only keeping the side
/// effects on the preprocessor).
void Preprocessor::HandleIncludeMacrosDirective(SourceLocation HashLoc,
Token &IncludeMacrosTok) {
// This directive should only occur in the predefines buffer. If not, emit an
// error and reject it.
SourceLocation Loc = IncludeMacrosTok.getLocation();
if (SourceMgr.getBufferName(Loc) != "<built-in>") {
Diag(IncludeMacrosTok.getLocation(),
diag::pp_include_macros_out_of_predefines);
DiscardUntilEndOfDirective();
return;
}
// Treat this as a normal #include for checking purposes. If this is
// successful, it will push a new lexer onto the include stack.
HandleIncludeDirective(HashLoc, IncludeMacrosTok);
Token TmpTok;
do {
Lex(TmpTok);
assert(TmpTok.isNot(tok::eof) && "Didn't find end of -imacros!");
} while (TmpTok.isNot(tok::hashhash));
}
//===----------------------------------------------------------------------===//
// Preprocessor Macro Directive Handling.
//===----------------------------------------------------------------------===//
/// ReadMacroParameterList - The ( starting a parameter list of a macro
/// definition has just been read. Lex the rest of the parameters and the
/// closing ), updating MI with what we learn. Return true if an error occurs
/// parsing the param list.
bool Preprocessor::ReadMacroParameterList(MacroInfo *MI, Token &Tok) {
SmallVector<IdentifierInfo*, 32> Parameters;
while (true) {
LexUnexpandedToken(Tok);
switch (Tok.getKind()) {
case tok::r_paren:
// Found the end of the parameter list.
if (Parameters.empty()) // #define FOO()
return false;
// Otherwise we have #define FOO(A,)
Diag(Tok, diag::err_pp_expected_ident_in_arg_list);
return true;
case tok::ellipsis: // #define X(... -> C99 varargs
if (!LangOpts.C99)
Diag(Tok, LangOpts.CPlusPlus11 ?
diag::warn_cxx98_compat_variadic_macro :
diag::ext_variadic_macro);
// OpenCL v1.2 s6.9.e: variadic macros are not supported.
if (LangOpts.OpenCL) {
Diag(Tok, diag::ext_pp_opencl_variadic_macros);
}
// Lex the token after the identifier.
LexUnexpandedToken(Tok);
if (Tok.isNot(tok::r_paren)) {
Diag(Tok, diag::err_pp_missing_rparen_in_macro_def);
return true;
}
// Add the __VA_ARGS__ identifier as a parameter.
Parameters.push_back(Ident__VA_ARGS__);
MI->setIsC99Varargs();
MI->setParameterList(Parameters, BP);
return false;
case tok::eod: // #define X(
Diag(Tok, diag::err_pp_missing_rparen_in_macro_def);
return true;
default:
// Handle keywords and identifiers here to accept things like
// #define Foo(for) for.
IdentifierInfo *II = Tok.getIdentifierInfo();
if (!II) {
// #define X(1
Diag(Tok, diag::err_pp_invalid_tok_in_arg_list);
return true;
}
// If this is already used as a parameter, it is used multiple times (e.g.
// #define X(A,A.
if (llvm::find(Parameters, II) != Parameters.end()) { // C99 6.10.3p6
Diag(Tok, diag::err_pp_duplicate_name_in_arg_list) << II;
return true;
}
// Add the parameter to the macro info.
Parameters.push_back(II);
// Lex the token after the identifier.
LexUnexpandedToken(Tok);
switch (Tok.getKind()) {
default: // #define X(A B
Diag(Tok, diag::err_pp_expected_comma_in_arg_list);
return true;
case tok::r_paren: // #define X(A)
MI->setParameterList(Parameters, BP);
return false;
case tok::comma: // #define X(A,
break;
case tok::ellipsis: // #define X(A... -> GCC extension
// Diagnose extension.
Diag(Tok, diag::ext_named_variadic_macro);
// Lex the token after the identifier.
