aboutsummaryrefslogtreecommitdiff
path: root/libcpp/lex.cc
blob: b1107920c947eb07981c2dba583c859dba54b57a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
/* CPP Library - lexical analysis.
   Copyright (C) 2000-2022 Free Software Foundation, Inc.
   Contributed by Per Bothner, 1994-95.
   Based on CCCP program by Paul Rubin, June 1986
   Adapted to ANSI C, Richard Stallman, Jan 1987
   Broken out to separate file, Zack Weinberg, Mar 2000

This program is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by the
Free Software Foundation; either version 3, or (at your option) any
later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with this program; see the file COPYING3.  If not see
<http://www.gnu.org/licenses/>.  */

#include "config.h"
#include "system.h"
#include "cpplib.h"
#include "internal.h"

enum spell_type
{
  SPELL_OPERATOR = 0,
  SPELL_IDENT,
  SPELL_LITERAL,
  SPELL_NONE
};

struct token_spelling
{
  enum spell_type category;
  const unsigned char *name;
};

static const unsigned char *const digraph_spellings[] =
{ UC"%:", UC"%:%:", UC"<:", UC":>", UC"<%", UC"%>" };

#define OP(e, s) { SPELL_OPERATOR, UC s  },
#define TK(e, s) { SPELL_ ## s,    UC #e },
static const struct token_spelling token_spellings[N_TTYPES] = { TTYPE_TABLE };
#undef OP
#undef TK

#define TOKEN_SPELL(token) (token_spellings[(token)->type].category)
#define TOKEN_NAME(token) (token_spellings[(token)->type].name)

/* ISO 10646 defines the UCS codespace as the range 0-0x10FFFF inclusive.  */
#define UCS_LIMIT 0x10FFFF

static void add_line_note (cpp_buffer *, const uchar *, unsigned int);
static int skip_line_comment (cpp_reader *);
static void skip_whitespace (cpp_reader *, cppchar_t);
static void lex_string (cpp_reader *, cpp_token *, const uchar *);
static void save_comment (cpp_reader *, cpp_token *, const uchar *, cppchar_t);
static void store_comment (cpp_reader *, cpp_token *);
static void create_literal (cpp_reader *, cpp_token *, const uchar *,
			    unsigned int, enum cpp_ttype);
static bool warn_in_comment (cpp_reader *, _cpp_line_note *);
static int name_p (cpp_reader *, const cpp_string *);
static tokenrun *next_tokenrun (tokenrun *);

static _cpp_buff *new_buff (size_t);


/* Utility routine:

   Compares, the token TOKEN to the NUL-terminated string STRING.
   TOKEN must be a CPP_NAME.  Returns 1 for equal, 0 for unequal.  */
int
cpp_ideq (const cpp_token *token, const char *string)
{
  if (token->type != CPP_NAME)
    return 0;

  return !ustrcmp (NODE_NAME (token->val.node.node), (const uchar *) string);
}

/* Record a note TYPE at byte POS into the current cleaned logical
   line.  */
static void
add_line_note (cpp_buffer *buffer, const uchar *pos, unsigned int type)
{
  if (buffer->notes_used == buffer->notes_cap)
    {
      buffer->notes_cap = buffer->notes_cap * 2 + 200;
      buffer->notes = XRESIZEVEC (_cpp_line_note, buffer->notes,
                                  buffer->notes_cap);
    }

  buffer->notes[buffer->notes_used].pos = pos;
  buffer->notes[buffer->notes_used].type = type;
  buffer->notes_used++;
}


/* Fast path to find line special characters using optimized character
   scanning algorithms.  Anything complicated falls back to the slow
   path below.  Since this loop is very hot it's worth doing these kinds
   of optimizations.

   One of the paths through the ifdefs should provide 

     const uchar *search_line_fast (const uchar *s, const uchar *end);

   Between S and END, search for \n, \r, \\, ?.  Return a pointer to
   the found character.

   Note that the last character of the buffer is *always* a newline,
   as forced by _cpp_convert_input.  This fact can be used to avoid
   explicitly looking for the end of the buffer.  */

/* Configure gives us an ifdef test.  */
#ifndef WORDS_BIGENDIAN
#define WORDS_BIGENDIAN 0
#endif

/* We'd like the largest integer that fits into a register.  There's nothing
   in <stdint.h> that gives us that.  For most hosts this is unsigned long,
   but MS decided on an LLP64 model.  Thankfully when building with GCC we
   can get the "real" word size.  */
#ifdef __GNUC__
typedef unsigned int word_type __attribute__((__mode__(__word__)));
#else
typedef unsigned long word_type;
#endif

/* The code below is only expecting sizes 4 or 8.
   Die at compile-time if this expectation is violated.  */
typedef char check_word_type_size
  [(sizeof(word_type) == 8 || sizeof(word_type) == 4) * 2 - 1];

/* Return X with the first N bytes forced to values that won't match one
   of the interesting characters.  Note that NUL is not interesting.  */

static inline word_type
acc_char_mask_misalign (word_type val, unsigned int n)
{
  word_type mask = -1;
  if (WORDS_BIGENDIAN)
    mask >>= n * 8;
  else
    mask <<= n * 8;
  return val & mask;
}

/* Return X replicated to all byte positions within WORD_TYPE.  */

static inline word_type
acc_char_replicate (uchar x)
{
  word_type ret;

  ret = (x << 24) | (x << 16) | (x << 8) | x;
  if (sizeof(word_type) == 8)
    ret = (ret << 16 << 16) | ret;
  return ret;
}

/* Return non-zero if some byte of VAL is (probably) C.  */

static inline word_type
acc_char_cmp (word_type val, word_type c)
{
#if defined(__GNUC__) && defined(__alpha__)
  /* We can get exact results using a compare-bytes instruction.  
     Get (val == c) via (0 >= (val ^ c)).  */
  return __builtin_alpha_cmpbge (0, val ^ c);
#else
  word_type magic = 0x7efefefeU;
  if (sizeof(word_type) == 8)
    magic = (magic << 16 << 16) | 0xfefefefeU;
  magic |= 1;

  val ^= c;
  return ((val + magic) ^ ~val) & ~magic;
#endif
}

/* Given the result of acc_char_cmp is non-zero, return the index of
   the found character.  If this was a false positive, return -1.  */

static inline int
acc_char_index (word_type cmp ATTRIBUTE_UNUSED,
		word_type val ATTRIBUTE_UNUSED)
{
#if defined(__GNUC__) && defined(__alpha__) && !WORDS_BIGENDIAN
  /* The cmpbge instruction sets *bits* of the result corresponding to
     matches in the bytes with no false positives.  */
  return __builtin_ctzl (cmp);
#else
  unsigned int i;

  /* ??? It would be nice to force unrolling here,
     and have all of these constants folded.  */
  for (i = 0; i < sizeof(word_type); ++i)
    {
      uchar c;
      if (WORDS_BIGENDIAN)
	c = (val >> (sizeof(word_type) - i - 1) * 8) & 0xff;
      else
	c = (val >> i * 8) & 0xff;

      if (c == '\n' || c == '\r' || c == '\\' || c == '?')
	return i;
    }

  return -1;
#endif
}

/* A version of the fast scanner using bit fiddling techniques.
 
   For 32-bit words, one would normally perform 16 comparisons and
   16 branches.  With this algorithm one performs 24 arithmetic
   operations and one branch.  Whether this is faster with a 32-bit
   word size is going to be somewhat system dependent.

   For 64-bit words, we eliminate twice the number of comparisons
   and branches without increasing the number of arithmetic operations.
   It's almost certainly going to be a win with 64-bit word size.  */

static const uchar * search_line_acc_char (const uchar *, const uchar *)
  ATTRIBUTE_UNUSED;

static const uchar *
search_line_acc_char (const uchar *s, const uchar *end ATTRIBUTE_UNUSED)
{
  const word_type repl_nl = acc_char_replicate ('\n');
  const word_type repl_cr = acc_char_replicate ('\r');
  const word_type repl_bs = acc_char_replicate ('\\');
  const word_type repl_qm = acc_char_replicate ('?');

  unsigned int misalign;
  const word_type *p;
  word_type val, t;
  
  /* Align the buffer.  Mask out any bytes from before the beginning.  */
  p = (word_type *)((uintptr_t)s & -sizeof(word_type));
  val = *p;
  misalign = (uintptr_t)s & (sizeof(word_type) - 1);
  if (misalign)
    val = acc_char_mask_misalign (val, misalign);

  /* Main loop.  */
  while (1)
    {
      t  = acc_char_cmp (val, repl_nl);
      t |= acc_char_cmp (val, repl_cr);
      t |= acc_char_cmp (val, repl_bs);
      t |= acc_char_cmp (val, repl_qm);

      if (__builtin_expect (t != 0, 0))
	{
	  int i = acc_char_index (t, val);
	  if (i >= 0)
	    return (const uchar *)p + i;
	}

      val = *++p;
    }
}

/* Disable on Solaris 2/x86 until the following problem can be properly
   autoconfed:

   The Solaris 10+ assembler tags objects with the instruction set
   extensions used, so SSE4.2 executables cannot run on machines that
   don't support that extension.  */

#if (GCC_VERSION >= 4005) && (__GNUC__ >= 5 || !defined(__PIC__)) && (defined(__i386__) || defined(__x86_64__)) && !(defined(__sun__) && defined(__svr4__))

/* Replicated character data to be shared between implementations.
   Recall that outside of a context with vector support we can't
   define compatible vector types, therefore these are all defined
   in terms of raw characters.  */
static const char repl_chars[4][16] __attribute__((aligned(16))) = {
  { '\n', '\n', '\n', '\n', '\n', '\n', '\n', '\n',
    '\n', '\n', '\n', '\n', '\n', '\n', '\n', '\n' },
  { '\r', '\r', '\r', '\r', '\r', '\r', '\r', '\r',
    '\r', '\r', '\r', '\r', '\r', '\r', '\r', '\r' },
  { '\\', '\\', '\\', '\\', '\\', '\\', '\\', '\\',
    '\\', '\\', '\\', '\\', '\\', '\\', '\\', '\\' },
  { '?', '?', '?', '?', '?', '?', '?', '?',
    '?', '?', '?', '?', '?', '?', '?', '?' },
};

/* A version of the fast scanner using MMX vectorized byte compare insns.

   This uses the PMOVMSKB instruction which was introduced with "MMX2",
   which was packaged into SSE1; it is also present in the AMD MMX
   extension.  Mark the function as using "sse" so that we emit a real
   "emms" instruction, rather than the 3dNOW "femms" instruction.  */

static const uchar *
#ifndef __SSE__
__attribute__((__target__("sse")))
#endif
search_line_mmx (const uchar *s, const uchar *end ATTRIBUTE_UNUSED)
{
  typedef char v8qi __attribute__ ((__vector_size__ (8)));
  typedef int __m64 __attribute__ ((__vector_size__ (8), __may_alias__));

  const v8qi repl_nl = *(const v8qi *)repl_chars[0];
  const v8qi repl_cr = *(const v8qi *)repl_chars[1];
  const v8qi repl_bs = *(const v8qi *)repl_chars[2];
  const v8qi repl_qm = *(const v8qi *)repl_chars[3];

  unsigned int misalign, found, mask;
  const v8qi *p;
  v8qi data, t, c;

  /* Align the source pointer.  While MMX doesn't generate unaligned data
     faults, this allows us to safely scan to the end of the buffer without
     reading beyond the end of the last page.  */
  misalign = (uintptr_t)s & 7;
  p = (const v8qi *)((uintptr_t)s & -8);
  data = *p;

  /* Create a mask for the bytes that are valid within the first
     16-byte block.  The Idea here is that the AND with the mask
     within the loop is "free", since we need some AND or TEST
     insn in order to set the flags for the branch anyway.  */
  mask = -1u << misalign;

  /* Main loop processing 8 bytes at a time.  */
  goto start;
  do
    {
      data = *++p;
      mask = -1;

    start:
      t = __builtin_ia32_pcmpeqb(data, repl_nl);
      c = __builtin_ia32_pcmpeqb(data, repl_cr);
      t = (v8qi) __builtin_ia32_por ((__m64)t, (__m64)c);
      c = __builtin_ia32_pcmpeqb(data, repl_bs);
      t = (v8qi) __builtin_ia32_por ((__m64)t, (__m64)c);
      c = __builtin_ia32_pcmpeqb(data, repl_qm);
      t = (v8qi) __builtin_ia32_por ((__m64)t, (__m64)c);
      found = __builtin_ia32_pmovmskb (t);
      found &= mask;
    }
  while (!found);

  __builtin_ia32_emms ();

  /* FOUND contains 1 in bits for which we matched a relevant
     character.  Conversion to the byte index is trivial.  */
  found = __builtin_ctz(found);
  return (const uchar *)p + found;
}

/* A version of the fast scanner using SSE2 vectorized byte compare insns.  */

static const uchar *
#ifndef __SSE2__
__attribute__((__target__("sse2")))
#endif
search_line_sse2 (const uchar *s, const uchar *end ATTRIBUTE_UNUSED)
{
  typedef char v16qi __attribute__ ((__vector_size__ (16)));

  const v16qi repl_nl = *(const v16qi *)repl_chars[0];
  const v16qi repl_cr = *(const v16qi *)repl_chars[1];
  const v16qi repl_bs = *(const v16qi *)repl_chars[2];
  const v16qi repl_qm = *(const v16qi *)repl_chars[3];

  unsigned int misalign, found, mask;
  const v16qi *p;
  v16qi data, t;

  /* Align the source pointer.  */
  misalign = (uintptr_t)s & 15;
  p = (const v16qi *)((uintptr_t)s & -16);
  data = *p;

  /* Create a mask for the bytes that are valid within the first
     16-byte block.  The Idea here is that the AND with the mask
     within the loop is "free", since we need some AND or TEST
     insn in order to set the flags for the branch anyway.  */
  mask = -1u << misalign;

  /* Main loop processing 16 bytes at a time.  */
  goto start;
  do
    {
      data = *++p;
      mask = -1;

    start:
      t  = data == repl_nl;
      t |= data == repl_cr;
      t |= data == repl_bs;
      t |= data == repl_qm;
      found = __builtin_ia32_pmovmskb128 (t);
      found &= mask;
    }
  while (!found);

  /* FOUND contains 1 in bits for which we matched a relevant
     character.  Conversion to the byte index is trivial.  */
  found = __builtin_ctz(found);
  return (const uchar *)p + found;
}

#ifdef HAVE_SSE4
/* A version of the fast scanner using SSE 4.2 vectorized string insns.  */

static const uchar *
#ifndef __SSE4_2__
__attribute__((__target__("sse4.2")))
#endif
search_line_sse42 (const uchar *s, const uchar *end)
{
  typedef char v16qi __attribute__ ((__vector_size__ (16)));
  static const v16qi search = { '\n', '\r', '?', '\\' };

  uintptr_t si = (uintptr_t)s;
  uintptr_t index;

  /* Check for unaligned input.  */
  if (si & 15)
    {
      v16qi sv;

      if (__builtin_expect (end - s < 16, 0)
	  && __builtin_expect ((si & 0xfff) > 0xff0, 0))
	{
	  /* There are less than 16 bytes left in the buffer, and less
	     than 16 bytes left on the page.  Reading 16 bytes at this
	     point might generate a spurious page fault.  Defer to the
	     SSE2 implementation, which already handles alignment.  */
	  return search_line_sse2 (s, end);
	}

      /* ??? The builtin doesn't understand that the PCMPESTRI read from
	 memory need not be aligned.  */
      sv = __builtin_ia32_loaddqu ((const char *) s);
      index = __builtin_ia32_pcmpestri128 (search, 4, sv, 16, 0);

      if (__builtin_expect (index < 16, 0))
	goto found;

      /* Advance the pointer to an aligned address.  We will re-scan a
	 few bytes, but we no longer need care for reading past the
	 end of a page, since we're guaranteed a match.  */
      s = (const uchar *)((si + 15) & -16);
    }

  /* Main loop, processing 16 bytes at a time.  */
#ifdef __GCC_ASM_FLAG_OUTPUTS__
  while (1)
    {
      char f;

      /* By using inline assembly instead of the builtin,
	 we can use the result, as well as the flags set.  */
      __asm ("%vpcmpestri\t$0, %2, %3"
	     : "=c"(index), "=@ccc"(f)
	     : "m"(*s), "x"(search), "a"(4), "d"(16));
      if (f)
	break;
      
      s += 16;
    }
#else
  s -= 16;
  /* By doing the whole loop in inline assembly,
     we can make proper use of the flags set.  */
  __asm (      ".balign 16\n"
	"0:	add $16, %1\n"
	"	%vpcmpestri\t$0, (%1), %2\n"
	"	jnc 0b"
	: "=&c"(index), "+r"(s)
	: "x"(search), "a"(4), "d"(16));
#endif

 found:
  return s + index;
}

#else
/* Work around out-dated assemblers without sse4 support.  */
#define search_line_sse42 search_line_sse2
#endif

/* Check the CPU capabilities.  */

#include "../gcc/config/i386/cpuid.h"

typedef const uchar * (*search_line_fast_type) (const uchar *, const uchar *);
static search_line_fast_type search_line_fast;

#define HAVE_init_vectorized_lexer 1
static inline void
init_vectorized_lexer (void)
{
  unsigned dummy, ecx = 0, edx = 0;
  search_line_fast_type impl = search_line_acc_char;
  int minimum = 0;

#if defined(__SSE4_2__)
  minimum = 3;
#elif defined(__SSE2__)
  minimum = 2;
#elif defined(__SSE__)
  minimum = 1;
#endif

  if (minimum == 3)
    impl = search_line_sse42;
  else if (__get_cpuid (1, &dummy, &dummy, &ecx, &edx) || minimum == 2)
    {
      if (minimum == 3 || (ecx & bit_SSE4_2))
        impl = search_line_sse42;
      else if (minimum == 2 || (edx & bit_SSE2))
	impl = search_line_sse2;
      else if (minimum == 1 || (edx & bit_SSE))
	impl = search_line_mmx;
    }
  else if (__get_cpuid (0x80000001, &dummy, &dummy, &dummy, &edx))
    {
      if (minimum == 1
	  || (edx & (bit_MMXEXT | bit_CMOV)) == (bit_MMXEXT | bit_CMOV))
	impl = search_line_mmx;
    }

  search_line_fast = impl;
}

#elif (GCC_VERSION >= 4005) && defined(_ARCH_PWR8) && defined(__ALTIVEC__)

/* A vection of the fast scanner using AltiVec vectorized byte compares
   and VSX unaligned loads (when VSX is available).  This is otherwise
   the same as the AltiVec version.  */

ATTRIBUTE_NO_SANITIZE_UNDEFINED
static const uchar *
search_line_fast (const uchar *s, const uchar *end ATTRIBUTE_UNUSED)
{
  typedef __attribute__((altivec(vector))) unsigned char vc;

  const vc repl_nl = {
    '\n', '\n', '\n', '\n', '\n', '\n', '\n', '\n', 
    '\n', '\n', '\n', '\n', '\n', '\n', '\n', '\n'
  };
  const vc repl_cr = {
    '\r', '\r', '\r', '\r', '\r', '\r', '\r', '\r', 
    '\r', '\r', '\r', '\r', '\r', '\r', '\r', '\r'
  };
  const vc repl_bs = {
    '\\', '\\', '\\', '\\', '\\', '\\', '\\', '\\', 
    '\\', '\\', '\\', '\\', '\\', '\\', '\\', '\\'
  };
  const vc repl_qm = {
    '?', '?', '?', '?', '?', '?', '?', '?', 
    '?', '?', '?', '?', '?', '?', '?', '?', 
  };
  const vc zero = { 0 };

  vc data, t;

  /* Main loop processing 16 bytes at a time.  */
  do
    {
      vc m_nl, m_cr, m_bs, m_qm;

      data = __builtin_vec_vsx_ld (0, s);
      s += 16;

      m_nl = (vc) __builtin_vec_cmpeq(data, repl_nl);
      m_cr = (vc) __builtin_vec_cmpeq(data, repl_cr);
      m_bs = (vc) __builtin_vec_cmpeq(data, repl_bs);
      m_qm = (vc) __builtin_vec_cmpeq(data, repl_qm);
      t = (m_nl | m_cr) | (m_bs | m_qm);

      /* T now contains 0xff in bytes for which we matched one of the relevant
	 characters.  We want to exit the loop if any byte in T is non-zero.
	 Below is the expansion of vec_any_ne(t, zero).  */
    }
  while (!__builtin_vec_vcmpeq_p(/*__CR6_LT_REV*/3, t, zero));

  /* Restore s to to point to the 16 bytes we just processed.  */
  s -= 16;

  {
#define N  (sizeof(vc) / sizeof(long))

    union {
      vc v;
      /* Statically assert that N is 2 or 4.  */
      unsigned long l[(N == 2 || N == 4) ? N : -1];
    } u;
    unsigned long l, i = 0;

    u.v = t;

    /* Find the first word of T that is non-zero.  */
    switch (N)
      {
      case 4:
	l = u.l[i++];
	if (l != 0)
	  break;
	s += sizeof(unsigned long);
	l = u.l[i++];
	if (l != 0)
	  break;
	s += sizeof(unsigned long);
	/* FALLTHRU */
      case 2:
	l = u.l[i++];
	if (l != 0)
	  break;
	s += sizeof(unsigned long);
	l = u.l[i];
      }

    /* L now contains 0xff in bytes for which we matched one of the
       relevant characters.  We can find the byte index by finding
       its bit index and dividing by 8.  */
#ifdef __BIG_ENDIAN__
    l = __builtin_clzl(l) >> 3;
#else
    l = __builtin_ctzl(l) >> 3;
#endif
    return s + l;

#undef N
  }
}

#elif (GCC_VERSION >= 4005) && defined(__ALTIVEC__) && defined (__BIG_ENDIAN__)

/* A vection of the fast scanner using AltiVec vectorized byte compares.
   This cannot be used for little endian because vec_lvsl/lvsr are
   deprecated for little endian and the code won't work properly.  */
/* ??? Unfortunately, attribute(target("altivec")) is not yet supported,
   so we can't compile this function without -maltivec on the command line
   (or implied by some other switch).  */

static const uchar *
search_line_fast (const uchar *s, const uchar *end ATTRIBUTE_UNUSED)
{
  typedef __attribute__((altivec(vector))) unsigned char vc;

  const vc repl_nl = {
    '\n', '\n', '\n', '\n', '\n', '\n', '\n', '\n', 
    '\n', '\n', '\n', '\n', '\n', '\n', '\n', '\n'
  };
  const vc repl_cr = {
    '\r', '\r', '\r', '\r', '\r', '\r', '\r', '\r', 
    '\r', '\r', '\r', '\r', '\r', '\r', '\r', '\r'
  };
  const vc repl_bs = {
    '\\', '\\', '\\', '\\', '\\', '\\', '\\', '\\', 
    '\\', '\\', '\\', '\\', '\\', '\\', '\\', '\\'
  };
  const vc repl_qm = {
    '?', '?', '?', '?', '?', '?', '?', '?', 
    '?', '?', '?', '?', '?', '?', '?', '?', 
  };
  const vc ones = {
    -1, -1, -1, -1, -1, -1, -1, -1,
    -1, -1, -1, -1, -1, -1, -1, -1,
  };
  const vc zero = { 0 };

  vc data, mask, t;

  /* Altivec loads automatically mask addresses with -16.  This lets us
     issue the first load as early as possible.  */
  data = __builtin_vec_ld(0, (const vc *)s);

  /* Discard bytes before the beginning of the buffer.  Do this by
     beginning with all ones and shifting in zeros according to the
     mis-alignment.  The LVSR instruction pulls the exact shift we
     want from the address.  */
  mask = __builtin_vec_lvsr(0, s);
  mask = __builtin_vec_perm(zero, ones, mask);
  data &= mask;

  /* While altivec loads mask addresses, we still need to align S so
     that the offset we compute at the end is correct.  */
  s = (const uchar *)((uintptr_t)s & -16);

  /* Main loop processing 16 bytes at a time.  */
  goto start;
  do
    {
      vc m_nl, m_cr, m_bs, m_qm;

      s += 16;
      data = __builtin_vec_ld(0, (const vc *)s);

    start:
      m_nl = (vc) __builtin_vec_cmpeq(data, repl_nl);
      m_cr = (vc) __builtin_vec_cmpeq(data, repl_cr);
      m_bs = (vc) __builtin_vec_cmpeq(data, repl_bs);
      m_qm = (vc) __builtin_vec_cmpeq(data, repl_qm);
      t = (m_nl | m_cr) | (m_bs | m_qm);

      /* T now contains 0xff in bytes for which we matched one of the relevant
	 characters.  We want to exit the loop if any byte in T is non-zero.
	 Below is the expansion of vec_any_ne(t, zero).  */
    }
  while (!__builtin_vec_vcmpeq_p(/*__CR6_LT_REV*/3, t, zero));

  {
#define N  (sizeof(vc) / sizeof(long))

    union {
      vc v;
      /* Statically assert that N is 2 or 4.  */
      unsigned long l[(N == 2 || N == 4) ? N : -1];
    } u;
    unsigned long l, i = 0;

    u.v = t;

    /* Find the first word of T that is non-zero.  */
    switch (N)
      {
      case 4:
	l = u.l[i++];
	if (l != 0)
	  break;
	s += sizeof(unsigned long);
	l = u.l[i++];
	if (l != 0)
	  break;
	s += sizeof(unsigned long);
	/* FALLTHROUGH */
      case 2:
	l = u.l[i++];
	if (l != 0)
	  break;
	s += sizeof(unsigned long);
	l = u.l[i];
      }

    /* L now contains 0xff in bytes for which we matched one of the
       relevant characters.  We can find the byte index by finding
       its bit index and dividing by 8.  */
    l = __builtin_clzl(l) >> 3;
    return s + l;

#undef N
  }
}

#elif defined (__ARM_NEON) && defined (__ARM_64BIT_STATE)
#include "arm_neon.h"

/* This doesn't have to be the exact page size, but no system may use
   a size smaller than this.  ARMv8 requires a minimum page size of
   4k.  The impact of being conservative here is a small number of
   cases will take the slightly slower entry path into the main
   loop.  */

#define AARCH64_MIN_PAGE_SIZE 4096

static const uchar *
search_line_fast (const uchar *s, const uchar *end ATTRIBUTE_UNUSED)
{
  const uint8x16_t repl_nl = vdupq_n_u8 ('\n');
  const uint8x16_t repl_cr = vdupq_n_u8 ('\r');
  const uint8x16_t repl_bs = vdupq_n_u8 ('\\');
  const uint8x16_t repl_qm = vdupq_n_u8 ('?');
  const uint8x16_t xmask = (uint8x16_t) vdupq_n_u64 (0x8040201008040201ULL);

#ifdef __ARM_BIG_ENDIAN
  const int16x8_t shift = {8, 8, 8, 8, 0, 0, 0, 0};
#else
  const int16x8_t shift = {0, 0, 0, 0, 8, 8, 8, 8};
#endif

  unsigned int found;
  const uint8_t *p;
  uint8x16_t data;
  uint8x16_t t;
  uint16x8_t m;
  uint8x16_t u, v, w;

  /* Align the source pointer.  */
  p = (const uint8_t *)((uintptr_t)s & -16);

  /* Assuming random string start positions, with a 4k page size we'll take
     the slow path about 0.37% of the time.  */
  if (__builtin_expect ((AARCH64_MIN_PAGE_SIZE
			 - (((uintptr_t) s) & (AARCH64_MIN_PAGE_SIZE - 1)))
			< 16, 0))
    {
      /* Slow path: the string starts near a possible page boundary.  */
      uint32_t misalign, mask;

      misalign = (uintptr_t)s & 15;
      mask = (-1u << misalign) & 0xffff;
      data = vld1q_u8 (p);
      t = vceqq_u8 (data, repl_nl);
      u = vceqq_u8 (data, repl_cr);
      v = vorrq_u8 (t, vceqq_u8 (data, repl_bs));
      w = vorrq_u8 (u, vceqq_u8 (data, repl_qm));
      t = vorrq_u8 (v, w);
      t = vandq_u8 (t, xmask);
      m = vpaddlq_u8 (t);
      m = vshlq_u16 (m, shift);
      found = vaddvq_u16 (m);
      found &= mask;
      if (found)
	return (const uchar*)p + __builtin_ctz (found);
    }
  else
    {
      data = vld1q_u8 ((const uint8_t *) s);
      t = vceqq_u8 (data, repl_nl);
      u = vceqq_u8 (data, repl_cr);
      v = vorrq_u8 (t, vceqq_u8 (data, repl_bs));
      w = vorrq_u8 (u, vceqq_u8 (data, repl_qm));
      t = vorrq_u8 (v, w);
      if (__builtin_expect (vpaddd_u64 ((uint64x2_t)t) != 0, 0))
	goto done;
    }

  do
    {
      p += 16;
      data = vld1q_u8 (p);
      t = vceqq_u8 (data, repl_nl);
      u = vceqq_u8 (data, repl_cr);
      v = vorrq_u8 (t, vceqq_u8 (data, repl_bs));
      w = vorrq_u8 (u, vceqq_u8 (data, repl_qm));
      t = vorrq_u8 (v, w);
    } while (!vpaddd_u64 ((uint64x2_t)t));

done:
  /* Now that we've found the terminating substring, work out precisely where
     we need to stop.  */
  t = vandq_u8 (t, xmask);
  m = vpaddlq_u8 (t);
  m = vshlq_u16 (m, shift);
  found = vaddvq_u16 (m);
  return (((((uintptr_t) p) < (uintptr_t) s) ? s : (const uchar *)p)
	  + __builtin_ctz (found));
}

#elif defined (__ARM_NEON)
#include "arm_neon.h"

static const uchar *
search_line_fast (const uchar *s, const uchar *end ATTRIBUTE_UNUSED)
{
  const uint8x16_t repl_nl = vdupq_n_u8 ('\n');
  const uint8x16_t repl_cr = vdupq_n_u8 ('\r');
  const uint8x16_t repl_bs = vdupq_n_u8 ('\\');
  const uint8x16_t repl_qm = vdupq_n_u8 ('?');
  const uint8x16_t xmask = (uint8x16_t) vdupq_n_u64 (0x8040201008040201ULL);

  unsigned int misalign, found, mask;
  const uint8_t *p;
  uint8x16_t data;

  /* Align the source pointer.  */
  misalign = (uintptr_t)s & 15;
  p = (const uint8_t *)((uintptr_t)s & -16);
  data = vld1q_u8 (p);

  /* Create a mask for the bytes that are valid within the first
     16-byte block.  The Idea here is that the AND with the mask
     within the loop is "free", since we need some AND or TEST
     insn in order to set the flags for the branch anyway.  */
  mask = (-1u << misalign) & 0xffff;

  /* Main loop, processing 16 bytes at a time.  */
  goto start;

  do
    {
      uint8x8_t l;
      uint16x4_t m;
      uint32x2_t n;
      uint8x16_t t, u, v, w;

      p += 16;
      data = vld1q_u8 (p);
      mask = 0xffff;

    start:
      t = vceqq_u8 (data, repl_nl);
      u = vceqq_u8 (data, repl_cr);
      v = vorrq_u8 (t, vceqq_u8 (data, repl_bs));
      w = vorrq_u8 (u, vceqq_u8 (data, repl_qm));
      t = vandq_u8 (vorrq_u8 (v, w), xmask);
      l = vpadd_u8 (vget_low_u8 (t), vget_high_u8 (t));
      m = vpaddl_u8 (l);
      n = vpaddl_u16 (m);
      
      found = vget_lane_u32 ((uint32x2_t) vorr_u64 ((uint64x1_t) n, 
	      vshr_n_u64 ((uint64x1_t) n, 24)), 0);
      found &= mask;
    }
  while (!found);

  /* FOUND contains 1 in bits for which we matched a relevant
     character.  Conversion to the byte index is trivial.  */
  found = __builtin_ctz (found);
  return (const uchar *)p + found;
}

#else

/* We only have one accelerated alternative.  Use a direct call so that
   we encourage inlining.  */

#define search_line_fast  search_line_acc_char

#endif

/* Initialize the lexer if needed.  */

void
_cpp_init_lexer (void)
{
#ifdef HAVE_init_vectorized_lexer
  init_vectorized_lexer ();
#endif
}

/* Returns with a logical line that contains no escaped newlines or
   trigraphs.  This is a time-critical inner loop.  */
void
_cpp_clean_line (cpp_reader *pfile)
{
  cpp_buffer *buffer;
  const uchar *s;
  uchar c, *d, *p;

  buffer = pfile->buffer;
  buffer->cur_note = buffer->notes_used = 0;
  buffer->cur = buffer->line_base = buffer->next_line;
  buffer->need_line = false;
  s = buffer->next_line;

  if (!buffer->from_stage3)
    {
      const uchar *pbackslash = NULL;

      /* Fast path.  This is the common case of an un-escaped line with
	 no trigraphs.  The primary win here is by not writing any
	 data back to memory until we have to.  */
      while (1)
	{
	  /* Perform an optimized search for \n, \r, \\, ?.  */
	  s = search_line_fast (s, buffer->rlimit);

	  c = *s;
	  if (c == '\\')
	    {
	      /* Record the location of the backslash and continue.  */
	      pbackslash = s++;
	    }
	  else if (__builtin_expect (c == '?', 0))
	    {
	      if (__builtin_expect (s[1] == '?', false)
		   && _cpp_trigraph_map[s[2]])
		{
		  /* Have a trigraph.  We may or may not have to convert
		     it.  Add a line note regardless, for -Wtrigraphs.  */
		  add_line_note (buffer, s, s[2]);
		  if (CPP_OPTION (pfile, trigraphs))
		    {
		      /* We do, and that means we have to switch to the
		         slow path.  */
		      d = (uchar *) s;
		      *d = _cpp_trigraph_map[s[2]];
		      s += 2;
		      goto slow_path;
		    }
		}
	      /* Not a trigraph.  Continue on fast-path.  */
	      s++;
	    }
	  else
	    break;
	}

      /* This must be \r or \n.  We're either done, or we'll be forced
	 to write back to the buffer and continue on the slow path.  */
      d = (uchar *) s;

      if (__builtin_expect (s == buffer->rlimit, false))
	goto done;

      /* DOS line ending? */
      if (__builtin_expect (c == '\r', false) && s[1] == '\n')
	{
	  s++;
	  if (s == buffer->rlimit)
	    goto done;
	}

      if (__builtin_expect (pbackslash == NULL, true))
	goto done;

      /* Check for escaped newline.  */
      p = d;
      while (is_nvspace (p[-1]))
	p--;
      if (p - 1 != pbackslash)
	goto done;

      /* Have an escaped newline; process it and proceed to
	 the slow path.  */
      add_line_note (buffer, p - 1, p != d ? ' ' : '\\');
      d = p - 2;
      buffer->next_line = p - 1;

    slow_path:
      while (1)
	{
	  c = *++s;
	  *++d = c;

	  if (c == '\n' || c == '\r')
	    {
	      /* Handle DOS line endings.  */
	      if (c == '\r' && s != buffer->rlimit && s[1] == '\n')
		s++;
	      if (s == buffer->rlimit)
		break;

	      /* Escaped?  */
	      p = d;
	      while (p != buffer->next_line && is_nvspace (p[-1]))
		p--;
	      if (p == buffer->next_line || p[-1] != '\\')
		break;

	      add_line_note (buffer, p - 1, p != d ? ' ': '\\');
	      d = p - 2;
	      buffer->next_line = p - 1;
	    }
	  else if (c == '?' && s[1] == '?' && _cpp_trigraph_map[s[2]])
	    {
	      /* Add a note regardless, for the benefit of -Wtrigraphs.  */
	      add_line_note (buffer, d, s[2]);
	      if (CPP_OPTION (pfile, trigraphs))
		{
		  *d = _cpp_trigraph_map[s[2]];
		  s += 2;
		}
	    }
	}
    }
  else
    {
      while (*s != '\n' && *s != '\r')
	s++;
      d = (uchar *) s;

      /* Handle DOS line endings.  */
      if (*s == '\r' && s + 1 != buffer->rlimit && s[1] == '\n')
	s++;
    }

 done:
  *d = '\n';
  /* A sentinel note that should never be processed.  */
  add_line_note (buffer, d + 1, '\n');
  buffer->next_line = s + 1;
}

template <bool lexing_raw_string>
static bool get_fresh_line_impl (cpp_reader *pfile);

/* Return true if the trigraph indicated by NOTE should be warned
   about in a comment.  */
static bool
warn_in_comment (cpp_reader *pfile, _cpp_line_note *note)
{
  const uchar *p;

  /* Within comments we don't warn about trigraphs, unless the
     trigraph forms an escaped newline, as that may change
     behavior.  */
  if (note->type != '/')
    return false;

  /* If -trigraphs, then this was an escaped newline iff the next note
     is coincident.  */
  if (CPP_OPTION (pfile, trigraphs))
    return note[1].pos == note->pos;

  /* Otherwise, see if this forms an escaped newline.  */
  p = note->pos + 3;
  while (is_nvspace (*p))
    p++;

  /* There might have been escaped newlines between the trigraph and the
     newline we found.  Hence the position test.  */
  return (*p == '\n' && p < note[1].pos);
}

/* Process the notes created by add_line_note as far as the current
   location.  */
void
_cpp_process_line_notes (cpp_reader *pfile, int in_comment)
{
  cpp_buffer *buffer = pfile->buffer;

  for (;;)
    {
      _cpp_line_note *note = &buffer->notes[buffer->cur_note];
      unsigned int col;

      if (note->pos > buffer->cur)
	break;

      buffer->cur_note++;
      col = CPP_BUF_COLUMN (buffer, note->pos + 1);

      if (note->type == '\\' || note->type == ' ')
	{
	  if (note->type == ' ' && !in_comment)
	    cpp_error_with_line (pfile, CPP_DL_WARNING, pfile->line_table->highest_line, col,
				 "backslash and newline separated by space");

	  if (buffer->next_line > buffer->rlimit)
	    {
	      cpp_error_with_line (pfile, CPP_DL_PEDWARN, pfile->line_table->highest_line, col,
				   "backslash-newline at end of file");
	      /* Prevent "no newline at end of file" warning.  */
	      buffer->next_line = buffer->rlimit;
	    }

	  buffer->line_base = note->pos;
	  CPP_INCREMENT_LINE (pfile, 0);
	}
      else if (_cpp_trigraph_map[note->type])
	{
	  if (CPP_OPTION (pfile, warn_trigraphs)
	      && (!in_comment || warn_in_comment (pfile, note)))
	    {
	      if (CPP_OPTION (pfile, trigraphs))
		cpp_warning_with_line (pfile, CPP_W_TRIGRAPHS,
                                       pfile->line_table->highest_line, col,
				       "trigraph ??%c converted to %c",
				       note->type,
				       (int) _cpp_trigraph_map[note->type]);
	      else
		{
		  cpp_warning_with_line 
		    (pfile, CPP_W_TRIGRAPHS,
                     pfile->line_table->highest_line, col,
		     "trigraph ??%c ignored, use -trigraphs to enable",
		     note->type);
		}
	    }
	}
      else if (note->type == 0)
	/* Already processed in lex_raw_string.  */;
      else
	abort ();
    }
}

namespace bidi {
  enum class kind {
    NONE, LRE, RLE, LRO, RLO, LRI, RLI, FSI, PDF, PDI, LTR, RTL
  };

  /* All the UTF-8 encodings of bidi characters start with E2.  */
  constexpr uchar utf8_start = 0xe2;

  struct context
  {
    context () {}
    context (location_t loc, kind k, bool pdf, bool ucn)
    : m_loc (loc), m_kind (k), m_pdf (pdf), m_ucn (ucn)
    {
    }

    kind get_pop_kind () const
    {
      return m_pdf ? kind::PDF : kind::PDI;
    }
    bool ucn_p () const
    {
      return m_ucn;
    }

    location_t m_loc;
    kind m_kind;
    unsigned m_pdf : 1;
    unsigned m_ucn : 1;
  };