LexUnexpandedToken(Tok);
if (Tok.isNot(tok::r_paren)) {
Diag(Tok, diag::err_pp_missing_rparen_in_macro_def);
return true;
}
MI->setIsGNUVarargs();
MI->setParameterList(Parameters, BP);
return false;
}
}
}
}
static bool isConfigurationPattern(Token &MacroName, MacroInfo *MI,
const LangOptions &LOptions) {
if (MI->getNumTokens() == 1) {
const Token &Value = MI->getReplacementToken(0);
// Macro that is identity, like '#define inline inline' is a valid pattern.
if (MacroName.getKind() == Value.getKind())
return true;
// Macro that maps a keyword to the same keyword decorated with leading/
// trailing underscores is a valid pattern:
// #define inline __inline
// #define inline __inline__
// #define inline _inline (in MS compatibility mode)
StringRef MacroText = MacroName.getIdentifierInfo()->getName();
if (IdentifierInfo *II = Value.getIdentifierInfo()) {
if (!II->isKeyword(LOptions))
return false;
StringRef ValueText = II->getName();
StringRef TrimmedValue = ValueText;
if (!ValueText.startswith("__")) {
if (ValueText.startswith("_"))
TrimmedValue = TrimmedValue.drop_front(1);
else
return false;
} else {
TrimmedValue = TrimmedValue.drop_front(2);
if (TrimmedValue.endswith("__"))
TrimmedValue = TrimmedValue.drop_back(2);
}
return TrimmedValue.equals(MacroText);
} else {
return false;
}
}
// #define inline
return MacroName.isOneOf(tok::kw_extern, tok::kw_inline, tok::kw_static,
tok::kw_const) &&
MI->getNumTokens() == 0;
}
// ReadOptionalMacroParameterListAndBody - This consumes all (i.e. the
// entire line) of the macro's tokens and adds them to MacroInfo, and while
// doing so performs certain validity checks including (but not limited to):
// - # (stringization) is followed by a macro parameter
//
// Returns a nullptr if an invalid sequence of tokens is encountered or returns
// a pointer to a MacroInfo object.
MacroInfo *Preprocessor::ReadOptionalMacroParameterListAndBody(
const Token &MacroNameTok, const bool ImmediatelyAfterHeaderGuard) {
Token LastTok = MacroNameTok;
// Create the new macro.
MacroInfo *const MI = AllocateMacroInfo(MacroNameTok.getLocation());
Token Tok;
LexUnexpandedToken(Tok);
// Ensure we consume the rest of the macro body if errors occur.
auto _ = llvm::make_scope_exit([&]() {
// The flag indicates if we are still waiting for 'eod'.
if (CurLexer->ParsingPreprocessorDirective)
DiscardUntilEndOfDirective();
});
// Used to un-poison and then re-poison identifiers of the __VA_ARGS__ ilk
// within their appropriate context.
VariadicMacroScopeGuard VariadicMacroScopeGuard(*this);
// If this is a function-like macro definition, parse the argument list,
// marking each of the identifiers as being used as macro arguments. Also,
// check other constraints on the first token of the macro body.
if (Tok.is(tok::eod)) {
if (ImmediatelyAfterHeaderGuard) {
// Save this macro information since it may part of a header guard.
CurPPLexer->MIOpt.SetDefinedMacro(MacroNameTok.getIdentifierInfo(),
MacroNameTok.getLocation());
}
// If there is no body to this macro, we have no special handling here.
} else if (Tok.hasLeadingSpace()) {
// This is a normal token with leading space. Clear the leading space
// marker on the first token to get proper expansion.
Tok.clearFlag(Token::LeadingSpace);
} else if (Tok.is(tok::l_paren)) {
// This is a function-like macro definition. Read the argument list.