  /* A vector holding currently open bidi contexts.  We use a char for
     each context, its LSB is 1 if it represents a PDF context, 0 if it
     represents a PDI context.  The next bit is 1 if this context was open
     by a bidi character written as a UCN, and 0 when it was UTF-8.  */
  semi_embedded_vec <context, 16> vec;

  /* Close the whole comment/identifier/string literal/character constant
     context.  */
  void on_close ()
  {
    vec.truncate (0);
  }

  /* Pop the last element in the vector.  */
  void pop ()
  {
    unsigned int len = vec.count ();
    gcc_checking_assert (len > 0);
    vec.truncate (len - 1);
  }

  /* Return the pop kind of the context of the Ith element.  */
  kind pop_kind_at (unsigned int i)
  {
    return vec[i].get_pop_kind ();
  }

  /* Return the pop kind of the context that is currently opened.  */
  kind current_ctx ()
  {
    unsigned int len = vec.count ();
    if (len == 0)
      return kind::NONE;
    return vec[len - 1].get_pop_kind ();
  }

  /* Return true if the current context comes from a UCN origin, that is,
     the bidi char which started this bidi context was written as a UCN.  */
  bool current_ctx_ucn_p ()
  {
    unsigned int len = vec.count ();
    gcc_checking_assert (len > 0);
    return vec[len - 1].m_ucn;
  }

  location_t current_ctx_loc ()
  {
    unsigned int len = vec.count ();
    gcc_checking_assert (len > 0);
    return vec[len - 1].m_loc;
  }

  /* We've read a bidi char, update the current vector as necessary.
     LOC is only valid when K is not kind::NONE.  */
  void on_char (kind k, bool ucn_p, location_t loc)
  {
    switch (k)
      {
      case kind::LRE:
      case kind::RLE:
      case kind::LRO:
      case kind::RLO:
	vec.push (context (loc, k, true, ucn_p));
	break;
      case kind::LRI:
      case kind::RLI:
      case kind::FSI:
	vec.push (context (loc, k, false, ucn_p));
	break;
      /* PDF terminates the scope of the last LRE, RLE, LRO, or RLO
	 whose scope has not yet been terminated.  */
      case kind::PDF:
	if (current_ctx () == kind::PDF)
	  pop ();
	break;
      /* PDI terminates the scope of the last LRI, RLI, or FSI whose
	 scope has not yet been terminated, as well as the scopes of
	 any subsequent LREs, RLEs, LROs, or RLOs whose scopes have not
	 yet been terminated.  */
      case kind::PDI:
	for (int i = vec.count () - 1; i >= 0; --i)
	  if (pop_kind_at (i) == kind::PDI)
	    {
	      vec.truncate (i);
	      break;
	    }
	break;
      case kind::LTR:
      case kind::RTL:
	/* These aren't popped by a PDF/PDI.  */
	break;
      ATTR_LIKELY case kind::NONE:
	break;
      default:
	abort ();
      }
  }

  /* Return a descriptive string for K.  */
  const char *to_str (kind k)
  {
    switch (k)
      {
      case kind::LRE:
	return "U+202A (LEFT-TO-RIGHT EMBEDDING)";
      case kind::RLE:
	return "U+202B (RIGHT-TO-LEFT EMBEDDING)";
      case kind::LRO:
	return "U+202D (LEFT-TO-RIGHT OVERRIDE)";
      case kind::RLO:
	return "U+202E (RIGHT-TO-LEFT OVERRIDE)";
      case kind::LRI:
	return "U+2066 (LEFT-TO-RIGHT ISOLATE)";
      case kind::RLI:
	return "U+2067 (RIGHT-TO-LEFT ISOLATE)";
      case kind::FSI:
	return "U+2068 (FIRST STRONG ISOLATE)";
      case kind::PDF:
	return "U+202C (POP DIRECTIONAL FORMATTING)";
      case kind::PDI:
	return "U+2069 (POP DIRECTIONAL ISOLATE)";
      case kind::LTR:
	return "U+200E (LEFT-TO-RIGHT MARK)";
      case kind::RTL:
	return "U+200F (RIGHT-TO-LEFT MARK)";
      default:
	abort ();
      }
  }
}

/* Get location_t for the range of bytes [START, START + NUM_BYTES)
   within the current line in FILE, with the caret at START.  */

static location_t
get_location_for_byte_range_in_cur_line (cpp_reader *pfile,
					 const unsigned char *const start,
					 size_t num_bytes)
{
  gcc_checking_assert (num_bytes > 0);

  /* CPP_BUF_COLUMN and linemap_position_for_column both refer
     to offsets in bytes, but CPP_BUF_COLUMN is 0-based,
     whereas linemap_position_for_column is 1-based.  */

  /* Get 0-based offsets within the line.  */
  size_t start_offset = CPP_BUF_COLUMN (pfile->buffer, start);
  size_t end_offset = start_offset + num_bytes - 1;

  /* Now convert to location_t, where "columns" are 1-based byte offsets.  */
  location_t start_loc = linemap_position_for_column (pfile->line_table,
						      start_offset + 1);
  location_t end_loc = linemap_position_for_column (pfile->line_table,
						     end_offset + 1);

  if (start_loc == end_loc)
    return start_loc;

  source_range src_range;
  src_range.m_start = start_loc;
  src_range.m_finish = end_loc;
  location_t combined_loc = COMBINE_LOCATION_DATA (pfile->line_table,
						   start_loc,
						   src_range,
						   NULL,
						   0);
  return combined_loc;
}

/* Parse a sequence of 3 bytes starting with P and return its bidi code.  */

static bidi::kind
get_bidi_utf8_1 (const unsigned char *const p)
{
  gcc_checking_assert (p[0] == bidi::utf8_start);

  if (p[1] == 0x80)
    switch (p[2])
      {
      case 0xaa:
	return bidi::kind::LRE;
      case 0xab:
	return bidi::kind::RLE;
      case 0xac:
	return bidi::kind::PDF;
      case 0xad:
	return bidi::kind::LRO;
      case 0xae:
	return bidi::kind::RLO;
      case 0x8e:
	return bidi::kind::LTR;
      case 0x8f:
	return bidi::kind::RTL;
      default:
	break;
      }
  else if (p[1] == 0x81)
    switch (p[2])
      {
      case 0xa6:
	return bidi::kind::LRI;
      case 0xa7:
	return bidi::kind::RLI;
      case 0xa8:
	return bidi::kind::FSI;
      case 0xa9:
	return bidi::kind::PDI;
      default:
	break;
      }

  return bidi::kind::NONE;
}

/* Parse a sequence of 3 bytes starting with P and return its bidi code.
   If the kind is not NONE, write the location to *OUT.*/

static bidi::kind
get_bidi_utf8 (cpp_reader *pfile, const unsigned char *const p, location_t *out)
{
  bidi::kind result = get_bidi_utf8_1 (p);
  if (result != bidi::kind::NONE)
    {
      /* We have a sequence of 3 bytes starting at P.  */
      *out = get_location_for_byte_range_in_cur_line (pfile, p, 3);
    }
  return result;
}

/* Parse a UCN where P points just past \u or \U and return its bidi code.  */

static bidi::kind
get_bidi_ucn_1 (const unsigned char *p, bool is_U, const unsigned char **end)
{
  /* 6.4.3 Universal Character Names
      \u hex-quad
      \U hex-quad hex-quad
      \u { simple-hexadecimal-digit-sequence }
     where \unnnn means \U0000nnnn.  */

  *end = p + 4;
  if (is_U)
    {
      if (p[0] != '0' || p[1] != '0' || p[2] != '0' || p[3] != '0')
	return bidi::kind::NONE;
      /* Skip 4B so we can treat \u and \U the same below.  */
      p += 4;
      *end += 4;
    }
  else if (p[0] == '{')
    {
      p++;
      while (*p == '0')
	p++;
      if (p[0] != '2'
	  || p[1] != '0'
	  || !ISXDIGIT (p[2])
	  || !ISXDIGIT (p[3])
	  || p[4] != '}')
	return bidi::kind::NONE;
      *end = p + 5;
    }

  /* All code points we are looking for start with 20xx.  */
  if (p[0] != '2' || p[1] != '0')
    return bidi::kind::NONE;
  else if (p[2] == '2')
    switch (p[3])
      {
      case 'a':
      case 'A':
	return bidi::kind::LRE;
      case 'b':
      case 'B':
	return bidi::kind::RLE;
      case 'c':
      case 'C':
	return bidi::kind::PDF;
      case 'd':
      case 'D':
	return bidi::kind::LRO;
      case 'e':
      case 'E':
	return bidi::kind::RLO;
      default:
	break;
      }
  else if (p[2] == '6')
    switch (p[3])
      {
      case '6':
	return bidi::kind::LRI;
      case '7':
	return bidi::kind::RLI;
      case '8':
	return bidi::kind::FSI;
      case '9':
	return bidi::kind::PDI;
      default:
	break;
      }
  else if (p[2] == '0')
    switch (p[3])
      {
      case 'e':
      case 'E':
	return bidi::kind::LTR;
      case 'f':
      case 'F':
	return bidi::kind::RTL;
      default:
	break;
      }

  return bidi::kind::NONE;
}

/* Parse a UCN where P points just past \u or \U and return its bidi code.
   If the kind is not NONE, write the location to *OUT.  */

static bidi::kind
get_bidi_ucn (cpp_reader *pfile, const unsigned char *p, bool is_U,
	      location_t *out)
{
  const unsigned char *end;
  bidi::kind result = get_bidi_ucn_1 (p, is_U, &end);
  if (result != bidi::kind::NONE)
    {
      const unsigned char *start = p - 2;
      size_t num_bytes = end - start;
      *out = get_location_for_byte_range_in_cur_line (pfile, start, num_bytes);
    }
  return result;
}

/* Parse a named universal character escape where P points just past \N and
   return its bidi code.  If the kind is not NONE, write the location to
   *OUT.  */

static bidi::kind
get_bidi_named (cpp_reader *pfile, const unsigned char *p, location_t *out)
{
  bidi::kind result = bidi::kind::NONE;
  if (*p != '{')
    return bidi::kind::NONE;
  if (strncmp ((const char *) (p + 1), "LEFT-TO-RIGHT ", 14) == 0)
    {
      if (strncmp ((const char *) (p + 15), "MARK}", 5) == 0)
	result = bidi::kind::LTR;
      else if (strncmp ((const char *) (p + 15), "EMBEDDING}", 10) == 0)
	result = bidi::kind::LRE;
      else if (strncmp ((const char *) (p + 15), "OVERRIDE}", 9) == 0)
	result = bidi::kind::LRO;
      else if (strncmp ((const char *) (p + 15), "ISOLATE}", 8) == 0)
	result = bidi::kind::LRI;
    }
  else if (strncmp ((const char *) (p + 1), "RIGHT-TO-LEFT ", 14) == 0)
    {
      if (strncmp ((const char *) (p + 15), "MARK}", 5) == 0)
	result = bidi::kind::RTL;
      else if (strncmp ((const char *) (p + 15), "EMBEDDING}", 10) == 0)
	result = bidi::kind::RLE;
      else if (strncmp ((const char *) (p + 15), "OVERRIDE}", 9) == 0)
	result = bidi::kind::RLO;
      else if (strncmp ((const char *) (p + 15), "ISOLATE}", 8) == 0)
	result = bidi::kind::RLI;
    }
  else if (strncmp ((const char *) (p + 1), "POP DIRECTIONAL ", 16) == 0)
    {
      if (strncmp ((const char *) (p + 16), "FORMATTING}", 11) == 0)
	result = bidi::kind::PDF;
      else if (strncmp ((const char *) (p + 16), "ISOLATE}", 8) == 0)
	result = bidi::kind::PDI;
    }
  else if (strncmp ((const char *) (p + 1), "FIRST STRONG ISOLATE}", 21) == 0)
    result = bidi::kind::FSI;
  if (result != bidi::kind::NONE)
    *out = get_location_for_byte_range_in_cur_line (pfile, p - 2,
						    (strchr ((const char *)
							     (p + 1), '}')
						     - (const char *) p)
						    + 3);
  return result;
}

/* Subclass of rich_location for reporting on unpaired UTF-8
   bidirectional control character(s).
   Escape the source lines on output, and show all unclosed
   bidi context, labelling everything.  */

class unpaired_bidi_rich_location : public rich_location
{
 public:
  class custom_range_label : public range_label
  {
   public:
     label_text get_text (unsigned range_idx) const final override
     {
       /* range 0 is the primary location; each subsequent range i + 1
	  is for bidi::vec[i].  */
       if (range_idx > 0)
	 {
	   const bidi::context &ctxt (bidi::vec[range_idx - 1]);
	   return label_text::borrow (bidi::to_str (ctxt.m_kind));
	 }
       else
	 return label_text::borrow (_("end of bidirectional context"));
     }
  };

  unpaired_bidi_rich_location (cpp_reader *pfile, location_t loc)
  : rich_location (pfile->line_table, loc, &m_custom_label)
  {
    set_escape_on_output (true);
    for (unsigned i = 0; i < bidi::vec.count (); i++)
      add_range (bidi::vec[i].m_loc,
		 SHOW_RANGE_WITHOUT_CARET,
		 &m_custom_label);
  }

 private:
   custom_range_label m_custom_label;
};

/* We're closing a bidi context, that is, we've encountered a newline,
   are closing a C-style comment, or are at the end of a string literal,
   character constant, or identifier.  Warn if this context was not
   properly terminated by a PDI or PDF.  P points to the last character
   in this context.  */

static void
maybe_warn_bidi_on_close (cpp_reader *pfile, const uchar *p)
{
  const auto warn_bidi = CPP_OPTION (pfile, cpp_warn_bidirectional);
  if (bidi::vec.count () > 0
      && (warn_bidi & bidirectional_unpaired
	  && (!bidi::current_ctx_ucn_p ()
	      || (warn_bidi & bidirectional_ucn))))
    {
      const location_t loc
	= linemap_position_for_column (pfile->line_table,
				       CPP_BUF_COLUMN (pfile->buffer, p));
      unpaired_bidi_rich_location rich_loc (pfile, loc);
      /* cpp_callbacks doesn't yet have a way to handle singular vs plural
	 forms of a diagnostic, so fake it for now.  */
      if (bidi::vec.count () > 1)
	cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
			"unpaired UTF-8 bidirectional control characters "
			"detected");
      else
	cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
			"unpaired UTF-8 bidirectional control character "
			"detected");
    }
  /* We're done with this context.  */
  bidi::on_close ();
}

/* We're at the beginning or in the middle of an identifier/comment/string
   literal/character constant.  Warn if we've encountered a bidi character.
   KIND says which bidi control character it was; UCN_P is true iff this bidi
   control character was written as a UCN.  LOC is the location of the
   character, but is only valid if KIND != bidi::kind::NONE.  */

static void
maybe_warn_bidi_on_char (cpp_reader *pfile, bidi::kind kind,
			 bool ucn_p, location_t loc)
{
  if (__builtin_expect (kind == bidi::kind::NONE, 1))
    return;

  const auto warn_bidi = CPP_OPTION (pfile, cpp_warn_bidirectional);

  if (warn_bidi & (bidirectional_unpaired|bidirectional_any))
    {
      rich_location rich_loc (pfile->line_table, loc);
      rich_loc.set_escape_on_output (true);

      /* It seems excessive to warn about a PDI/PDF that is closing
	 an opened context because we've already warned about the
	 opening character.  Except warn when we have a UCN x UTF-8
	 mismatch, if UCN checking is enabled.  */
      if (kind == bidi::current_ctx ())
	{
	  if (warn_bidi == (bidirectional_unpaired|bidirectional_ucn)
	      && bidi::current_ctx_ucn_p () != ucn_p)
	    {
	      rich_loc.add_range (bidi::current_ctx_loc ());
	      cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
			      "UTF-8 vs UCN mismatch when closing "
			      "a context by \"%s\"", bidi::to_str (kind));
	    }
	}
      else if (warn_bidi & bidirectional_any
	       && (!ucn_p || (warn_bidi & bidirectional_ucn)))
	{
	  if (kind == bidi::kind::PDF || kind == bidi::kind::PDI)
	    cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
			    "\"%s\" is closing an unopened context",
			    bidi::to_str (kind));
	  else
	    cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
			    "found problematic Unicode character \"%s\"",
			    bidi::to_str (kind));
	}
    }
  /* We're done with this context.  */
  bidi::on_char (kind, ucn_p, loc);
}

static const cppchar_t utf8_continuation = 0x80;
static const cppchar_t utf8_signifier = 0xC0;

/* Emit -Winvalid-utf8 warning on invalid UTF-8 character starting
   at PFILE->buffer->cur.  Return a pointer after the diagnosed
   invalid character.  */

static const uchar *
_cpp_warn_invalid_utf8 (cpp_reader *pfile)
{
  cpp_buffer *buffer = pfile->buffer;
  const uchar *cur = buffer->cur;
  bool pedantic = (CPP_PEDANTIC (pfile)
		   && CPP_OPTION (pfile, cpp_warn_invalid_utf8) == 2);

  if (cur[0] < utf8_signifier
      || cur[1] < utf8_continuation || cur[1] >= utf8_signifier)
    {
      if (pedantic)
	cpp_error_with_line (pfile, CPP_DL_PEDWARN,
			     pfile->line_table->highest_line,
			     CPP_BUF_COL (buffer),
			     "invalid UTF-8 character <%x>",
			     cur[0]);
      else
	cpp_warning_with_line (pfile, CPP_W_INVALID_UTF8,
			       pfile->line_table->highest_line,
			       CPP_BUF_COL (buffer),
			       "invalid UTF-8 character <%x>",
			       cur[0]);
      return cur + 1;
    }
  else if (cur[2] < utf8_continuation || cur[2] >= utf8_signifier)
    {
      if (pedantic)
	cpp_error_with_line (pfile, CPP_DL_PEDWARN,
			     pfile->line_table->highest_line,
			     CPP_BUF_COL (buffer),
			     "invalid UTF-8 character <%x><%x>",
			     cur[0], cur[1]);
      else
	cpp_warning_with_line (pfile, CPP_W_INVALID_UTF8,
			       pfile->line_table->highest_line,
			       CPP_BUF_COL (buffer),
			       "invalid UTF-8 character <%x><%x>",
			       cur[0], cur[1]);
      return cur + 2;
    }
  else if (cur[3] < utf8_continuation || cur[3] >= utf8_signifier)
    {
      if (pedantic)
	cpp_error_with_line (pfile, CPP_DL_PEDWARN,
			     pfile->line_table->highest_line,
			     CPP_BUF_COL (buffer),
			     "invalid UTF-8 character <%x><%x><%x>",
			     cur[0], cur[1], cur[2]);
      else
	cpp_warning_with_line (pfile, CPP_W_INVALID_UTF8,
			       pfile->line_table->highest_line,
			       CPP_BUF_COL (buffer),
			       "invalid UTF-8 character <%x><%x><%x>",
			       cur[0], cur[1], cur[2]);
      return cur + 3;
    }
  else
    {
      if (pedantic)
	cpp_error_with_line (pfile, CPP_DL_PEDWARN,
			     pfile->line_table->highest_line,
			     CPP_BUF_COL (buffer),
			     "invalid UTF-8 character <%x><%x><%x><%x>",
			     cur[0], cur[1], cur[2], cur[3]);
      else
	cpp_warning_with_line (pfile, CPP_W_INVALID_UTF8,
			       pfile->line_table->highest_line,
			       CPP_BUF_COL (buffer),
			       "invalid UTF-8 character <%x><%x><%x><%x>",
			       cur[0], cur[1], cur[2], cur[3]);
      return cur + 4;
    }
}

/* Helper function of *skip_*_comment and lex*_string.  For C,
   character at CUR[-1] with MSB set handle -Wbidi-chars* and
   -Winvalid-utf8 diagnostics and return pointer to first character
   that should be processed next.  */

static inline const uchar *
_cpp_handle_multibyte_utf8 (cpp_reader *pfile, uchar c,
			    const uchar *cur, bool warn_bidi_p,
			    bool warn_invalid_utf8_p)
{
  /* If this is a beginning of a UTF-8 encoding, it might be
     a bidirectional control character.  */
  if (c == bidi::utf8_start && warn_bidi_p)
    {
      location_t loc;
      bidi::kind kind = get_bidi_utf8 (pfile, cur - 1, &loc);
      maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
    }
  if (!warn_invalid_utf8_p)
    return cur;
  if (c >= utf8_signifier)
    {
      cppchar_t s;
      const uchar *pstr = cur - 1;
      if (_cpp_valid_utf8 (pfile, &pstr, pfile->buffer->rlimit, 0, NULL, &s)
	  && s <= UCS_LIMIT)
	return pstr;
    }
  pfile->buffer->cur = cur - 1;
  return _cpp_warn_invalid_utf8 (pfile);
}

/* Skip a C-style block comment.  We find the end of the comment by
   seeing if an asterisk is before every '/' we encounter.  Returns
   nonzero if comment terminated by EOF, zero otherwise.

   Buffer->cur points to the initial asterisk of the comment.  */
bool
_cpp_skip_block_comment (cpp_reader *pfile)
{
  cpp_buffer *buffer = pfile->buffer;
  const uchar *cur = buffer->cur;
  uchar c;
  const bool warn_bidi_p = pfile->warn_bidi_p ();
  const bool warn_invalid_utf8_p = CPP_OPTION (pfile, cpp_warn_invalid_utf8);
  const bool warn_bidi_or_invalid_utf8_p = warn_bidi_p | warn_invalid_utf8_p;

  cur++;
  if (*cur == '/')
    cur++;

  for (;;)
    {
      /* People like decorating comments with '*', so check for '/'
	 instead for efficiency.  */
      c = *cur++;

      if (c == '/')
	{
	  if (cur[-2] == '*')
	    {
	      if (warn_bidi_p)
		maybe_warn_bidi_on_close (pfile, cur);
	      break;
	    }

	  /* Warn about potential nested comments, but not if the '/'
	     comes immediately before the true comment delimiter.
	     Don't bother to get it right across escaped newlines.  */
	  if (CPP_OPTION (pfile, warn_comments)
	      && cur[0] == '*' && cur[1] != '/')
	    {
	      buffer->cur = cur;
	      cpp_warning_with_line (pfile, CPP_W_COMMENTS,
				     pfile->line_table->highest_line,
				     CPP_BUF_COL (buffer),
				     "\"/*\" within comment");
	    }
	}
      else if (c == '\n')
	{
	  unsigned int cols;
	  buffer->cur = cur - 1;
	  if (warn_bidi_p)
	    maybe_warn_bidi_on_close (pfile, cur);
	  _cpp_process_line_notes (pfile, true);
	  if (buffer->next_line >= buffer->rlimit)
	    return true;
	  _cpp_clean_line (pfile);

	  cols = buffer->next_line - buffer->line_base;
	  CPP_INCREMENT_LINE (pfile, cols);

	  cur = buffer->cur;
	}
      else if (__builtin_expect (c >= utf8_continuation, 0)
	       && warn_bidi_or_invalid_utf8_p)
	cur = _cpp_handle_multibyte_utf8 (pfile, c, cur, warn_bidi_p,
					  warn_invalid_utf8_p);
    }

  buffer->cur = cur;
  _cpp_process_line_notes (pfile, true);
  return false;
}

/* Skip a C++ line comment, leaving buffer->cur pointing to the
   terminating newline.  Handles escaped newlines.  Returns nonzero
   if a multiline comment.  */
static int
skip_line_comment (cpp_reader *pfile)
{
  cpp_buffer *buffer = pfile->buffer;
  location_t orig_line = pfile->line_table->highest_line;
  const bool warn_bidi_p = pfile->warn_bidi_p ();
  const bool warn_invalid_utf8_p = CPP_OPTION (pfile, cpp_warn_invalid_utf8);
  const bool warn_bidi_or_invalid_utf8_p = warn_bidi_p | warn_invalid_utf8_p;

  if (!warn_bidi_or_invalid_utf8_p)
    while (*buffer->cur != '\n')
      buffer->cur++;
  else if (!warn_invalid_utf8_p)
    {
      while (*buffer->cur != '\n'
	     && *buffer->cur != bidi::utf8_start)
	buffer->cur++;
      if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0))
	{
	  while (*buffer->cur != '\n')
	    {
	      if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0))
		{
		  location_t loc;
		  bidi::kind kind = get_bidi_utf8 (pfile, buffer->cur, &loc);
		  maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
		}
	      buffer->cur++;
	    }
	  maybe_warn_bidi_on_close (pfile, buffer->cur);
	}
    }
  else
    {
      while (*buffer->cur != '\n')
	{
	  if (*buffer->cur < utf8_continuation)
	    {
	      buffer->cur++;
	      continue;
	    }
	  buffer->cur
	    = _cpp_handle_multibyte_utf8 (pfile, *buffer->cur, buffer->cur + 1,
					  warn_bidi_p, warn_invalid_utf8_p);
	}
      if (warn_bidi_p)
	maybe_warn_bidi_on_close (pfile, buffer->cur);
    }

  _cpp_process_line_notes (pfile, true);
  return orig_line != pfile->line_table->highest_line;
}

/* Skips whitespace, saving the next non-whitespace character.  */
static void
skip_whitespace (cpp_reader *pfile, cppchar_t c)
{
  cpp_buffer *buffer = pfile->buffer;
  bool saw_NUL = false;

  do
    {
      /* Horizontal space always OK.  */
      if (c == ' ' || c == '\t')
	;
      /* Just \f \v or \0 left.  */
      else if (c == '\0')
	saw_NUL = true;
      else if (pfile->state.in_directive && CPP_PEDANTIC (pfile))
	cpp_error_with_line (pfile, CPP_DL_PEDWARN, pfile->line_table->highest_line,
			     CPP_BUF_COL (buffer),
			     "%s in preprocessing directive",
			     c == '\f' ? "form feed" : "vertical tab");

      c = *buffer->cur++;
    }
  /* We only want non-vertical space, i.e. ' ' \t \f \v \0.  */
  while (is_nvspace (c));

  if (saw_NUL)
    {
      encoding_rich_location rich_loc (pfile);
      cpp_error_at (pfile, CPP_DL_WARNING, &rich_loc,
		    "null character(s) ignored");
    }

  buffer->cur--;
}

/* See if the characters of a number token are valid in a name (no
   '.', '+' or '-').  */
static int
name_p (cpp_reader *pfile, const cpp_string *string)
{
  unsigned int i;

  for (i = 0; i < string->len; i++)
    if (!is_idchar (string->text[i]))
      return 0;

  return 1;
}

/* After parsing an identifier or other sequence, produce a warning about
   sequences not in NFC/NFKC.  */
static void
warn_about_normalization (cpp_reader *pfile, 
			  const cpp_token *token,
			  const struct normalize_state *s,
			  bool identifier)
{
  if (CPP_OPTION (pfile, warn_normalize) < NORMALIZE_STATE_RESULT (s)
      && !pfile->state.skipping)
    {
      location_t loc = token->src_loc;

      /* If possible, create a location range for the token.  */
      if (loc >= RESERVED_LOCATION_COUNT
	  && token->type != CPP_EOF
	  /* There must be no line notes to process.  */
	  && (!(pfile->buffer->cur
		>= pfile->buffer->notes[pfile->buffer->cur_note].pos
		&& !pfile->overlaid_buffer)))
	{
	  source_range tok_range;
	  tok_range.m_start = loc;
	  tok_range.m_finish
	    = linemap_position_for_column (pfile->line_table,
					   CPP_BUF_COLUMN (pfile->buffer,
							   pfile->buffer->cur));
	  loc = COMBINE_LOCATION_DATA (pfile->line_table,
				       loc, tok_range, NULL, 0);
	}

      encoding_rich_location rich_loc (pfile, loc);

      /* Make sure that the token is printed using UCNs, even
	 if we'd otherwise happily print UTF-8.  */
      unsigned char *buf = XNEWVEC (unsigned char, cpp_token_len (token));
      size_t sz;

      sz = cpp_spell_token (pfile, token, buf, false) - buf;
      if (NORMALIZE_STATE_RESULT (s) == normalized_C)
	cpp_warning_at (pfile, CPP_W_NORMALIZE, &rich_loc,
			"`%.*s' is not in NFKC", (int) sz, buf);
      else if (identifier && CPP_OPTION (pfile, xid_identifiers))
	cpp_pedwarning_at (pfile, CPP_W_NORMALIZE, &rich_loc,
				  "`%.*s' is not in NFC", (int) sz, buf);
      else
	cpp_warning_at (pfile, CPP_W_NORMALIZE, &rich_loc,
			"`%.*s' is not in NFC", (int) sz, buf);
      free (buf);
    }
}

/* Returns TRUE if the sequence starting at buffer->cur is valid in
   an identifier.  FIRST is TRUE if this starts an identifier.  */

static bool
forms_identifier_p (cpp_reader *pfile, int first,
		    struct normalize_state *state)
{
  cpp_buffer *buffer = pfile->buffer;
  const bool warn_bidi_p = pfile->warn_bidi_p ();

  if (*buffer->cur == '$')
    {
      if (!CPP_OPTION (pfile, dollars_in_ident))
	return false;

      buffer->cur++;
      if (CPP_OPTION (pfile, warn_dollars) && !pfile->state.skipping)
	{
	  CPP_OPTION (pfile, warn_dollars) = 0;
	  cpp_error (pfile, CPP_DL_PEDWARN, "'$' in identifier or number");
	}

      return true;
    }

  /* Is this a syntactically valid UCN or a valid UTF-8 char?  */
  if (CPP_OPTION (pfile, extended_identifiers))
    {
      cppchar_t s;
      if (*buffer->cur >= utf8_signifier)
	{
	  if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0)
	      && warn_bidi_p)
	    {
	      location_t loc;
	      bidi::kind kind = get_bidi_utf8 (pfile, buffer->cur, &loc);
	      maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
	    }
	  if (_cpp_valid_utf8 (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
			       state, &s))
	    return true;
	}
      else if (*buffer->cur == '\\'
	       && (buffer->cur[1] == 'u'
		   || buffer->cur[1] == 'U'
		   || buffer->cur[1] == 'N'))
	{
	  buffer->cur += 2;
	  if (warn_bidi_p)
	    {
	      location_t loc;
	      bidi::kind kind;
	      if (buffer->cur[-1] == 'N')
		kind = get_bidi_named (pfile, buffer->cur, &loc);
	      else
		kind = get_bidi_ucn (pfile, buffer->cur,
				     buffer->cur[-1] == 'U', &loc);
	      maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/true, loc);
	    }
	  if (_cpp_valid_ucn (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
			      state, &s, NULL, NULL))
	    return true;
	  buffer->cur -= 2;
	}
    }

  return false;
}

/* Helper function to issue error about improper __VA_OPT__ use.  */
static void
maybe_va_opt_error (cpp_reader *pfile)
{
  if (CPP_PEDANTIC (pfile) && !CPP_OPTION (pfile, va_opt))
    {
      /* __VA_OPT__ should not be accepted at all, but allow it in
	 system headers.  */
      if (!_cpp_in_system_header (pfile))
	cpp_error (pfile, CPP_DL_PEDWARN,
		   "__VA_OPT__ is not available until C++20");
    }
  else if (!pfile->state.va_args_ok)
    {
      /* __VA_OPT__ should only appear in the replacement list of a
	 variadic macro.  */
      cpp_error (pfile, CPP_DL_PEDWARN,
		 "__VA_OPT__ can only appear in the expansion"
		 " of a C++20 variadic macro");
    }
}

/* Helper function to get the cpp_hashnode of the identifier BASE.  */
static cpp_hashnode *
lex_identifier_intern (cpp_reader *pfile, const uchar *base)
{
  cpp_hashnode *result;
  const uchar *cur;
  unsigned int len;
  unsigned int hash = HT_HASHSTEP (0, *base);

  cur = base + 1;
  while (ISIDNUM (*cur))
    {
      hash = HT_HASHSTEP (hash, *cur);
      cur++;
    }
  len = cur - base;
  hash = HT_HASHFINISH (hash, len);
  result = CPP_HASHNODE (ht_lookup_with_hash (pfile->hash_table,
					      base, len, hash, HT_ALLOC));

  /* Rarely, identifiers require diagnostics when lexed.  */
  if (__builtin_expect ((result->flags & NODE_DIAGNOSTIC)
			&& !pfile->state.skipping, 0))
    {
      /* It is allowed to poison the same identifier twice.  */
      if ((result->flags & NODE_POISONED) && !pfile->state.poisoned_ok)
	cpp_error (pfile, CPP_DL_ERROR, "attempt to use poisoned \"%s\"",
		   NODE_NAME (result));

      /* Constraint 6.10.3.5: __VA_ARGS__ should only appear in the
	 replacement list of a variadic macro.  */
      if (result == pfile->spec_nodes.n__VA_ARGS__
	  && !pfile->state.va_args_ok)
	{
	  if (CPP_OPTION (pfile, cplusplus))
	    cpp_error (pfile, CPP_DL_PEDWARN,
		       "__VA_ARGS__ can only appear in the expansion"
		       " of a C++11 variadic macro");
	  else
	    cpp_error (pfile, CPP_DL_PEDWARN,
		       "__VA_ARGS__ can only appear in the expansion"
		       " of a C99 variadic macro");
	}

      if (result == pfile->spec_nodes.n__VA_OPT__)
	maybe_va_opt_error (pfile);

      /* For -Wc++-compat, warn about use of C++ named operators.  */
      if (result->flags & NODE_WARN_OPERATOR)
	cpp_warning (pfile, CPP_W_CXX_OPERATOR_NAMES,
		     "identifier \"%s\" is a special operator name in C++",
		     NODE_NAME (result));
    }

  return result;
}

/* Get the cpp_hashnode of an identifier specified by NAME in
   the current cpp_reader object.  If none is found, NULL is returned.  */
cpp_hashnode *
_cpp_lex_identifier (cpp_reader *pfile, const char *name)
{
  cpp_hashnode *result;
  result = lex_identifier_intern (pfile, (uchar *) name);
  return result;
}

/* Lex an identifier starting at BUFFER->CUR - 1.  */
static cpp_hashnode *
lex_identifier (cpp_reader *pfile, const uchar *base, bool starts_ucn,
		struct normalize_state *nst, cpp_hashnode **spelling)
{
  cpp_hashnode *result;
  const uchar *cur;
  unsigned int len;
  unsigned int hash = HT_HASHSTEP (0, *base);
  const bool warn_bidi_p = pfile->warn_bidi_p ();

  cur = pfile->buffer->cur;
  if (! starts_ucn)
    {
      while (ISIDNUM (*cur))
	{
	  hash = HT_HASHSTEP (hash, *cur);
	  cur++;
	}
      NORMALIZE_STATE_UPDATE_IDNUM (nst, *(cur - 1));
    }
  pfile->buffer->cur = cur;
  if (starts_ucn || forms_identifier_p (pfile, false, nst))
    {
      /* Slower version for identifiers containing UCNs
	 or extended chars (including $).  */
      do {
	while (ISIDNUM (*pfile->buffer->cur))
	  {
	    NORMALIZE_STATE_UPDATE_IDNUM (nst, *pfile->buffer->cur);
	    pfile->buffer->cur++;
	  }
      } while (forms_identifier_p (pfile, false, nst));
      if (warn_bidi_p)
	maybe_warn_bidi_on_close (pfile, pfile->buffer->cur);
      result = _cpp_interpret_identifier (pfile, base,
					  pfile->buffer->cur - base);
      *spelling = cpp_lookup (pfile, base, pfile->buffer->cur - base);
    }
  else
    {
      len = cur - base;
      hash = HT_HASHFINISH (hash, len);

      result = CPP_HASHNODE (ht_lookup_with_hash (pfile->hash_table,
						  base, len, hash, HT_ALLOC));
      *spelling = result;
    }

  /* Rarely, identifiers require diagnostics when lexed.  */
  if (__builtin_expect ((result->flags & NODE_DIAGNOSTIC)
			&& !pfile->state.skipping, 0))
    {
      /* It is allowed to poison the same identifier twice.  */
      if ((result->flags & NODE_POISONED) && !pfile->state.poisoned_ok)
	cpp_error (pfile, CPP_DL_ERROR, "attempt to use poisoned \"%s\"",
		   NODE_NAME (result));

      /* Constraint 6.10.3.5: __VA_ARGS__ should only appear in the
	 replacement list of a variadic macro.  */
      if (result == pfile->spec_nodes.n__VA_ARGS__
	  && !pfile->state.va_args_ok)
	{
	  if (CPP_OPTION (pfile, cplusplus))
	    cpp_error (pfile, CPP_DL_PEDWARN,
		       "__VA_ARGS__ can only appear in the expansion"
		       " of a C++11 variadic macro");
	  else
	    cpp_error (pfile, CPP_DL_PEDWARN,
		       "__VA_ARGS__ can only appear in the expansion"
		       " of a C99 variadic macro");
	}

      /* __VA_OPT__ should only appear in the replacement list of a
	 variadic macro.  */
      if (result == pfile->spec_nodes.n__VA_OPT__)
	maybe_va_opt_error (pfile);

      /* For -Wc++-compat, warn about use of C++ named operators.  */
      if (result->flags & NODE_WARN_OPERATOR)
	cpp_warning (pfile, CPP_W_CXX_OPERATOR_NAMES,
		     "identifier \"%s\" is a special operator name in C++",
		     NODE_NAME (result));
    }

  return result;
}

/* Lex a number to NUMBER starting at BUFFER->CUR - 1.  */
static void
lex_number (cpp_reader *pfile, cpp_string *number,
	    struct normalize_state *nst)
{
  const uchar *cur;
  const uchar *base;
  uchar *dest;

  base = pfile->buffer->cur - 1;
  do
    {
      const uchar *adj_digit_sep = NULL;
      cur = pfile->buffer->cur;

      /* N.B. ISIDNUM does not include $.  */
      while (ISIDNUM (*cur)
	     || (*cur == '.' && !DIGIT_SEP (cur[-1]))
	     || DIGIT_SEP (*cur)
	     || (VALID_SIGN (*cur, cur[-1]) && !DIGIT_SEP (cur[-2])))
	{
	  NORMALIZE_STATE_UPDATE_IDNUM (nst, *cur);
	  /* Adjacent digit separators do not form part of the pp-number syntax.
	     However, they can safely be diagnosed here as an error, since '' is
	     not a valid preprocessing token.  */
	  if (DIGIT_SEP (*cur) && DIGIT_SEP (cur[-1]) && !adj_digit_sep)
	    adj_digit_sep = cur;
	  cur++;
	}
      /* A number can't end with a digit separator.  */
      while (cur > pfile->buffer->cur && DIGIT_SEP (cur[-1]))
	--cur;
      if (adj_digit_sep && adj_digit_sep < cur)
	cpp_error (pfile, CPP_DL_ERROR, "adjacent digit separators");

      pfile->buffer->cur = cur;
    }
  while (forms_identifier_p (pfile, false, nst));

  number->len = cur - base;
  dest = _cpp_unaligned_alloc (pfile, number->len + 1);
  memcpy (dest, base, number->len);
  dest[number->len] = '\0';
  number->text = dest;
}

/* Create a token of type TYPE with a literal spelling.  */
static void
create_literal (cpp_reader *pfile, cpp_token *token, const uchar *base,
		unsigned int len, enum cpp_ttype type)
{
  token->type = type;
  token->val.str.len = len;
  token->val.str.text = cpp_alloc_token_string (pfile, base, len);
}

const uchar *
cpp_alloc_token_string (cpp_reader *pfile,
			const unsigned char *ptr, unsigned len)
{
  uchar *dest = _cpp_unaligned_alloc (pfile, len + 1);

  dest[len] = 0;
  memcpy (dest, ptr, len);
  return dest;
}

/* A pair of raw buffer pointers.  The currently open one is [1], the
   first one is [0].  Used for string literal lexing.  */
struct lit_accum {
  _cpp_buff *first;
  _cpp_buff *last;
  const uchar *rpos;
  size_t accum;

  lit_accum ()
    : first (NULL), last (NULL), rpos (0), accum (0)
  {
  }

  void append (cpp_reader *, const uchar *, size_t);

  void read_begin (cpp_reader *);
  bool reading_p () const
  {
    return rpos != NULL;
  }
  char read_char ()
  {
    char c = *rpos++;
    if (rpos == BUFF_FRONT (last))
      rpos = NULL;
    return c;
  }
};