MI->setIsFunctionLike();
if (ReadMacroParameterList(MI, LastTok))
return nullptr;
// If this is a definition of an ISO C/C++ variadic function-like macro (not
// using the GNU named varargs extension) inform our variadic scope guard
// which un-poisons and re-poisons certain identifiers (e.g. __VA_ARGS__)
// allowed only within the definition of a variadic macro.
if (MI->isC99Varargs()) {
VariadicMacroScopeGuard.enterScope();
}
// Read the first token after the arg list for down below.
LexUnexpandedToken(Tok);
} else if (LangOpts.C99 || LangOpts.CPlusPlus11) {
// C99 requires whitespace between the macro definition and the body. Emit
// a diagnostic for something like "#define X+".
Diag(Tok, diag::ext_c99_whitespace_required_after_macro_name);
} else {
// C90 6.8 TC1 says: "In the definition of an object-like macro, if the
// first character of a replacement list is not a character required by
// subclause 5.2.1, then there shall be white-space separation between the
// identifier and the replacement list.". 5.2.1 lists this set:
// "A-Za-z0-9!"#%&'()*+,_./:;<=>?[\]^_{|}~" as well as whitespace, which
// is irrelevant here.
bool isInvalid = false;
if (Tok.is(tok::at)) // @ is not in the list above.
isInvalid = true;
else if (Tok.is(tok::unknown)) {
// If we have an unknown token, it is something strange like "`". Since
// all of valid characters would have lexed into a single character
// token of some sort, we know this is not a valid case.
isInvalid = true;
}
if (isInvalid)
Diag(Tok, diag::ext_missing_whitespace_after_macro_name);
else
Diag(Tok, diag::warn_missing_whitespace_after_macro_name);
}
if (!Tok.is(tok::eod))
LastTok = Tok;
// Read the rest of the macro body.
if (MI->isObjectLike()) {
// Object-like macros are very simple, just read their body.
while (Tok.isNot(tok::eod)) {
LastTok = Tok;
MI->AddTokenToBody(Tok);
// Get the next token of the macro.
LexUnexpandedToken(Tok);
}
} else {
// Otherwise, read the body of a function-like macro. While we are at it,
// check C99 6.10.3.2p1: ensure that # operators are followed by macro
// parameters in function-like macro expansions.
VAOptDefinitionContext VAOCtx(*this);
while (Tok.isNot(tok::eod)) {
LastTok = Tok;
if (!Tok.isOneOf(tok::hash, tok::hashat, tok::hashhash)) {
MI->AddTokenToBody(Tok);
if (VAOCtx.isVAOptToken(Tok)) {
// If we're already within a VAOPT, emit an error.
if (VAOCtx.isInVAOpt()) {
Diag(Tok, diag::err_pp_vaopt_nested_use);
return nullptr;
}
// Ensure VAOPT is followed by a '(' .
LexUnexpandedToken(Tok);
if (Tok.isNot(tok::l_paren)) {
Diag(Tok, diag::err_pp_missing_lparen_in_vaopt_use);
return nullptr;
}
MI->AddTokenToBody(Tok);
VAOCtx.sawVAOptFollowedByOpeningParens(Tok.getLocation());
LexUnexpandedToken(Tok);
if (Tok.is(tok::hashhash)) {
Diag(Tok, diag::err_vaopt_paste_at_start);
return nullptr;
}
continue;
} else if (VAOCtx.isInVAOpt()) {
if (Tok.is(tok::r_paren)) {
if (VAOCtx.sawClosingParen()) {
const unsigned NumTokens = MI->getNumTokens();
assert(NumTokens >= 3 && "Must have seen at least __VA_OPT__( "
"and a subsequent tok::r_paren");
if (MI->getReplacementToken(NumTokens - 2).is(tok::hashhash)) {
Diag(Tok, diag::err_vaopt_paste_at_end);
return nullptr;
}
}
} else if (Tok.is(tok::l_paren)) {
VAOCtx.sawOpeningParen(Tok.getLocation());
}
}
// Get the next token of the macro.
LexUnexpandedToken(Tok);
continue;
}
// If we're in -traditional mode, then we should ignore stringification
// and token pasting. Mark the tokens as unknown so as not to confuse
// things.
if (getLangOpts().TraditionalCPP) {
Tok.setKind(tok::unknown);
MI->AddTokenToBody(Tok);
// Get the next token of the macro.
LexUnexpandedToken(Tok);
continue;
}
if (Tok.is(tok::hashhash)) {
// If we see token pasting, check if it looks like the gcc comma
// pasting extension. We'll use this information to suppress
// diagnostics later on.
// Get the next token of the macro.
LexUnexpandedToken(Tok);
if (Tok.is(tok::eod)) {
MI->AddTokenToBody(LastTok);
break;
}
unsigned NumTokens = MI->getNumTokens();
if (NumTokens && Tok.getIdentifierInfo() == Ident__VA_ARGS__ &&
MI->getReplacementToken(NumTokens-1).is(tok::comma))
MI->setHasCommaPasting();
// Things look ok, add the '##' token to the macro.
MI->AddTokenToBody(LastTok);
continue;
}
// Our Token is a stringization operator.
// Get the next token of the macro.
LexUnexpandedToken(Tok);
// Check for a valid macro arg identifier or __VA_OPT__.
if (!VAOCtx.isVAOptToken(Tok) &&
(Tok.getIdentifierInfo() == nullptr ||
MI->getParameterNum(Tok.getIdentifierInfo()) == -1)) {
// If this is assembler-with-cpp mode, we accept random gibberish after
// the '#' because '#' is often a comment character. However, change
// the kind of the token to tok::unknown so that the preprocessor isn't
// confused.
if (getLangOpts().AsmPreprocessor && Tok.isNot(tok::eod)) {
LastTok.setKind(tok::unknown);
MI->AddTokenToBody(LastTok);
continue;
} else {
Diag(Tok, diag::err_pp_stringize_not_parameter)
<< LastTok.is(tok::hashat);
return nullptr;
}
}
// Things look ok, add the '#' and param name tokens to the macro.
MI->AddTokenToBody(LastTok);
// If the token following '#' is VAOPT, let the next iteration handle it
// and check it for correctness, otherwise add the token and prime the
// loop with the next one.
if (!VAOCtx.isVAOptToken(Tok)) {
MI->AddTokenToBody(Tok);
LastTok = Tok;
// Get the next token of the macro.
LexUnexpandedToken(Tok);
}
}
if (VAOCtx.isInVAOpt()) {
assert(Tok.is(tok::eod) && "Must be at End Of preprocessing Directive");
Diag(Tok, diag::err_pp_expected_after)
<< LastTok.getKind() << tok::r_paren;
Diag(VAOCtx.getUnmatchedOpeningParenLoc(), diag::note_matching) << tok::l_paren;
return nullptr;
}
}
MI->setDefinitionEndLoc(LastTok.getLocation());
return MI;
}
/// HandleDefineDirective - Implements \#define. This consumes the entire macro
/// line then lets the caller lex the next real token.
void Preprocessor::HandleDefineDirective(
Token &DefineTok, const bool ImmediatelyAfterHeaderGuard) {
++NumDefined;
Token MacroNameTok;
bool MacroShadowsKeyword;
ReadMacroName(MacroNameTok, MU_Define, &MacroShadowsKeyword);
// Error reading macro name? If so, diagnostic already issued.
if (MacroNameTok.is(tok::eod))
return;
// If we are supposed to keep comments in #defines, reenable comment saving
// mode.
if (CurLexer) CurLexer->SetCommentRetentionState(KeepMacroComments);
MacroInfo *const MI = ReadOptionalMacroParameterListAndBody(
MacroNameTok, ImmediatelyAfterHeaderGuard);
if (!MI) return;
if (MacroShadowsKeyword &&
!isConfigurationPattern(MacroNameTok, MI, getLangOpts())) {
Diag(MacroNameTok, diag::warn_pp_macro_hides_keyword);
}
// Check that there is no paste (##) operator at the beginning or end of the
// replacement list.