/* Subroutine of lex_raw_string: Append LEN chars from BASE to the buffer
   sequence from *FIRST_BUFF_P to LAST_BUFF_P.  */

void
lit_accum::append (cpp_reader *pfile, const uchar *base, size_t len)
{
  if (!last)
    /* Starting.  */
    first = last = _cpp_get_buff (pfile, len);
  else if (len > BUFF_ROOM (last))
    {
      /* There is insufficient room in the buffer.  Copy what we can,
	 and then either extend or create a new one.  */
      size_t room = BUFF_ROOM (last);
      memcpy (BUFF_FRONT (last), base, room);
      BUFF_FRONT (last) += room;
      base += room;
      len -= room;
      accum += room;

      gcc_checking_assert (!rpos);

      last = _cpp_append_extend_buff (pfile, last, len);
    }

  memcpy (BUFF_FRONT (last), base, len);
  BUFF_FRONT (last) += len;
  accum += len;
}

void
lit_accum::read_begin (cpp_reader *pfile)
{
  /* We never accumulate more than 4 chars to read.  */
  if (BUFF_ROOM (last) < 4)

    last = _cpp_append_extend_buff (pfile, last, 4);
  rpos = BUFF_FRONT (last);
}

/* Returns true if a macro has been defined.
   This might not work if compile with -save-temps,
   or preprocess separately from compilation.  */

static bool
is_macro(cpp_reader *pfile, const uchar *base)
{
  const uchar *cur = base;
  if (! ISIDST (*cur))
    return false;
  unsigned int hash = HT_HASHSTEP (0, *cur);
  ++cur;
  while (ISIDNUM (*cur))
    {
      hash = HT_HASHSTEP (hash, *cur);
      ++cur;
    }
  hash = HT_HASHFINISH (hash, cur - base);

  cpp_hashnode *result = CPP_HASHNODE (ht_lookup_with_hash (pfile->hash_table,
					base, cur - base, hash, HT_NO_INSERT));

  return result && cpp_macro_p (result);
}

/* Returns true if a literal suffix does not have the expected form
   and is defined as a macro.  */

static bool
is_macro_not_literal_suffix(cpp_reader *pfile, const uchar *base)
{
  /* User-defined literals outside of namespace std must start with a single
     underscore, so assume anything of that form really is a UDL suffix.
     We don't need to worry about UDLs defined inside namespace std because
     their names are reserved, so cannot be used as macro names in valid
     programs.  */
  if (base[0] == '_' && base[1] != '_')
    return false;
  return is_macro (pfile, base);
}

/* Lexes a raw string.  The stored string contains the spelling,
   including double quotes, delimiter string, '(' and ')', any leading
   'L', 'u', 'U' or 'u8' and 'R' modifier.  The created token contains
   the type of the literal, or CPP_OTHER if it was not properly
   terminated.

   BASE is the start of the token.  Updates pfile->buffer->cur to just
   after the lexed string.

   The spelling is NUL-terminated, but it is not guaranteed that this
   is the first NUL since embedded NULs are preserved.  */

static void
lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
{
  const uchar *pos = base;
  const bool warn_bidi_p = pfile->warn_bidi_p ();
  const bool warn_invalid_utf8_p = CPP_OPTION (pfile, cpp_warn_invalid_utf8);
  const bool warn_bidi_or_invalid_utf8_p = warn_bidi_p | warn_invalid_utf8_p;

  /* 'tis a pity this information isn't passed down from the lexer's
     initial categorization of the token.  */
  enum cpp_ttype type = CPP_STRING;

  if (*pos == 'L')
    {
      type = CPP_WSTRING;
      pos++;
    }
  else if (*pos == 'U')
    {
      type = CPP_STRING32;
      pos++;
    }
  else if (*pos == 'u')
    {
      if (pos[1] == '8')
	{
	  type = CPP_UTF8STRING;
	  pos++;
	}
      else
	type = CPP_STRING16;
      pos++;
    }

  gcc_checking_assert (pos[0] == 'R' && pos[1] == '"');
  pos += 2;

  _cpp_line_note *note = &pfile->buffer->notes[pfile->buffer->cur_note];

  /* Skip notes before the ".  */
  while (note->pos < pos)
    ++note;

  lit_accum accum;
  
  uchar prefix[17];
  unsigned prefix_len = 0;
  enum Phase
  {
   PHASE_PREFIX = -2,
   PHASE_NONE = -1,
   PHASE_SUFFIX = 0
  } phase = PHASE_PREFIX;

  for (;;)
    {
      gcc_checking_assert (note->pos >= pos);

      /* Undo any escaped newlines and trigraphs.  */
      if (!accum.reading_p () && note->pos == pos)
	switch (note->type)
	  {
	  case '\\':
	  case ' ':
	    /* Restore backslash followed by newline.  */
	    accum.append (pfile, base, pos - base);
	    base = pos;
	    accum.read_begin (pfile);
	    accum.append (pfile, UC"\\", 1);

	  after_backslash:
	    if (note->type == ' ')
	      /* GNU backslash whitespace newline extension.  FIXME
		 could be any sequence of non-vertical space.  When we
		 can properly restore any such sequence, we should
		 mark this note as handled so _cpp_process_line_notes
		 doesn't warn.  */
	      accum.append (pfile, UC" ", 1);

	    accum.append (pfile, UC"\n", 1);
	    note++;
	    break;

	  case '\n':
	    /* This can happen for ??/<NEWLINE> when trigraphs are not
	       being interpretted.  */
	    gcc_checking_assert (!CPP_OPTION (pfile, trigraphs));
	    note->type = 0;
	    note++;
	    break;

	  default:
	    gcc_checking_assert (_cpp_trigraph_map[note->type]);

	    /* Don't warn about this trigraph in
	       _cpp_process_line_notes, since trigraphs show up as
	       trigraphs in raw strings.  */
	    uchar type = note->type;
	    note->type = 0;

	    if (CPP_OPTION (pfile, trigraphs))
	      {
		accum.append (pfile, base, pos - base);
		base = pos;
		accum.read_begin (pfile);
		accum.append (pfile, UC"??", 2);
		accum.append (pfile, &type, 1);

		/* ??/ followed by newline gets two line notes, one for
		   the trigraph and one for the backslash/newline.  */
		if (type == '/' && note[1].pos == pos)
		  {
		    note++;
		    gcc_assert (note->type == '\\' || note->type == ' ');
		    goto after_backslash;
		  }
		/* Skip the replacement character.  */
		base = ++pos;
	      }

	    note++;
	    break;
	  }

      /* Now get a char to process.  Either from an expanded note, or
	 from the line buffer.  */
      bool read_note = accum.reading_p ();
      char c = read_note ? accum.read_char () : *pos++;

      if (phase == PHASE_PREFIX)
	{
	  if (c == '(')
	    {
	      /* Done.  */
	      phase = PHASE_NONE;
	      prefix[prefix_len++] = '"';
	    }
	  else if (prefix_len < 16
		   /* Prefix chars are any of the basic character set,
		      [lex.charset] except for '
		      ()\\\t\v\f\n'. Optimized for a contiguous
		      alphabet.  */
		   /* Unlike a switch, this collapses down to one or
		      two shift and bitmask operations on an ASCII
		      system, with an outlier or two.   */
		   && (('Z' - 'A' == 25
			? ((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z'))
			: ISIDST (c))
		       || (c >= '0' && c <= '9')
		       || c == '_' || c == '{' || c == '}'
		       || c == '[' || c == ']' || c == '#'
		       || c == '<' || c == '>' || c == '%'
		       || c == ':' || c == ';' || c == '.' || c == '?'
		       || c == '*' || c == '+' || c == '-' || c == '/'
		       || c == '^' || c == '&' || c == '|' || c == '~'
		       || c == '!' || c == '=' || c == ','
		       || c == '"' || c == '\''))
	    prefix[prefix_len++] = c;
	  else
	    {
	      /* Something is wrong.  */
	      int col = CPP_BUF_COLUMN (pfile->buffer, pos) + read_note;
	      if (prefix_len == 16)
		cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc,
				     col, "raw string delimiter longer "
				     "than 16 characters");
	      else if (c == '\n')
		cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc,
				     col, "invalid new-line in raw "
				     "string delimiter");
	      else
		cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc,
				     col, "invalid character '%c' in "
				     "raw string delimiter", c);
	      type = CPP_OTHER;
	      phase = PHASE_NONE;
	      /* Continue until we get a close quote, that's probably
		 the best failure mode.  */
	      prefix_len = 0;
	    }
	  if (c != '\n')
	    continue;
	}

      if (phase != PHASE_NONE)
	{
	  if (prefix[phase] != c)
	    phase = PHASE_NONE;
	  else if (unsigned (phase + 1) == prefix_len)
	    break;
	  else
	    {
	      phase = Phase (phase + 1);
	      continue;
	    }
	}

      if (!prefix_len && c == '"')
	/* Failure mode lexing.  */
	goto out;
      else if (prefix_len && c == ')')
	phase = PHASE_SUFFIX;
      else if (!read_note && c == '\n')
	{
	  pos--;
	  pfile->buffer->cur = pos;
	  if ((pfile->state.in_directive || pfile->state.parsing_args)
	      && pfile->buffer->next_line >= pfile->buffer->rlimit)
	    {
	      cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc, 0,
				   "unterminated raw string");
	      type = CPP_OTHER;
	      goto out;
	    }

	  accum.append (pfile, base, pos - base + 1);
	  _cpp_process_line_notes (pfile, false);

	  if (pfile->buffer->next_line < pfile->buffer->rlimit)
	    CPP_INCREMENT_LINE (pfile, 0);
	  pfile->buffer->need_line = true;

	  if (!get_fresh_line_impl<true> (pfile))
	    {
	      /* We ran out of file and failed to get a line.  */
	      location_t src_loc = token->src_loc;
	      token->type = CPP_EOF;
	      /* Tell the compiler the line number of the EOF token.  */
	      token->src_loc = pfile->line_table->highest_line;
	      token->flags = BOL;
	      if (accum.first)
		_cpp_release_buff (pfile, accum.first);
	      cpp_error_with_line (pfile, CPP_DL_ERROR, src_loc, 0,
				   "unterminated raw string");

	      /* Now pop the buffer that get_fresh_line_impl() did not.  Popping
		 is not safe if processing a directive, however this cannot
		 happen as we already checked above that a line would be
		 available, and get_fresh_line_impl() can't fail in this
		 case.  */
	      gcc_assert (!pfile->state.in_directive);
	      _cpp_pop_buffer (pfile);

	      return;
	    }

	  pos = base = pfile->buffer->cur;
	  note = &pfile->buffer->notes[pfile->buffer->cur_note];
	}
      else if (__builtin_expect ((unsigned char) c >= utf8_continuation, 0)
	       && warn_bidi_or_invalid_utf8_p)
	pos = _cpp_handle_multibyte_utf8 (pfile, c, pos, warn_bidi_p,
					  warn_invalid_utf8_p);
    }

  if (warn_bidi_p)
    maybe_warn_bidi_on_close (pfile, pos);

  if (CPP_OPTION (pfile, user_literals))
    {
      /* If a string format macro, say from inttypes.h, is placed touching
	 a string literal it could be parsed as a C++11 user-defined string
	 literal thus breaking the program.  */
      if (is_macro_not_literal_suffix (pfile, pos))
	{
	  /* Raise a warning, but do not consume subsequent tokens.  */
	  if (CPP_OPTION (pfile, warn_literal_suffix) && !pfile->state.skipping)
	    cpp_warning_with_line (pfile, CPP_W_LITERAL_SUFFIX,
				   token->src_loc, 0,
				   "invalid suffix on literal; C++11 requires "
				   "a space between literal and string macro");
	}
      /* Grab user defined literal suffix.  */
      else if (ISIDST (*pos))
	{
	  type = cpp_userdef_string_add_type (type);
	  ++pos;

	  while (ISIDNUM (*pos))
	    ++pos;
	}
    }

 out:
  pfile->buffer->cur = pos;
  if (!accum.accum)
    create_literal (pfile, token, base, pos - base, type);
  else
    {
      size_t extra_len = pos - base;
      uchar *dest = _cpp_unaligned_alloc (pfile, accum.accum + extra_len + 1);

      token->type = type;
      token->val.str.len = accum.accum + extra_len;
      token->val.str.text = dest;
      for (_cpp_buff *buf = accum.first; buf; buf = buf->next)
	{
	  size_t len = BUFF_FRONT (buf) - buf->base;
	  memcpy (dest, buf->base, len);
	  dest += len;
	}
      _cpp_release_buff (pfile, accum.first);
      memcpy (dest, base, extra_len);
      dest[extra_len] = '\0';
    }
}

/* Lexes a string, character constant, or angle-bracketed header file
   name.  The stored string contains the spelling, including opening
   quote and any leading 'L', 'u', 'U' or 'u8' and optional
   'R' modifier.  It returns the type of the literal, or CPP_OTHER
   if it was not properly terminated, or CPP_LESS for an unterminated
   header name which must be relexed as normal tokens.

   The spelling is NUL-terminated, but it is not guaranteed that this
   is the first NUL since embedded NULs are preserved.  */
static void
lex_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
{
  bool saw_NUL = false;
  const uchar *cur;
  cppchar_t terminator;
  enum cpp_ttype type;

  cur = base;
  terminator = *cur++;
  if (terminator == 'L' || terminator == 'U')
    terminator = *cur++;
  else if (terminator == 'u')
    {
      terminator = *cur++;
      if (terminator == '8')
	terminator = *cur++;
    }
  if (terminator == 'R')
    {
      lex_raw_string (pfile, token, base);
      return;
    }
  if (terminator == '"')
    type = (*base == 'L' ? CPP_WSTRING :
	    *base == 'U' ? CPP_STRING32 :
	    *base == 'u' ? (base[1] == '8' ? CPP_UTF8STRING : CPP_STRING16)
			 : CPP_STRING);
  else if (terminator == '\'')
    type = (*base == 'L' ? CPP_WCHAR :
	    *base == 'U' ? CPP_CHAR32 :
	    *base == 'u' ? (base[1] == '8' ? CPP_UTF8CHAR : CPP_CHAR16)
			 : CPP_CHAR);
  else
    terminator = '>', type = CPP_HEADER_NAME;

  const bool warn_bidi_p = pfile->warn_bidi_p ();
  const bool warn_invalid_utf8_p = CPP_OPTION (pfile, cpp_warn_invalid_utf8);
  const bool warn_bidi_or_invalid_utf8_p = warn_bidi_p | warn_invalid_utf8_p;
  for (;;)
    {
      cppchar_t c = *cur++;

      /* In #include-style directives, terminators are not escapable.  */
      if (c == '\\' && !pfile->state.angled_headers && *cur != '\n')
	{
	  if ((cur[0] == 'u' || cur[0] == 'U' || cur[0] == 'N') && warn_bidi_p)
	    {
	      location_t loc;
	      bidi::kind kind;
	      if (cur[0] == 'N')
		kind = get_bidi_named (pfile, cur + 1, &loc);
	      else
		kind = get_bidi_ucn (pfile, cur + 1, cur[0] == 'U', &loc);
	      maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/true, loc);
	    }
	  cur++;
	}
      else if (c == terminator)
	{
	  if (warn_bidi_p)
	    maybe_warn_bidi_on_close (pfile, cur - 1);
	  break;
	}
      else if (c == '\n')
	{
	  cur--;
	  /* Unmatched quotes always yield undefined behavior, but
	     greedy lexing means that what appears to be an unterminated
	     header name may actually be a legitimate sequence of tokens.  */
	  if (terminator == '>')
	    {
	      token->type = CPP_LESS;
	      return;
	    }
	  type = CPP_OTHER;
	  break;
	}
      else if (c == '\0')
	saw_NUL = true;
      else if (__builtin_expect (c >= utf8_continuation, 0)
	       && warn_bidi_or_invalid_utf8_p)
	cur = _cpp_handle_multibyte_utf8 (pfile, c, cur, warn_bidi_p,
					  warn_invalid_utf8_p);
    }

  if (saw_NUL && !pfile->state.skipping)
    cpp_error (pfile, CPP_DL_WARNING,
	       "null character(s) preserved in literal");

  if (type == CPP_OTHER && CPP_OPTION (pfile, lang) != CLK_ASM)
    cpp_error (pfile, CPP_DL_PEDWARN, "missing terminating %c character",
	       (int) terminator);

  if (CPP_OPTION (pfile, user_literals))
    {
      /* If a string format macro, say from inttypes.h, is placed touching
	 a string literal it could be parsed as a C++11 user-defined string
	 literal thus breaking the program.  */
      if (is_macro_not_literal_suffix (pfile, cur))
	{
	  /* Raise a warning, but do not consume subsequent tokens.  */
	  if (CPP_OPTION (pfile, warn_literal_suffix) && !pfile->state.skipping)
	    cpp_warning_with_line (pfile, CPP_W_LITERAL_SUFFIX,
				   token->src_loc, 0,
				   "invalid suffix on literal; C++11 requires "
				   "a space between literal and string macro");
	}
      /* Grab user defined literal suffix.  */
      else if (ISIDST (*cur))
	{
	  type = cpp_userdef_char_add_type (type);
	  type = cpp_userdef_string_add_type (type);
          ++cur;

	  while (ISIDNUM (*cur))
	    ++cur;
	}
    }
  else if (CPP_OPTION (pfile, cpp_warn_cxx11_compat)
	   && is_macro (pfile, cur)
	   && !pfile->state.skipping)
    cpp_warning_with_line (pfile, CPP_W_CXX11_COMPAT,
			   token->src_loc, 0, "C++11 requires a space "
			   "between string literal and macro");

  pfile->buffer->cur = cur;
  create_literal (pfile, token, base, cur - base, type);
}

/* Return the comment table. The client may not make any assumption
   about the ordering of the table.  */
cpp_comment_table *
cpp_get_comments (cpp_reader *pfile)
{
  return &pfile->comments;
}

/* Append a comment to the end of the comment table. */
static void 
store_comment (cpp_reader *pfile, cpp_token *token) 
{
  int len;

  if (pfile->comments.allocated == 0)
    {
      pfile->comments.allocated = 256; 
      pfile->comments.entries = (cpp_comment *) xmalloc
	(pfile->comments.allocated * sizeof (cpp_comment));
    }

  if (pfile->comments.count == pfile->comments.allocated)
    {
      pfile->comments.allocated *= 2;
      pfile->comments.entries = (cpp_comment *) xrealloc
	(pfile->comments.entries,
	 pfile->comments.allocated * sizeof (cpp_comment));
    }

  len = token->val.str.len;

  /* Copy comment. Note, token may not be NULL terminated. */
  pfile->comments.entries[pfile->comments.count].comment = 
    (char *) xmalloc (sizeof (char) * (len + 1));
  memcpy (pfile->comments.entries[pfile->comments.count].comment,
	  token->val.str.text, len);
  pfile->comments.entries[pfile->comments.count].comment[len] = '\0';

  /* Set source location. */
  pfile->comments.entries[pfile->comments.count].sloc = token->src_loc;

  /* Increment the count of entries in the comment table. */
  pfile->comments.count++;
}

/* The stored comment includes the comment start and any terminator.  */
static void
save_comment (cpp_reader *pfile, cpp_token *token, const unsigned char *from,
	      cppchar_t type)
{
  unsigned char *buffer;
  unsigned int len, clen, i;

  len = pfile->buffer->cur - from + 1; /* + 1 for the initial '/'.  */

  /* C++ comments probably (not definitely) have moved past a new
     line, which we don't want to save in the comment.  */
  if (is_vspace (pfile->buffer->cur[-1]))
    len--;

  /* If we are currently in a directive or in argument parsing, then
     we need to store all C++ comments as C comments internally, and
     so we need to allocate a little extra space in that case.