unsigned NumTokens = MI->getNumTokens();
if (NumTokens != 0) {
if (MI->getReplacementToken(0).is(tok::hashhash)) {
Diag(MI->getReplacementToken(0), diag::err_paste_at_start);
return;
}
if (MI->getReplacementToken(NumTokens-1).is(tok::hashhash)) {
Diag(MI->getReplacementToken(NumTokens-1), diag::err_paste_at_end);
return;
}
}
// When skipping just warn about macros that do not match.
if (SkippingUntilPCHThroughHeader) {
const MacroInfo *OtherMI = getMacroInfo(MacroNameTok.getIdentifierInfo());
if (!OtherMI || !MI->isIdenticalTo(*OtherMI, *this,
/*Syntactic=*/LangOpts.MicrosoftExt))
Diag(MI->getDefinitionLoc(), diag::warn_pp_macro_def_mismatch_with_pch)
<< MacroNameTok.getIdentifierInfo();
return;
}
// Finally, if this identifier already had a macro defined for it, verify that
// the macro bodies are identical, and issue diagnostics if they are not.
if (const MacroInfo *OtherMI=getMacroInfo(MacroNameTok.getIdentifierInfo())) {
// In Objective-C, ignore attempts to directly redefine the builtin
// definitions of the ownership qualifiers. It's still possible to
// #undef them.
auto isObjCProtectedMacro = [](const IdentifierInfo *II) -> bool {
return II->isStr("__strong") ||
II->isStr("__weak") ||
II->isStr("__unsafe_unretained") ||
II->isStr("__autoreleasing");
};
if (getLangOpts().ObjC &&
SourceMgr.getFileID(OtherMI->getDefinitionLoc())
== getPredefinesFileID() &&
isObjCProtectedMacro(MacroNameTok.getIdentifierInfo())) {
// Warn if it changes the tokens.
if ((!getDiagnostics().getSuppressSystemWarnings() ||
!SourceMgr.isInSystemHeader(DefineTok.getLocation())) &&
!MI->isIdenticalTo(*OtherMI, *this,
/*Syntactic=*/LangOpts.MicrosoftExt)) {
Diag(MI->getDefinitionLoc(), diag::warn_pp_objc_macro_redef_ignored);
}
assert(!OtherMI->isWarnIfUnused());
return;
}
// It is very common for system headers to have tons of macro redefinitions
// and for warnings to be disabled in system headers. If this is the case,
// then don't bother calling MacroInfo::isIdenticalTo.
if (!getDiagnostics().getSuppressSystemWarnings() ||
!SourceMgr.isInSystemHeader(DefineTok.getLocation())) {
if (!OtherMI->isUsed() && OtherMI->isWarnIfUnused())
Diag(OtherMI->getDefinitionLoc(), diag::pp_macro_not_used);
// Warn if defining "__LINE__" and other builtins, per C99 6.10.8/4 and
// C++ [cpp.predefined]p4, but allow it as an extension.
if (OtherMI->isBuiltinMacro())
Diag(MacroNameTok, diag::ext_pp_redef_builtin_macro);
// Macros must be identical. This means all tokens and whitespace
// separation must be the same. C99 6.10.3p2.
else if (!OtherMI->isAllowRedefinitionsWithoutWarning() &&
!MI->isIdenticalTo(*OtherMI, *this, /*Syntactic=*/LangOpts.MicrosoftExt)) {
Diag(MI->getDefinitionLoc(), diag::ext_pp_macro_redef)
<< MacroNameTok.getIdentifierInfo();
Diag(OtherMI->getDefinitionLoc(), diag::note_previous_definition);
}
}
if (OtherMI->isWarnIfUnused())
WarnUnusedMacroLocs.erase(OtherMI->getDefinitionLoc());
}
DefMacroDirective *MD =
appendDefMacroDirective(MacroNameTok.getIdentifierInfo(), MI);
assert(!MI->isUsed());
// If we need warning for not using the macro, add its location in the
// warn-because-unused-macro set. If it gets used it will be removed from set.
if (getSourceManager().isInMainFile(MI->getDefinitionLoc()) &&
!Diags->isIgnored(diag::pp_macro_not_used, MI->getDefinitionLoc()) &&
!MacroExpansionInDirectivesOverride) {
MI->setIsWarnIfUnused(true);
WarnUnusedMacroLocs.insert(MI->getDefinitionLoc());
}
// If the callbacks want to know, tell them about the macro definition.
if (Callbacks)
Callbacks->MacroDefined(MacroNameTok, MD);
}
/// HandleUndefDirective - Implements \#undef.
///
void Preprocessor::HandleUndefDirective() {
++NumUndefined;
Token MacroNameTok;
ReadMacroName(MacroNameTok, MU_Undef);
// Error reading macro name? If so, diagnostic already issued.
if (MacroNameTok.is(tok::eod))
return;
// Check to see if this is the last token on the #undef line.
CheckEndOfDirective("undef");
// Okay, we have a valid identifier to undef.
auto *II = MacroNameTok.getIdentifierInfo();
auto MD = getMacroDefinition(II);
UndefMacroDirective *Undef = nullptr;
// If the macro is not defined, this is a noop undef.
if (const MacroInfo *MI = MD.getMacroInfo()) {
if (!MI->isUsed() && MI->isWarnIfUnused())
Diag(MI->getDefinitionLoc(), diag::pp_macro_not_used);
if (MI->isWarnIfUnused())
WarnUnusedMacroLocs.erase(MI->getDefinitionLoc());
Undef = AllocateUndefMacroDirective(MacroNameTok.getLocation());
}
// If the callbacks want to know, tell them about the macro #undef.
// Note: no matter if the macro was defined or not.
if (Callbacks)
Callbacks->MacroUndefined(MacroNameTok, MD, Undef);
if (Undef)
appendMacroDirective(II, Undef);
}
//===----------------------------------------------------------------------===//
// Preprocessor Conditional Directive Handling.
//===----------------------------------------------------------------------===//
/// HandleIfdefDirective - Implements the \#ifdef/\#ifndef directive. isIfndef
/// is true when this is a \#ifndef directive. ReadAnyTokensBeforeDirective is
/// true if any tokens have been returned or pp-directives activated before this
/// \#ifndef has been lexed.
///
void Preprocessor::HandleIfdefDirective(Token &Result,
const Token &HashToken,
bool isIfndef,
bool ReadAnyTokensBeforeDirective) {
++NumIf;
Token DirectiveTok = Result;
Token MacroNameTok;
ReadMacroName(MacroNameTok);
// Error reading macro name? If so, diagnostic already issued.
if (MacroNameTok.is(tok::eod)) {
// Skip code until we get to #endif. This helps with recovery by not
// emitting an error when the #endif is reached.
SkipExcludedConditionalBlock(HashToken.getLocation(),
DirectiveTok.getLocation(),
/*Foundnonskip*/ false, /*FoundElse*/ false);
return;
}
// Check to see if this is the last token on the #if[n]def line.
CheckEndOfDirective(isIfndef ? "ifndef" : "ifdef");
IdentifierInfo *MII = MacroNameTok.getIdentifierInfo();
auto MD = getMacroDefinition(MII);
MacroInfo *MI = MD.getMacroInfo();
if (CurPPLexer->getConditionalStackDepth() == 0) {
// If the start of a top-level #ifdef and if the macro is not defined,
// inform MIOpt that this might be the start of a proper include guard.