     Note that the only time we encounter a directive here is
     when we are saving comments in a "#define".  */
  clen = ((pfile->state.in_directive || pfile->state.parsing_args)
	  && type == '/') ? len + 2 : len;

  buffer = _cpp_unaligned_alloc (pfile, clen);

  token->type = CPP_COMMENT;
  token->val.str.len = clen;
  token->val.str.text = buffer;

  buffer[0] = '/';
  memcpy (buffer + 1, from, len - 1);

  /* Finish conversion to a C comment, if necessary.  */
  if ((pfile->state.in_directive || pfile->state.parsing_args) && type == '/')
    {
      buffer[1] = '*';
      buffer[clen - 2] = '*';
      buffer[clen - 1] = '/';
      /* As there can be in a C++ comments illegal sequences for C comments
         we need to filter them out.  */
      for (i = 2; i < (clen - 2); i++)
        if (buffer[i] == '/' && (buffer[i - 1] == '*' || buffer[i + 1] == '*'))
          buffer[i] = '|';
    }

  /* Finally store this comment for use by clients of libcpp. */
  store_comment (pfile, token);
}

/* Returns true if comment at COMMENT_START is a recognized FALLTHROUGH
   comment.  */

static bool
fallthrough_comment_p (cpp_reader *pfile, const unsigned char *comment_start)
{
  const unsigned char *from = comment_start + 1;

  switch (CPP_OPTION (pfile, cpp_warn_implicit_fallthrough))
    {
      /* For both -Wimplicit-fallthrough=0 and -Wimplicit-fallthrough=5 we
	 don't recognize any comments.  The latter only checks attributes,
	 the former doesn't warn.  */
    case 0:
    default:
      return false;
      /* -Wimplicit-fallthrough=1 considers any comment, no matter what
	 content it has.  */
    case 1:
      return true;
    case 2:
      /* -Wimplicit-fallthrough=2 looks for (case insensitive)
	 .*falls?[ \t-]*thr(u|ough).* regex.  */
      for (; (size_t) (pfile->buffer->cur - from) >= sizeof "fallthru" - 1;
	   from++)
	{
	  /* Is there anything like strpbrk with upper boundary, or
	     memchr looking for 2 characters rather than just one?  */
	  if (from[0] != 'f' && from[0] != 'F')
	    continue;
	  if (from[1] != 'a' && from[1] != 'A')
	    continue;
	  if (from[2] != 'l' && from[2] != 'L')
	    continue;
	  if (from[3] != 'l' && from[3] != 'L')
	    continue;
	  from += sizeof "fall" - 1;
	  if (from[0] == 's' || from[0] == 'S')
	    from++;
	  while (*from == ' ' || *from == '\t' || *from == '-')
	    from++;
	  if (from[0] != 't' && from[0] != 'T')
	    continue;
	  if (from[1] != 'h' && from[1] != 'H')
	    continue;
	  if (from[2] != 'r' && from[2] != 'R')
	    continue;
	  if (from[3] == 'u' || from[3] == 'U')
	    return true;
	  if (from[3] != 'o' && from[3] != 'O')
	    continue;
	  if (from[4] != 'u' && from[4] != 'U')
	    continue;
	  if (from[5] != 'g' && from[5] != 'G')
	    continue;
	  if (from[6] != 'h' && from[6] != 'H')
	    continue;
	  return true;
	}
      return false;
    case 3:
    case 4:
      break;
    }

  /* Whole comment contents:
     -fallthrough
     @fallthrough@
   */
  if (*from == '-' || *from == '@')
    {
      size_t len = sizeof "fallthrough" - 1;
      if ((size_t) (pfile->buffer->cur - from - 1) < len)
	return false;
      if (memcmp (from + 1, "fallthrough", len))
	return false;
      if (*from == '@')
	{
	  if (from[len + 1] != '@')
	    return false;
	  len++;
	}
      from += 1 + len;
    }
  /* Whole comment contents (regex):
     lint -fallthrough[ \t]*
   */
  else if (*from == 'l')
    {
      size_t len = sizeof "int -fallthrough" - 1;
      if ((size_t) (pfile->buffer->cur - from - 1) < len)
	return false;
      if (memcmp (from + 1, "int -fallthrough", len))
	return false;
      from += 1 + len;
      while (*from == ' ' || *from == '\t')
	from++;
    }
  /* Whole comment contents (regex):
     [ \t]*FALLTHR(U|OUGH)[ \t]*
   */
  else if (CPP_OPTION (pfile, cpp_warn_implicit_fallthrough) == 4)
    {
      while (*from == ' ' || *from == '\t')
	from++;
      if ((size_t) (pfile->buffer->cur - from)  < sizeof "FALLTHRU" - 1)
	return false;
      if (memcmp (from, "FALLTHR", sizeof "FALLTHR" - 1))
	return false;
      from += sizeof "FALLTHR" - 1;
      if (*from == 'U')
	from++;
      else if ((size_t) (pfile->buffer->cur - from)  < sizeof "OUGH" - 1)
	return false;
      else if (memcmp (from, "OUGH", sizeof "OUGH" - 1))
	return false;
      else
	from += sizeof "OUGH" - 1;
      while (*from == ' ' || *from == '\t')
	from++;
    }
  /* Whole comment contents (regex):
     [ \t.!]*(ELSE,? |INTENTIONAL(LY)? )?FALL(S | |-)?THR(OUGH|U)[ \t.!]*(-[^\n\r]*)?
     [ \t.!]*(Else,? |Intentional(ly)? )?Fall((s | |-)[Tt]|t)hr(ough|u)[ \t.!]*(-[^\n\r]*)?
     [ \t.!]*([Ee]lse,? |[Ii]ntentional(ly)? )?fall(s | |-)?thr(ough|u)[ \t.!]*(-[^\n\r]*)?
   */
  else
    {
      while (*from == ' ' || *from == '\t' || *from == '.' || *from == '!')
	from++;
      unsigned char f = *from;
      bool all_upper = false;
      if (f == 'E' || f == 'e')
	{
	  if ((size_t) (pfile->buffer->cur - from)
	      < sizeof "else fallthru" - 1)
	    return false;
	  if (f == 'E' && memcmp (from + 1, "LSE", sizeof "LSE" - 1) == 0)
	    all_upper = true;
	  else if (memcmp (from + 1, "lse", sizeof "lse" - 1))
	    return false;
	  from += sizeof "else" - 1;
	  if (*from == ',')
	    from++;
	  if (*from != ' ')
	    return false;
	  from++;
	  if (all_upper && *from == 'f')
	    return false;
	  if (f == 'e' && *from == 'F')
	    return false;
	  f = *from;
	}
      else if (f == 'I' || f == 'i')
	{
	  if ((size_t) (pfile->buffer->cur - from)
	      < sizeof "intentional fallthru" - 1)
	    return false;
	  if (f == 'I' && memcmp (from + 1, "NTENTIONAL",
				  sizeof "NTENTIONAL" - 1) == 0)
	    all_upper = true;
	  else if (memcmp (from + 1, "ntentional",
			   sizeof "ntentional" - 1))
	    return false;
	  from += sizeof "intentional" - 1;
	  if (*from == ' ')
	    {
	      from++;
	      if (all_upper && *from == 'f')
		return false;
	    }
	  else if (all_upper)
	    {
	      if (memcmp (from, "LY F", sizeof "LY F" - 1))
		return false;
	      from += sizeof "LY " - 1;
	    }
	  else
	    {
	      if (memcmp (from, "ly ", sizeof "ly " - 1))
		return false;
	      from += sizeof "ly " - 1;
	    }
	  if (f == 'i' && *from == 'F')
	    return false;
	  f = *from;
	}
      if (f != 'F' && f != 'f')
	return false;
      if ((size_t) (pfile->buffer->cur - from) < sizeof "fallthru" - 1)
	return false;
      if (f == 'F' && memcmp (from + 1, "ALL", sizeof "ALL" - 1) == 0)
	all_upper = true;
      else if (all_upper)
	return false;
      else if (memcmp (from + 1, "all", sizeof "all" - 1))
	return false;
      from += sizeof "fall" - 1;
      if (*from == (all_upper ? 'S' : 's') && from[1] == ' ')
	from += 2;
      else if (*from == ' ' || *from == '-')
	from++;
      else if (*from != (all_upper ? 'T' : 't'))
	return false;
      if ((f == 'f' || *from != 'T') && (all_upper || *from != 't'))
	return false;
      if ((size_t) (pfile->buffer->cur - from) < sizeof "thru" - 1)
	return false;
      if (memcmp (from + 1, all_upper ? "HRU" : "hru", sizeof "hru" - 1))
	{
	  if ((size_t) (pfile->buffer->cur - from) < sizeof "through" - 1)
	    return false;
	  if (memcmp (from + 1, all_upper ? "HROUGH" : "hrough",
		      sizeof "hrough" - 1))
	    return false;
	  from += sizeof "through" - 1;
	}
      else
	from += sizeof "thru" - 1;
      while (*from == ' ' || *from == '\t' || *from == '.' || *from == '!')
	from++;
      if (*from == '-')
	{
	  from++;
	  if (*comment_start == '*')
	    {
	      do
		{
		  while (*from && *from != '*'
			 && *from != '\n' && *from != '\r')
		    from++;
		  if (*from != '*' || from[1] == '/')
		    break;
		  from++;
		}
	      while (1);
	    }
	  else
	    while (*from && *from != '\n' && *from != '\r')
	      from++;
	}
    }
  /* C block comment.  */
  if (*comment_start == '*')
    {
      if (*from != '*' || from[1] != '/')
	return false;
    }
  /* C++ line comment.  */
  else if (*from != '\n')
    return false;

  return true;
}

/* Allocate COUNT tokens for RUN.  */
void
_cpp_init_tokenrun (tokenrun *run, unsigned int count)
{
  run->base = XNEWVEC (cpp_token, count);
  run->limit = run->base + count;
  run->next = NULL;
}

/* Returns the next tokenrun, or creates one if there is none.  */
static tokenrun *
next_tokenrun (tokenrun *run)
{
  if (run->next == NULL)
    {
      run->next = XNEW (tokenrun);
      run->next->prev = run;
      _cpp_init_tokenrun (run->next, 250);
    }

  return run->next;
}

/* Return the number of not yet processed token in a given
   context.  */
int
_cpp_remaining_tokens_num_in_context (cpp_context *context)
{
  if (context->tokens_kind == TOKENS_KIND_DIRECT)
    return (LAST (context).token - FIRST (context).token);
  else if (context->tokens_kind == TOKENS_KIND_INDIRECT
	   || context->tokens_kind == TOKENS_KIND_EXTENDED)
    return (LAST (context).ptoken - FIRST (context).ptoken);
  else
      abort ();
}

/* Returns the token present at index INDEX in a given context.  If
   INDEX is zero, the next token to be processed is returned.  */
static const cpp_token*
_cpp_token_from_context_at (cpp_context *context, int index)
{
  if (context->tokens_kind == TOKENS_KIND_DIRECT)
    return &(FIRST (context).token[index]);
  else if (context->tokens_kind == TOKENS_KIND_INDIRECT
	   || context->tokens_kind == TOKENS_KIND_EXTENDED)
    return FIRST (context).ptoken[index];
 else
   abort ();
}

/* Look ahead in the input stream.  */
const cpp_token *
cpp_peek_token (cpp_reader *pfile, int index)
{
  cpp_context *context = pfile->context;
  const cpp_token *peektok;
  int count;

  /* First, scan through any pending cpp_context objects.  */
  while (context->prev)
    {
      ptrdiff_t sz = _cpp_remaining_tokens_num_in_context (context);

      if (index < (int) sz)
        return _cpp_token_from_context_at (context, index);
      index -= (int) sz;
      context = context->prev;
    }

  /* We will have to read some new tokens after all (and do so
     without invalidating preceding tokens).  */
  count = index;
  pfile->keep_tokens++;

  /* For peeked tokens temporarily disable line_change reporting,
     until the tokens are parsed for real.  */
  void (*line_change) (cpp_reader *, const cpp_token *, int)
    = pfile->cb.line_change;
  pfile->cb.line_change = NULL;

  do
    {
      peektok = _cpp_lex_token (pfile);
      if (peektok->type == CPP_EOF)
	{
	  index--;
	  break;
	}
      else if (peektok->type == CPP_PRAGMA)
	{
	  /* Don't peek past a pragma.  */
	  if (peektok == &pfile->directive_result)
	    /* Save the pragma in the buffer.  */
	    *pfile->cur_token++ = *peektok;
	  index--;
	  break;
	}
    }
  while (index--);

  _cpp_backup_tokens_direct (pfile, count - index);
  pfile->keep_tokens--;
  pfile->cb.line_change = line_change;

  return peektok;
}

/* Allocate a single token that is invalidated at the same time as the
   rest of the tokens on the line.  Has its line and col set to the
   same as the last lexed token, so that diagnostics appear in the
   right place.  */
cpp_token *
_cpp_temp_token (cpp_reader *pfile)
{
  cpp_token *old, *result;
  ptrdiff_t sz = pfile->cur_run->limit - pfile->cur_token;
  ptrdiff_t la = (ptrdiff_t) pfile->lookaheads;

  old = pfile->cur_token - 1;
  /* Any pre-existing lookaheads must not be clobbered.  */
  if (la)
    {
      if (sz <= la)
        {
          tokenrun *next = next_tokenrun (pfile->cur_run);

          if (sz < la)
            memmove (next->base + 1, next->base,
                     (la - sz) * sizeof (cpp_token));

          next->base[0] = pfile->cur_run->limit[-1];
        }

      if (sz > 1)
        memmove (pfile->cur_token + 1, pfile->cur_token,
                 MIN (la, sz - 1) * sizeof (cpp_token));
    }

  if (!sz && pfile->cur_token == pfile->cur_run->limit)
    {
      pfile->cur_run = next_tokenrun (pfile->cur_run);
      pfile->cur_token = pfile->cur_run->base;
    }

  result = pfile->cur_token++;
  result->src_loc = old->src_loc;
  return result;
}

/* We're at the beginning of a logical line (so not in
  directives-mode) and RESULT is a CPP_NAME with NODE_MODULE set.  See
  if we should enter deferred_pragma mode to tokenize the rest of the
  line as a module control-line.  */

static void
cpp_maybe_module_directive (cpp_reader *pfile, cpp_token *result)
{
  unsigned backup = 0; /* Tokens we peeked.  */
  cpp_hashnode *node = result->val.node.node;
  cpp_token *peek = result;
  cpp_token *keyword = peek;
  cpp_hashnode *(&n_modules)[spec_nodes::M_HWM][2] = pfile->spec_nodes.n_modules;
  int header_count = 0;

  /* Make sure the incoming state is as we expect it.  This way we
     can restore it using constants.  */
  gcc_checking_assert (!pfile->state.in_deferred_pragma
		       && !pfile->state.skipping
		       && !pfile->state.parsing_args
		       && !pfile->state.angled_headers
		       && (pfile->state.save_comments
			   == !CPP_OPTION (pfile, discard_comments)));

  /* Enter directives mode sufficiently for peeking.  We don't have
     to actually set in_directive.  */
  pfile->state.in_deferred_pragma = true;

  /* These two fields are needed to process tokenization in deferred
     pragma mode.  They are not used outside deferred pragma mode or
     directives mode.  */
  pfile->state.pragma_allow_expansion = true;
  pfile->directive_line = result->src_loc;

  /* Saving comments is incompatible with directives mode.   */
  pfile->state.save_comments = 0;

  if (node == n_modules[spec_nodes::M_EXPORT][0])
    {
      peek = _cpp_lex_direct (pfile);
      keyword = peek;
      backup++;
      if (keyword->type != CPP_NAME)
	goto not_module;
      node = keyword->val.node.node;
      if (!(node->flags & NODE_MODULE))
	goto not_module;
    }

  if (node == n_modules[spec_nodes::M__IMPORT][0])
    /* __import  */
    header_count = backup + 2 + 16;
  else if (node == n_modules[spec_nodes::M_IMPORT][0])
    /* import  */
    header_count = backup + 2 + (CPP_OPTION (pfile, preprocessed) ? 16 : 0);
  else if (node == n_modules[spec_nodes::M_MODULE][0])
    ; /* module  */
  else
    goto not_module;

  /* We've seen [export] {module|import|__import}.  Check the next token.  */
  if (header_count)
    /* After '{,__}import' a header name may appear.  */
    pfile->state.angled_headers = true;
  peek = _cpp_lex_direct (pfile);
  backup++;

  /* ... import followed by identifier, ':', '<' or
     header-name preprocessing tokens, or module
     followed by cpp-identifier, ':' or ';' preprocessing
     tokens.  C++ keywords are not yet relevant.  */
  if (peek->type == CPP_NAME
      || peek->type == CPP_COLON
      ||  (header_count
	   ? (peek->type == CPP_LESS
	      || (peek->type == CPP_STRING && peek->val.str.text[0] != 'R')
	      || peek->type == CPP_HEADER_NAME)
	   : peek->type == CPP_SEMICOLON))
    {
      pfile->state.pragma_allow_expansion = !CPP_OPTION (pfile, preprocessed);
      if (!pfile->state.pragma_allow_expansion)
	pfile->state.prevent_expansion++;

      if (!header_count && linemap_included_from
	  (LINEMAPS_LAST_ORDINARY_MAP (pfile->line_table)))
	cpp_error_with_line (pfile, CPP_DL_ERROR, keyword->src_loc, 0,
			     "module control-line cannot be in included file");

      /* The first one or two tokens cannot be macro names.  */
      for (int ix = backup; ix--;)
	{
	  cpp_token *tok = ix ? keyword : result;
	  cpp_hashnode *node = tok->val.node.node;

	  /* Don't attempt to expand the token.  */
	  tok->flags |= NO_EXPAND;
	  if (_cpp_defined_macro_p (node)
	      && _cpp_maybe_notify_macro_use (pfile, node, tok->src_loc)
	      && !cpp_fun_like_macro_p (node))
	    cpp_error_with_line (pfile, CPP_DL_ERROR, tok->src_loc, 0, 
				 "module control-line \"%s\" cannot be"
				 " an object-like macro",
				 NODE_NAME (node));
	}

      /* Map to underbar variants.  */
      keyword->val.node.node = n_modules[header_count
					 ? spec_nodes::M_IMPORT
					 : spec_nodes::M_MODULE][1];
      if (backup != 1)
	result->val.node.node = n_modules[spec_nodes::M_EXPORT][1];

      /* Maybe tell the tokenizer we expect a header-name down the
	 road.  */
      pfile->state.directive_file_token = header_count;
    }
  else
    {
    not_module:
      /* Drop out of directive mode.  */
      /* We aaserted save_comments had this value upon entry.  */
      pfile->state.save_comments
	= !CPP_OPTION (pfile, discard_comments);
      pfile->state.in_deferred_pragma = false;
      /* Do not let this remain on.  */
      pfile->state.angled_headers = false;
    }

  /* In either case we want to backup the peeked tokens.  */
  if (backup)
    {
      /* If we saw EOL, we should drop it, because this isn't a module
	 control-line after all.  */
      bool eol = peek->type == CPP_PRAGMA_EOL;
      if (!eol || backup > 1)
	{
	  /* Put put the peeked tokens back  */
	  _cpp_backup_tokens_direct (pfile, backup);
	  /* But if the last one was an EOL, forget it.  */
	  if (eol)
	    pfile->lookaheads--;
	}
    }
}