// Otherwise it is some other form of unknown conditional which we can't
// handle.
if (!ReadAnyTokensBeforeDirective && !MI) {
assert(isIfndef && "#ifdef shouldn't reach here");
CurPPLexer->MIOpt.EnterTopLevelIfndef(MII, MacroNameTok.getLocation());
} else
CurPPLexer->MIOpt.EnterTopLevelConditional();
}
// If there is a macro, process it.
if (MI) // Mark it used.
markMacroAsUsed(MI);
if (Callbacks) {
if (isIfndef)
Callbacks->Ifndef(DirectiveTok.getLocation(), MacroNameTok, MD);
else
Callbacks->Ifdef(DirectiveTok.getLocation(), MacroNameTok, MD);
}
bool RetainExcludedCB = PPOpts->RetainExcludedConditionalBlocks &&
getSourceManager().isInMainFile(DirectiveTok.getLocation());
// Should we include the stuff contained by this directive?
if (PPOpts->SingleFileParseMode && !MI) {
// In 'single-file-parse mode' undefined identifiers trigger parsing of all
// the directive blocks.
CurPPLexer->pushConditionalLevel(DirectiveTok.getLocation(),
/*wasskip*/false, /*foundnonskip*/false,
/*foundelse*/false);
} else if (!MI == isIfndef || RetainExcludedCB) {
// Yes, remember that we are inside a conditional, then lex the next token.
CurPPLexer->pushConditionalLevel(DirectiveTok.getLocation(),
/*wasskip*/false, /*foundnonskip*/true,
/*foundelse*/false);
} else {
// No, skip the contents of this block.
SkipExcludedConditionalBlock(HashToken.getLocation(),
DirectiveTok.getLocation(),
/*Foundnonskip*/ false,
/*FoundElse*/ false);
}
}
/// HandleIfDirective - Implements the \#if directive.
///
void Preprocessor::HandleIfDirective(Token &IfToken,
const Token &HashToken,
bool ReadAnyTokensBeforeDirective) {
++NumIf;
// Parse and evaluate the conditional expression.
IdentifierInfo *IfNDefMacro = nullptr;
const DirectiveEvalResult DER = EvaluateDirectiveExpression(IfNDefMacro);
const bool ConditionalTrue = DER.Conditional;
// If this condition is equivalent to #ifndef X, and if this is the first
// directive seen, handle it for the multiple-include optimization.
if (CurPPLexer->getConditionalStackDepth() == 0) {
if (!ReadAnyTokensBeforeDirective && IfNDefMacro && ConditionalTrue)
// FIXME: Pass in the location of the macro name, not the 'if' token.
CurPPLexer->MIOpt.EnterTopLevelIfndef(IfNDefMacro, IfToken.getLocation());
else
CurPPLexer->MIOpt.EnterTopLevelConditional();
}
if (Callbacks)
Callbacks->If(
IfToken.getLocation(), DER.ExprRange,
(ConditionalTrue ? PPCallbacks::CVK_True : PPCallbacks::CVK_False));
bool RetainExcludedCB = PPOpts->RetainExcludedConditionalBlocks &&
getSourceManager().isInMainFile(IfToken.getLocation());
// Should we include the stuff contained by this directive?
if (PPOpts->SingleFileParseMode && DER.IncludedUndefinedIds) {
// In 'single-file-parse mode' undefined identifiers trigger parsing of all
// the directive blocks.
CurPPLexer->pushConditionalLevel(IfToken.getLocation(), /*wasskip*/false,
/*foundnonskip*/false, /*foundelse*/false);
} else if (ConditionalTrue || RetainExcludedCB) {
// Yes, remember that we are inside a conditional, then lex the next token.
CurPPLexer->pushConditionalLevel(IfToken.getLocation(), /*wasskip*/false,
/*foundnonskip*/true, /*foundelse*/false);
} else {
// No, skip the contents of this block.
SkipExcludedConditionalBlock(HashToken.getLocation(), IfToken.getLocation(),
/*Foundnonskip*/ false,
/*FoundElse*/ false);
}
}
/// HandleEndifDirective - Implements the \#endif directive.
///
void Preprocessor::HandleEndifDirective(Token &EndifToken) {
++NumEndif;
// Check that this is the whole directive.
CheckEndOfDirective("endif");
PPConditionalInfo CondInfo;
if (CurPPLexer->popConditionalLevel(CondInfo)) {
// No conditionals on the stack: this is an #endif without an #if.
Diag(EndifToken, diag::err_pp_endif_without_if);
return;
}
// If this the end of a top-level #endif, inform MIOpt.
if (CurPPLexer->getConditionalStackDepth() == 0)
CurPPLexer->MIOpt.ExitTopLevelConditional();
assert(!CondInfo.WasSkipping && !CurPPLexer->LexingRawMode &&
"This code should only be reachable in the non-skipping case!");
if (Callbacks)
Callbacks->Endif(EndifToken.getLocation(), CondInfo.IfLoc);
}
/// HandleElseDirective - Implements the \#else directive.
///
void Preprocessor::HandleElseDirective(Token &Result, const Token &HashToken) {
++NumElse;
// #else directive in a non-skipping conditional... start skipping.
CheckEndOfDirective("else");
PPConditionalInfo CI;
if (CurPPLexer->popConditionalLevel(CI)) {
Diag(Result, diag::pp_err_else_without_if);
return;
}
// If this is a top-level #else, inform the MIOpt.
if (CurPPLexer->getConditionalStackDepth() == 0)
CurPPLexer->MIOpt.EnterTopLevelConditional();
// If this is a #else with a #else before it, report the error.
if (CI.FoundElse) Diag(Result, diag::pp_err_else_after_else);
if (Callbacks)
Callbacks->Else(Result.getLocation(), CI.IfLoc);
bool RetainExcludedCB = PPOpts->RetainExcludedConditionalBlocks &&
getSourceManager().isInMainFile(Result.getLocation());
if ((PPOpts->SingleFileParseMode && !CI.FoundNonSkip) || RetainExcludedCB) {
// In 'single-file-parse mode' undefined identifiers trigger parsing of all
// the directive blocks.
CurPPLexer->pushConditionalLevel(CI.IfLoc, /*wasskip*/false,
/*foundnonskip*/false, /*foundelse*/true);
return;
}
// Finally, skip the rest of the contents of this block.
SkipExcludedConditionalBlock(HashToken.getLocation(), CI.IfLoc,
/*Foundnonskip*/ true,
/*FoundElse*/ true, Result.getLocation());
}
/// HandleElifDirective - Implements the \#elif directive.
///
void Preprocessor::HandleElifDirective(Token &ElifToken,
const Token &HashToken) {
++NumElse;
// #elif directive in a non-skipping conditional... start skipping.
// We don't care what the condition is, because we will always skip it (since
// the block immediately before it was included).
SourceRange ConditionRange = DiscardUntilEndOfDirective();
PPConditionalInfo CI;
if (CurPPLexer->popConditionalLevel(CI)) {
Diag(ElifToken, diag::pp_err_elif_without_if);
return;
}
// If this is a top-level #elif, inform the MIOpt.
if (CurPPLexer->getConditionalStackDepth() == 0)
CurPPLexer->MIOpt.EnterTopLevelConditional();
// If this is a #elif with a #else before it, report the error.
if (CI.FoundElse) Diag(ElifToken, diag::pp_err_elif_after_else);
if (Callbacks)
Callbacks->Elif(ElifToken.getLocation(), ConditionRange,
PPCallbacks::CVK_NotEvaluated, CI.IfLoc);
bool RetainExcludedCB = PPOpts->RetainExcludedConditionalBlocks &&
getSourceManager().isInMainFile(ElifToken.getLocation());
if ((PPOpts->SingleFileParseMode && !CI.FoundNonSkip) || RetainExcludedCB) {
// In 'single-file-parse mode' undefined identifiers trigger parsing of all
// the directive blocks.
CurPPLexer->pushConditionalLevel(ElifToken.getLocation(), /*wasskip*/false,
/*foundnonskip*/false, /*foundelse*/false);
return;
}
// Finally, skip the rest of the contents of this block.
SkipExcludedConditionalBlock(
HashToken.getLocation(), CI.IfLoc, /*Foundnonskip*/ true,
/*FoundElse*/ CI.FoundElse, ElifToken.getLocation());
}
|