/* Lex a token into RESULT (external interface).  Takes care of issues
   like directive handling, token lookahead, multiple include
   optimization and skipping.  */
const cpp_token *
_cpp_lex_token (cpp_reader *pfile)
{
  cpp_token *result;

  for (;;)
    {
      if (pfile->cur_token == pfile->cur_run->limit)
	{
	  pfile->cur_run = next_tokenrun (pfile->cur_run);
	  pfile->cur_token = pfile->cur_run->base;
	}
      /* We assume that the current token is somewhere in the current
	 run.  */
      if (pfile->cur_token < pfile->cur_run->base
	  || pfile->cur_token >= pfile->cur_run->limit)
	abort ();

      if (pfile->lookaheads)
	{
	  pfile->lookaheads--;
	  result = pfile->cur_token++;
	}
      else
	result = _cpp_lex_direct (pfile);

      if (result->flags & BOL)
	{
	  /* Is this a directive.  If _cpp_handle_directive returns
	     false, it is an assembler #.  */
	  if (result->type == CPP_HASH
	      /* 6.10.3 p 11: Directives in a list of macro arguments
		 gives undefined behavior.  This implementation
		 handles the directive as normal.  */
	      && pfile->state.parsing_args != 1)
	    {
	      if (_cpp_handle_directive (pfile, result->flags & PREV_WHITE))
		{
		  if (pfile->directive_result.type == CPP_PADDING)
		    continue;
		  result = &pfile->directive_result;
		}
	    }
	  else if (pfile->state.in_deferred_pragma)
	    result = &pfile->directive_result;
	  else if (result->type == CPP_NAME
		   && (result->val.node.node->flags & NODE_MODULE)
		   && !pfile->state.skipping
		   /* Unlike regular directives, we do not deal with
		      tokenizing module directives as macro arguments.
		      That's not permitted.  */
		   && !pfile->state.parsing_args)
	    {
	      /* P1857.  Before macro expansion, At start of logical
		 line ... */
	      /* We don't have to consider lookaheads at this point.  */
	      gcc_checking_assert (!pfile->lookaheads);

	      cpp_maybe_module_directive (pfile, result);
	    }

	  if (pfile->cb.line_change && !pfile->state.skipping)
	    pfile->cb.line_change (pfile, result, pfile->state.parsing_args);
	}

      /* We don't skip tokens in directives.  */
      if (pfile->state.in_directive || pfile->state.in_deferred_pragma)
	break;

      /* Outside a directive, invalidate controlling macros.  At file
	 EOF, _cpp_lex_direct takes care of popping the buffer, so we never
	 get here and MI optimization works.  */
      pfile->mi_valid = false;

      if (!pfile->state.skipping || result->type == CPP_EOF)
	break;
    }

  return result;
}

/* Returns true if a fresh line has been loaded.  */
template <bool lexing_raw_string>
static bool
get_fresh_line_impl (cpp_reader *pfile)
{
  /* We can't get a new line until we leave the current directive, unless we
     are lexing a raw string, in which case it will be OK as long as we don't
     pop the current buffer.  */
  if (!lexing_raw_string && pfile->state.in_directive)
    return false;

  for (;;)
    {
      cpp_buffer *buffer = pfile->buffer;

      if (!buffer->need_line)
	return true;

      if (buffer->next_line < buffer->rlimit)
	{
	  _cpp_clean_line (pfile);
	  return true;
	}

      /* We can't change buffers until we leave the current directive.  */
      if (lexing_raw_string && pfile->state.in_directive)
	return false;

      /* First, get out of parsing arguments state.  */
      if (pfile->state.parsing_args)
	return false;

      /* End of buffer.  Non-empty files should end in a newline.  */
      if (buffer->buf != buffer->rlimit
	  && buffer->next_line > buffer->rlimit
	  && !buffer->from_stage3)
	{
	  /* Clip to buffer size.  */
	  buffer->next_line = buffer->rlimit;
	}

      if (buffer->prev && !buffer->return_at_eof)
	_cpp_pop_buffer (pfile);
      else
	{
	  /* End of translation.  Do not pop the buffer yet. Increment
	     line number so that the EOF token is on a line of its own
	     (_cpp_lex_direct doesn't increment in that case, because
	     it's hard for it to distinguish this special case). */
	  CPP_INCREMENT_LINE (pfile, 0);
	  return false;
	}
    }
}

bool
_cpp_get_fresh_line (cpp_reader *pfile)
{
  return get_fresh_line_impl<false> (pfile);
}


#define IF_NEXT_IS(CHAR, THEN_TYPE, ELSE_TYPE)		\
  do							\
    {							\
      result->type = ELSE_TYPE;				\
      if (*buffer->cur == CHAR)				\
	buffer->cur++, result->type = THEN_TYPE;	\
    }							\
  while (0)

/* Lex a token into pfile->cur_token, which is also incremented, to
   get diagnostics pointing to the correct location.

   Does not handle issues such as token lookahead, multiple-include
   optimization, directives, skipping etc.  This function is only
   suitable for use by _cpp_lex_token, and in special cases like
   lex_expansion_token which doesn't care for any of these issues.

   When meeting a newline, returns CPP_EOF if parsing a directive,
   otherwise returns to the start of the token buffer if permissible.
   Returns the location of the lexed token.  */
cpp_token *
_cpp_lex_direct (cpp_reader *pfile)
{
  cppchar_t c;
  cpp_buffer *buffer;
  const unsigned char *comment_start;
  bool fallthrough_comment = false;
  cpp_token *result = pfile->cur_token++;

 fresh_line:
  result->flags = 0;
  buffer = pfile->buffer;
  if (buffer->need_line)
    {
      if (pfile->state.in_deferred_pragma)
	{
	  /* This can happen in cases like:
	     #define loop(x) whatever
	     #pragma omp loop
	     where when trying to expand loop we need to peek
	     next token after loop, but aren't still in_deferred_pragma
	     mode but are in in_directive mode, so buffer->need_line
	     is set, a CPP_EOF is peeked.  */
	  result->type = CPP_PRAGMA_EOL;
	  pfile->state.in_deferred_pragma = false;
	  if (!pfile->state.pragma_allow_expansion)
	    pfile->state.prevent_expansion--;
	  return result;
	}
      if (!_cpp_get_fresh_line (pfile))
	{
	  result->type = CPP_EOF;
	  /* Not a real EOF in a directive or arg parsing -- we refuse
  	     to advance to the next file now, and will once we're out
  	     of those modes.  */
	  if (!pfile->state.in_directive && !pfile->state.parsing_args)
	    {
	      /* Tell the compiler the line number of the EOF token.  */
	      result->src_loc = pfile->line_table->highest_line;
	      result->flags = BOL;
	      /* Now pop the buffer that _cpp_get_fresh_line did not.  */
	      _cpp_pop_buffer (pfile);
	    }
	  return result;
	}
      if (buffer != pfile->buffer)
	fallthrough_comment = false;
      if (!pfile->keep_tokens)
	{
	  pfile->cur_run = &pfile->base_run;
	  result = pfile->base_run.base;
	  pfile->cur_token = result + 1;
	}
      result->flags = BOL;
      if (pfile->state.parsing_args == 2)
	result->flags |= PREV_WHITE;
    }
  buffer = pfile->buffer;
 update_tokens_line:
  result->src_loc = pfile->line_table->highest_line;

 skipped_white:
  if (buffer->cur >= buffer->notes[buffer->cur_note].pos
      && !pfile->overlaid_buffer)
    {
      _cpp_process_line_notes (pfile, false);
      result->src_loc = pfile->line_table->highest_line;
    }
  c = *buffer->cur++;

  if (pfile->forced_token_location)
    result->src_loc = pfile->forced_token_location;
  else
    result->src_loc = linemap_position_for_column (pfile->line_table,
					  CPP_BUF_COLUMN (buffer, buffer->cur));

  switch (c)
    {
    case ' ': case '\t': case '\f': case '\v': case '\0':
      result->flags |= PREV_WHITE;
      skip_whitespace (pfile, c);
      goto skipped_white;

    case '\n':
      /* Increment the line, unless this is the last line ...  */
      if (buffer->cur < buffer->rlimit
	  /* ... or this is a #include, (where _cpp_stack_file needs to
	     unwind by one line) ...  */
	  || (pfile->state.in_directive > 1
	      /* ... except traditional-cpp increments this elsewhere.  */
	      && !CPP_OPTION (pfile, traditional)))
	CPP_INCREMENT_LINE (pfile, 0);
      buffer->need_line = true;
      if (pfile->state.in_deferred_pragma)
	{
	  /* Produce the PRAGMA_EOL on this line.  File reading
	     ensures there is always a \n at end of the buffer, thus
	     in a deferred pragma we always see CPP_PRAGMA_EOL before
	     any CPP_EOF.  */
	  result->type = CPP_PRAGMA_EOL;
	  result->flags &= ~PREV_WHITE;
	  pfile->state.in_deferred_pragma = false;
	  if (!pfile->state.pragma_allow_expansion)
	    pfile->state.prevent_expansion--;
	  return result;
	}
      goto fresh_line;

    case '0': case '1': case '2': case '3': case '4':
    case '5': case '6': case '7': case '8': case '9':
      {
	struct normalize_state nst = INITIAL_NORMALIZE_STATE;
	result->type = CPP_NUMBER;
	lex_number (pfile, &result->val.str, &nst);
	warn_about_normalization (pfile, result, &nst, false);
	break;
      }

    case 'L':
    case 'u':
    case 'U':
    case 'R':
      /* 'L', 'u', 'U', 'u8' or 'R' may introduce wide characters,
	 wide strings or raw strings.  */
      if (c == 'L' || CPP_OPTION (pfile, rliterals)
	  || (c != 'R' && CPP_OPTION (pfile, uliterals)))
	{
	  if ((*buffer->cur == '\'' && c != 'R')
	      || *buffer->cur == '"'
	      || (*buffer->cur == 'R'
		  && c != 'R'
		  && buffer->cur[1] == '"'
		  && CPP_OPTION (pfile, rliterals))
	      || (*buffer->cur == '8'
		  && c == 'u'
		  && ((buffer->cur[1] == '"' || (buffer->cur[1] == '\''
				&& CPP_OPTION (pfile, utf8_char_literals)))
		      || (buffer->cur[1] == 'R' && buffer->cur[2] == '"'
			  && CPP_OPTION (pfile, rliterals)))))
	    {
	      lex_string (pfile, result, buffer->cur - 1);
	      break;
	    }
	}
      /* Fall through.  */

    case '_':
    case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
    case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
    case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
    case 's': case 't':           case 'v': case 'w': case 'x':
    case 'y': case 'z':
    case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
    case 'G': case 'H': case 'I': case 'J': case 'K':
    case 'M': case 'N': case 'O': case 'P': case 'Q':
    case 'S': case 'T':           case 'V': case 'W': case 'X':
    case 'Y': case 'Z':
      result->type = CPP_NAME;
      {
	struct normalize_state nst = INITIAL_NORMALIZE_STATE;
	result->val.node.node = lex_identifier (pfile, buffer->cur - 1, false,
						&nst,
						&result->val.node.spelling);
	warn_about_normalization (pfile, result, &nst, true);
      }

      /* Convert named operators to their proper types.  */
      if (result->val.node.node->flags & NODE_OPERATOR)
	{
	  result->flags |= NAMED_OP;
	  result->type = (enum cpp_ttype) result->val.node.node->directive_index;
	}

      /* Signal FALLTHROUGH comment followed by another token.  */
      if (fallthrough_comment)
	result->flags |= PREV_FALLTHROUGH;
      break;

    case '\'':
    case '"':
      lex_string (pfile, result, buffer->cur - 1);
      break;

    case '/':
      /* A potential block or line comment.  */
      comment_start = buffer->cur;
      c = *buffer->cur;
      
      if (c == '*')
	{
	  if (_cpp_skip_block_comment (pfile))
	    cpp_error (pfile, CPP_DL_ERROR, "unterminated comment");
	}
      else if (c == '/' && ! CPP_OPTION (pfile, traditional))
	{
	  /* Don't warn for system headers.  */
	  if (_cpp_in_system_header (pfile))
	    ;
	  /* Warn about comments if pedantically GNUC89, and not
	     in system headers.  */
	  else if (CPP_OPTION (pfile, lang) == CLK_GNUC89
		   && CPP_PEDANTIC (pfile)
		   && ! buffer->warned_cplusplus_comments)
	    {
	      if (cpp_error (pfile, CPP_DL_PEDWARN,
			     "C++ style comments are not allowed in ISO C90"))
		cpp_error (pfile, CPP_DL_NOTE,
			   "(this will be reported only once per input file)");
	      buffer->warned_cplusplus_comments = 1;
	    }
	  /* Or if specifically desired via -Wc90-c99-compat.  */
	  else if (CPP_OPTION (pfile, cpp_warn_c90_c99_compat) > 0
		   && ! CPP_OPTION (pfile, cplusplus)
		   && ! buffer->warned_cplusplus_comments)
	    {
	      if (cpp_error (pfile, CPP_DL_WARNING,
			     "C++ style comments are incompatible with C90"))
		cpp_error (pfile, CPP_DL_NOTE,
			   "(this will be reported only once per input file)");
	      buffer->warned_cplusplus_comments = 1;
	    }
	  /* In C89/C94, C++ style comments are forbidden.  */
	  else if ((CPP_OPTION (pfile, lang) == CLK_STDC89
		    || CPP_OPTION (pfile, lang) == CLK_STDC94))
	    {
	      /* But don't be confused about valid code such as
	         - // immediately followed by *,
		 - // in a preprocessing directive,
		 - // in an #if 0 block.  */
	      if (buffer->cur[1] == '*'
		  || pfile->state.in_directive
		  || pfile->state.skipping)
		{
		  result->type = CPP_DIV;
		  break;
		}
	      else if (! buffer->warned_cplusplus_comments)
		{
		  if (cpp_error (pfile, CPP_DL_ERROR,
				 "C++ style comments are not allowed in "
				 "ISO C90"))
		    cpp_error (pfile, CPP_DL_NOTE,
			       "(this will be reported only once per input "
			       "file)");
		  buffer->warned_cplusplus_comments = 1;
		}
	    }
	  if (skip_line_comment (pfile) && CPP_OPTION (pfile, warn_comments))
	    cpp_warning (pfile, CPP_W_COMMENTS, "multi-line comment");
	}
      else if (c == '=')
	{
	  buffer->cur++;
	  result->type = CPP_DIV_EQ;
	  break;
	}
      else
	{
	  result->type = CPP_DIV;
	  break;
	}

      if (fallthrough_comment_p (pfile, comment_start))
	fallthrough_comment = true;

      if (pfile->cb.comment)
	{
	  size_t len = pfile->buffer->cur - comment_start;
	  pfile->cb.comment (pfile, result->src_loc, comment_start - 1,
			     len + 1);
	}

      if (!pfile->state.save_comments)
	{
	  result->flags |= PREV_WHITE;
	  goto update_tokens_line;
	}

      if (fallthrough_comment)
	result->flags |= PREV_FALLTHROUGH;

      /* Save the comment as a token in its own right.  */
      save_comment (pfile, result, comment_start, c);
      break;

    case '<':
      if (pfile->state.angled_headers)
	{
	  lex_string (pfile, result, buffer->cur - 1);
	  if (result->type != CPP_LESS)
	    break;
	}

      result->type = CPP_LESS;
      if (*buffer->cur == '=')
	{
	  buffer->cur++, result->type = CPP_LESS_EQ;
	  if (*buffer->cur == '>'
	      && CPP_OPTION (pfile, cplusplus)
	      && CPP_OPTION (pfile, lang) >= CLK_GNUCXX20)
	    buffer->cur++, result->type = CPP_SPACESHIP;
	}
      else if (*buffer->cur == '<')
	{
	  buffer->cur++;
	  IF_NEXT_IS ('=', CPP_LSHIFT_EQ, CPP_LSHIFT);
	}
      else if (CPP_OPTION (pfile, digraphs))
	{
	  if (*buffer->cur == ':')
	    {
	      /* C++11 [2.5/3 lex.pptoken], "Otherwise, if the next
		 three characters are <:: and the subsequent character
		 is neither : nor >, the < is treated as a preprocessor
		 token by itself".  */
	      if (CPP_OPTION (pfile, cplusplus)
		  && CPP_OPTION (pfile, lang) != CLK_CXX98
		  && CPP_OPTION (pfile, lang) != CLK_GNUCXX
		  && buffer->cur[1] == ':'
		  && buffer->cur[2] != ':' && buffer->cur[2] != '>')
		break;

	      buffer->cur++;
	      result->flags |= DIGRAPH;
	      result->type = CPP_OPEN_SQUARE;
	    }
	  else if (*buffer->cur == '%')
	    {
	      buffer->cur++;
	      result->flags |= DIGRAPH;
	      result->type = CPP_OPEN_BRACE;
	    }
	}
      break;

    case '>':
      result->type = CPP_GREATER;
      if (*buffer->cur == '=')
	buffer->cur++, result->type = CPP_GREATER_EQ;
      else if (*buffer->cur == '>')
	{
	  buffer->cur++;
	  IF_NEXT_IS ('=', CPP_RSHIFT_EQ, CPP_RSHIFT);
	}
      break;

    case '%':
      result->type = CPP_MOD;
      if (*buffer->cur == '=')
	buffer->cur++, result->type = CPP_MOD_EQ;
      else if (CPP_OPTION (pfile, digraphs))
	{
	  if (*buffer->cur == ':')
	    {
	      buffer->cur++;
	      result->flags |= DIGRAPH;
	      result->type = CPP_HASH;
	      if (*buffer->cur == '%' && buffer->cur[1] == ':')
		buffer->cur += 2, result->type = CPP_PASTE, result->val.token_no = 0;
	    }
	  else if (*buffer->cur == '>')
	    {
	      buffer->cur++;
	      result->flags |= DIGRAPH;
	      result->type = CPP_CLOSE_BRACE;
	    }
	}
      break;

    case '.':
      result->type = CPP_DOT;
      if (ISDIGIT (*buffer->cur))
	{
	  struct normalize_state nst = INITIAL_NORMALIZE_STATE;
	  result->type = CPP_NUMBER;
	  lex_number (pfile, &result->val.str, &nst);
	  warn_about_normalization (pfile, result, &nst, false);
	}
      else if (*buffer->cur == '.' && buffer->cur[1] == '.')
	buffer->cur += 2, result->type = CPP_ELLIPSIS;
      else if (*buffer->cur == '*' && CPP_OPTION (pfile, cplusplus))
	buffer->cur++, result->type = CPP_DOT_STAR;
      break;

    case '+':
      result->type = CPP_PLUS;
      if (*buffer->cur == '+')
	buffer->cur++, result->type = CPP_PLUS_PLUS;
      else if (*buffer->cur == '=')
	buffer->cur++, result->type = CPP_PLUS_EQ;
      break;

    case '-':
      result->type = CPP_MINUS;
      if (*buffer->cur == '>')
	{
	  buffer->cur++;
	  result->type = CPP_DEREF;
	  if (*buffer->cur == '*' && CPP_OPTION (pfile, cplusplus))
	    buffer->cur++, result->type = CPP_DEREF_STAR;
	}
      else if (*buffer->cur == '-')
	buffer->cur++, result->type = CPP_MINUS_MINUS;
      else if (*buffer->cur == '=')
	buffer->cur++, result->type = CPP_MINUS_EQ;
      break;

    case '&':
      result->type = CPP_AND;
      if (*buffer->cur == '&')
	buffer->cur++, result->type = CPP_AND_AND;
      else if (*buffer->cur == '=')
	buffer->cur++, result->type = CPP_AND_EQ;
      break;

    case '|':
      result->type = CPP_OR;
      if (*buffer->cur == '|')
	buffer->cur++, result->type = CPP_OR_OR;
      else if (*buffer->cur == '=')
	buffer->cur++, result->type = CPP_OR_EQ;
      break;

    case ':':
      result->type = CPP_COLON;
      if (*buffer->cur == ':' && CPP_OPTION (pfile, scope))
	buffer->cur++, result->type = CPP_SCOPE;
      else if (*buffer->cur == '>' && CPP_OPTION (pfile, digraphs))
	{
	  buffer->cur++;
	  result->flags |= DIGRAPH;
	  result->type = CPP_CLOSE_SQUARE;
	}
      break;

    case '*': IF_NEXT_IS ('=', CPP_MULT_EQ, CPP_MULT); break;
    case '=': IF_NEXT_IS ('=', CPP_EQ_EQ, CPP_EQ); break;
    case '!': IF_NEXT_IS ('=', CPP_NOT_EQ, CPP_NOT); break;
    case '^': IF_NEXT_IS ('=', CPP_XOR_EQ, CPP_XOR); break;
    case '#': IF_NEXT_IS ('#', CPP_PASTE, CPP_HASH); result->val.token_no = 0; break;

    case '?': result->type = CPP_QUERY; break;
    case '~': result->type = CPP_COMPL; break;
    case ',': result->type = CPP_COMMA; break;
    case '(': result->type = CPP_OPEN_PAREN; break;
    case ')': result->type = CPP_CLOSE_PAREN; break;
    case '[': result->type = CPP_OPEN_SQUARE; break;
    case ']': result->type = CPP_CLOSE_SQUARE; break;
    case '{': result->type = CPP_OPEN_BRACE; break;
    case '}': result->type = CPP_CLOSE_BRACE; break;
    case ';': result->type = CPP_SEMICOLON; break;

      /* @ is a punctuator in Objective-C.  */
    case '@': result->type = CPP_ATSIGN; break;

    default:
      {
	const uchar *base = --buffer->cur;
	static int no_warn_cnt;

	/* Check for an extended identifier ($ or UCN or UTF-8).  */
	struct normalize_state nst = INITIAL_NORMALIZE_STATE;
	if (forms_identifier_p (pfile, true, &nst))
	  {
	    result->type = CPP_NAME;
	    result->val.node.node = lex_identifier (pfile, base, true, &nst,
						    &result->val.node.spelling);
	    warn_about_normalization (pfile, result, &nst, true);
	    break;
	  }

	/* Otherwise this will form a CPP_OTHER token.  Parse valid UTF-8 as a
	   single token.  */
	buffer->cur++;
	if (c >= utf8_signifier)
	  {
	    const uchar *pstr = base;
	    cppchar_t s;
	    if (_cpp_valid_utf8 (pfile, &pstr, buffer->rlimit, 0, NULL, &s))
	      {
		if (s > UCS_LIMIT && CPP_OPTION (pfile, cpp_warn_invalid_utf8))
		  {
		    buffer->cur = base;
		    _cpp_warn_invalid_utf8 (pfile);
		  }
		buffer->cur = pstr;
	      }
	    else if (CPP_OPTION (pfile, cpp_warn_invalid_utf8))
	      {
		buffer->cur = base;
		const uchar *end = _cpp_warn_invalid_utf8 (pfile);
		buffer->cur = base + 1;
		no_warn_cnt = end - buffer->cur;
	      }
	  }
	else if (c >= utf8_continuation
		 && CPP_OPTION (pfile, cpp_warn_invalid_utf8))
	  {
	    if (no_warn_cnt)
	      --no_warn_cnt;
	    else
	      {
		buffer->cur = base;
		_cpp_warn_invalid_utf8 (pfile);
		buffer->cur = base + 1;
	      }
	  }
	create_literal (pfile, result, base, buffer->cur - base, CPP_OTHER);
	break;
      }

    }

  /* Potentially convert the location of the token to a range.  */
  if (result->src_loc >= RESERVED_LOCATION_COUNT
      && result->type != CPP_EOF)
    {
      /* Ensure that any line notes are processed, so that we have the
	 correct physical line/column for the end-point of the token even
	 when a logical line is split via one or more backslashes.  */
      if (buffer->cur >= buffer->notes[buffer->cur_note].pos
	  && !pfile->overlaid_buffer)
	_cpp_process_line_notes (pfile, false);

      source_range tok_range;
      tok_range.m_start = result->src_loc;
      tok_range.m_finish
	= linemap_position_for_column (pfile->line_table,
				       CPP_BUF_COLUMN (buffer, buffer->cur));

      result->src_loc = COMBINE_LOCATION_DATA (pfile->line_table,
					       result->src_loc,
					       tok_range, NULL, 0);
    }

  return result;
}

/* An upper bound on the number of bytes needed to spell TOKEN.
   Does not include preceding whitespace.  */
unsigned int
cpp_token_len (const cpp_token *token)
{
  unsigned int len;

  switch (TOKEN_SPELL (token))
    {
    default:		len = 6;				break;
    case SPELL_LITERAL:	len = token->val.str.len;		break;
    case SPELL_IDENT:	len = NODE_LEN (token->val.node.node) * 10;	break;
    }

  return len;
}

/* Parse UTF-8 out of NAMEP and place a \U escape in BUFFER.
   Return the number of bytes read out of NAME.  (There are always
   10 bytes written to BUFFER.)  */

static size_t
utf8_to_ucn (unsigned char *buffer, const unsigned char *name)
{
  int j;
  int ucn_len = 0;
  int ucn_len_c;
  unsigned t;
  unsigned long utf32;
  
  /* Compute the length of the UTF-8 sequence.  */
  for (t = *name; t & 0x80; t <<= 1)
    ucn_len++;
  
  utf32 = *name & (0x7F >> ucn_len);
  for (ucn_len_c = 1; ucn_len_c < ucn_len; ucn_len_c++)
    {
      utf32 = (utf32 << 6) | (*++name & 0x3F);
      
      /* Ill-formed UTF-8.  */
      if ((*name & ~0x3F) != 0x80)
	abort ();
    }
  
  *buffer++ = '\\';
  *buffer++ = 'U';
  for (j = 7; j >= 0; j--)
    *buffer++ = "0123456789abcdef"[(utf32 >> (4 * j)) & 0xF];
  return ucn_len;
}

/* Given a token TYPE corresponding to a digraph, return a pointer to
   the spelling of the digraph.  */
static const unsigned char *
cpp_digraph2name (enum cpp_ttype type)
{
  return digraph_spellings[(int) type - (int) CPP_FIRST_DIGRAPH];
}

/* Write the spelling of an identifier IDENT, using UCNs, to BUFFER.
   The buffer must already contain the enough space to hold the
   token's spelling.  Returns a pointer to the character after the
   last character written.  */
unsigned char *
_cpp_spell_ident_ucns (unsigned char *buffer, cpp_hashnode *ident)
{
  size_t i;
  const unsigned char *name = NODE_NAME (ident);
	  
  for (i = 0; i < NODE_LEN (ident); i++)
    if (name[i] & ~0x7F)
      {
	i += utf8_to_ucn (buffer, name + i) - 1;
	buffer += 10;
      }
    else
      *buffer++ = name[i];

  return buffer;
}

/* Write the spelling of a token TOKEN to BUFFER.  The buffer must
   already contain the enough space to hold the token's spelling.
   Returns a pointer to the character after the last character written.
   FORSTRING is true if this is to be the spelling after translation
   phase 1 (with the original spelling of extended identifiers), false
   if extended identifiers should always be written using UCNs (there is
   no option for always writing them in the internal UTF-8 form).
   FIXME: Would be nice if we didn't need the PFILE argument.  */
unsigned char *
cpp_spell_token (cpp_reader *pfile, const cpp_token *token,
		 unsigned char *buffer, bool forstring)
{
  switch (TOKEN_SPELL (token))
    {
    case SPELL_OPERATOR:
      {
	const unsigned char *spelling;
	unsigned char c;

	if (token->flags & DIGRAPH)
	  spelling = cpp_digraph2name (token->type);
	else if (token->flags & NAMED_OP)
	  goto spell_ident;
	else
	  spelling = TOKEN_NAME (token);

	while ((c = *spelling++) != '\0')
	  *buffer++ = c;
      }
      break;

    spell_ident:
    case SPELL_IDENT:
      if (forstring)
	{
	  memcpy (buffer, NODE_NAME (token->val.node.spelling),
		  NODE_LEN (token->val.node.spelling));
	  buffer += NODE_LEN (token->val.node.spelling);
	}
      else
	buffer = _cpp_spell_ident_ucns (buffer, token->val.node.node);
      break;

    case SPELL_LITERAL:
      memcpy (buffer, token->val.str.text, token->val.str.len);
      buffer += token->val.str.len;
      break;

    case SPELL_NONE:
      cpp_error (pfile, CPP_DL_ICE,
		 "unspellable token %s", TOKEN_NAME (token));
      break;
    }

  return buffer;
}

/* Returns TOKEN spelt as a null-terminated string.  The string is
   freed when the reader is destroyed.  Useful for diagnostics.  */
unsigned char *
cpp_token_as_text (cpp_reader *pfile, const cpp_token *token)
{ 
  unsigned int len = cpp_token_len (token) + 1;
  unsigned char *start = _cpp_unaligned_alloc (pfile, len), *end;

  end = cpp_spell_token (pfile, token, start, false);
  end[0] = '\0';

  return start;
}

/* Returns a pointer to a string which spells the token defined by
   TYPE and FLAGS.  Used by C front ends, which really should move to
   using cpp_token_as_text.  */
const char *
cpp_type2name (enum cpp_ttype type, unsigned char flags)
{
  if (flags & DIGRAPH)
    return (const char *) cpp_digraph2name (type);
  else if (flags & NAMED_OP)
    return cpp_named_operator2name (type);

  return (const char *) token_spellings[type].name;
}

/* Writes the spelling of token to FP, without any preceding space.
   Separated from cpp_spell_token for efficiency - to avoid stdio
   double-buffering.  */
void
cpp_output_token (const cpp_token *token, FILE *fp)
{
  switch (TOKEN_SPELL (token))
    {
    case SPELL_OPERATOR:
      {
	const unsigned char *spelling;
	int c;

	if (token->flags & DIGRAPH)
	  spelling = cpp_digraph2name (token->type);
	else if (token->flags & NAMED_OP)
	  goto spell_ident;
	else
	  spelling = TOKEN_NAME (token);

	c = *spelling;
	do
	  putc (c, fp);
	while ((c = *++spelling) != '\0');
      }
      break;

    spell_ident:
    case SPELL_IDENT:
      {
	size_t i;
	const unsigned char * name = NODE_NAME (token->val.node.node);
	
	for (i = 0; i < NODE_LEN (token->val.node.node); i++)
	  if (name[i] & ~0x7F)
	    {
	      unsigned char buffer[10];
	      i += utf8_to_ucn (buffer, name + i) - 1;
	      fwrite (buffer, 1, 10, fp);
	    }
	  else
	    fputc (NODE_NAME (token->val.node.node)[i], fp);
      }
      break;

    case SPELL_LITERAL:
      if (token->type == CPP_HEADER_NAME)
	fputc ('"', fp);
      fwrite (token->val.str.text, 1, token->val.str.len, fp);
      if (token->type == CPP_HEADER_NAME)
	fputc ('"', fp);
      break;

    case SPELL_NONE:
      /* An error, most probably.  */
      break;
    }
}

/* Compare two tokens.  */
int
_cpp_equiv_tokens (const cpp_token *a, const cpp_token *b)
{
  if (a->type == b->type && a->flags == b->flags)
    switch (TOKEN_SPELL (a))
      {
      default:			/* Keep compiler happy.  */
      case SPELL_OPERATOR:
	/* token_no is used to track where multiple consecutive ##
	   tokens were originally located.  */
	return (a->type != CPP_PASTE || a->val.token_no == b->val.token_no);
      case SPELL_NONE:
	return (a->type != CPP_MACRO_ARG
		|| (a->val.macro_arg.arg_no == b->val.macro_arg.arg_no
		    && a->val.macro_arg.spelling == b->val.macro_arg.spelling));
      case SPELL_IDENT:
	return (a->val.node.node == b->val.node.node
		&& a->val.node.spelling == b->val.node.spelling);
      case SPELL_LITERAL:
	return (a->val.str.len == b->val.str.len
		&& !memcmp (a->val.str.text, b->val.str.text,
			    a->val.str.len));
      }

  return 0;
}

/* Returns nonzero if a space should be inserted to avoid an
   accidental token paste for output.  For simplicity, it is
   conservative, and occasionally advises a space where one is not
   needed, e.g. "." and ".2".  */
int
cpp_avoid_paste (cpp_reader *pfile, const cpp_token *token1,
		 const cpp_token *token2)
{
  enum cpp_ttype a = token1->type, b = token2->type;
  cppchar_t c;

  if (token1->flags & NAMED_OP)
    a = CPP_NAME;
  if (token2->flags & NAMED_OP)
    b = CPP_NAME;

  c = EOF;
  if (token2->flags & DIGRAPH)
    c = digraph_spellings[(int) b - (int) CPP_FIRST_DIGRAPH][0];
  else if (token_spellings[b].category == SPELL_OPERATOR)
    c = token_spellings[b].name[0];

  /* Quickly get everything that can paste with an '='.  */
  if ((int) a <= (int) CPP_LAST_EQ && c == '=')
    return 1;

  switch (a)
    {
    case CPP_GREATER:	return c == '>';
    case CPP_LESS:	return c == '<' || c == '%' || c == ':';
    case CPP_PLUS:	return c == '+';
    case CPP_MINUS:	return c == '-' || c == '>';
    case CPP_DIV:	return c == '/' || c == '*'; /* Comments.  */
    case CPP_MOD:	return c == ':' || c == '>';
    case CPP_AND:	return c == '&';
    case CPP_OR:	return c == '|';
    case CPP_COLON:	return c == ':' || c == '>';
    case CPP_DEREF:	return c == '*';
    case CPP_DOT:	return c == '.' || c == '%' || b == CPP_NUMBER;
    case CPP_HASH:	return c == '#' || c == '%'; /* Digraph form.  */
    case CPP_PRAGMA:
    case CPP_NAME:	return ((b == CPP_NUMBER
				 && name_p (pfile, &token2->val.str))
				|| b == CPP_NAME
				|| b == CPP_CHAR || b == CPP_STRING); /* L */
    case CPP_NUMBER:	return (b == CPP_NUMBER || b == CPP_NAME
				|| b == CPP_CHAR
				|| c == '.' || c == '+' || c == '-');
				      /* UCNs */
    case CPP_OTHER:	return ((token1->val.str.text[0] == '\\'
				 && b == CPP_NAME)
				|| (CPP_OPTION (pfile, objc)
				    && token1->val.str.text[0] == '@'
				    && (b == CPP_NAME || b == CPP_STRING)));
    case CPP_LESS_EQ:	return c == '>';
    case CPP_STRING:
    case CPP_WSTRING:
    case CPP_UTF8STRING:
    case CPP_STRING16:
    case CPP_STRING32:	return (CPP_OPTION (pfile, user_literals)
				&& (b == CPP_NAME
				    || (TOKEN_SPELL (token2) == SPELL_LITERAL
					&& ISIDST (token2->val.str.text[0]))));

    default:		break;
    }

  return 0;
}

/* Output all the remaining tokens on the current line, and a newline
   character, to FP.  Leading whitespace is removed.  If there are
   macros, special token padding is not performed.  */
void
cpp_output_line (cpp_reader *pfile, FILE *fp)
{
  const cpp_token *token;

  token = cpp_get_token (pfile);
  while (token->type != CPP_EOF)
    {
      cpp_output_token (token, fp);
      token = cpp_get_token (pfile);
      if (token->flags & PREV_WHITE)
	putc (' ', fp);
    }

  putc ('\n', fp);
}

/* Return a string representation of all the remaining tokens on the
   current line.  The result is allocated using xmalloc and must be
   freed by the caller.  */
unsigned char *
cpp_output_line_to_string (cpp_reader *pfile, const unsigned char *dir_name)
{
  const cpp_token *token;
  unsigned int out = dir_name ? ustrlen (dir_name) : 0;
  unsigned int alloced = 120 + out;
  unsigned char *result = (unsigned char *) xmalloc (alloced);

  /* If DIR_NAME is empty, there are no initial contents.  */
  if (dir_name)
    {
      sprintf ((char *) result, "#%s ", dir_name);
      out += 2;
    }

  token = cpp_get_token (pfile);
  while (token->type != CPP_EOF)
    {
      unsigned char *last;
      /* Include room for a possible space and the terminating nul.  */
      unsigned int len = cpp_token_len (token) + 2;

      if (out + len > alloced)
	{
	  alloced *= 2;
	  if (out + len > alloced)
	    alloced = out + len;
	  result = (unsigned char *) xrealloc (result, alloced);
	}

      last = cpp_spell_token (pfile, token, &result[out], 0);
      out = last - result;

      token = cpp_get_token (pfile);
      if (token->flags & PREV_WHITE)
	result[out++] = ' ';
    }

  result[out] = '\0';
  return result;
}

/* Memory buffers.  Changing these three constants can have a dramatic
   effect on performance.  The values here are reasonable defaults,
   but might be tuned.  If you adjust them, be sure to test across a
   range of uses of cpplib, including heavy nested function-like macro
   expansion.  Also check the change in peak memory usage (NJAMD is a
   good tool for this).  */
#define MIN_BUFF_SIZE 8000
#define BUFF_SIZE_UPPER_BOUND(MIN_SIZE) (MIN_BUFF_SIZE + (MIN_SIZE) * 3 / 2)
#define EXTENDED_BUFF_SIZE(BUFF, MIN_EXTRA) \
	(MIN_EXTRA + ((BUFF)->limit - (BUFF)->cur) * 2)

#if MIN_BUFF_SIZE > BUFF_SIZE_UPPER_BOUND (0)
  #error BUFF_SIZE_UPPER_BOUND must be at least as large as MIN_BUFF_SIZE!
#endif

/* Create a new allocation buffer.  Place the control block at the end
   of the buffer, so that buffer overflows will cause immediate chaos.  */
static _cpp_buff *
new_buff (size_t len)
{
  _cpp_buff *result;
  unsigned char *base;

  if (len < MIN_BUFF_SIZE)
    len = MIN_BUFF_SIZE;
  len = CPP_ALIGN (len);

#ifdef ENABLE_VALGRIND_ANNOTATIONS
  /* Valgrind warns about uses of interior pointers, so put _cpp_buff
     struct first.  */
  size_t slen = CPP_ALIGN2 (sizeof (_cpp_buff), 2 * DEFAULT_ALIGNMENT);
  base = XNEWVEC (unsigned char, len + slen);
  result = (_cpp_buff *) base;
  base += slen;
#else
  base = XNEWVEC (unsigned char, len + sizeof (_cpp_buff));
  result = (_cpp_buff *) (base + len);
#endif
  result->base = base;
  result->cur = base;
  result->limit = base + len;
  result->next = NULL;
  return result;
}

/* Place a chain of unwanted allocation buffers on the free list.  */
void
_cpp_release_buff (cpp_reader *pfile, _cpp_buff *buff)
{
  _cpp_buff *end = buff;

  while (end->next)
    end = end->next;
  end->next = pfile->free_buffs;
  pfile->free_buffs = buff;
}

/* Return a free buffer of size at least MIN_SIZE.  */
_cpp_buff *
_cpp_get_buff (cpp_reader *pfile, size_t min_size)
{
  _cpp_buff *result, **p;

  for (p = &pfile->free_buffs;; p = &(*p)->next)
    {
      size_t size;

      if (*p == NULL)
	return new_buff (min_size);
      result = *p;
      size = result->limit - result->base;
      /* Return a buffer that's big enough, but don't waste one that's
         way too big.  */
      if (size >= min_size && size <= BUFF_SIZE_UPPER_BOUND (min_size))
	break;
    }

  *p = result->next;
  result->next = NULL;
  result->cur = result->base;
  return result;
}

/* Creates a new buffer with enough space to hold the uncommitted
   remaining bytes of BUFF, and at least MIN_EXTRA more bytes.  Copies
   the excess bytes to the new buffer.  Chains the new buffer after
   BUFF, and returns the new buffer.  */
_cpp_buff *
_cpp_append_extend_buff (cpp_reader *pfile, _cpp_buff *buff, size_t min_extra)
{
  size_t size = EXTENDED_BUFF_SIZE (buff, min_extra);
  _cpp_buff *new_buff = _cpp_get_buff (pfile, size);

  buff->next = new_buff;
  memcpy (new_buff->base, buff->cur, BUFF_ROOM (buff));
  return new_buff;
}

/* Creates a new buffer with enough space to hold the uncommitted
   remaining bytes of the buffer pointed to by BUFF, and at least
   MIN_EXTRA more bytes.  Copies the excess bytes to the new buffer.
   Chains the new buffer before the buffer pointed to by BUFF, and
   updates the pointer to point to the new buffer.  */
void
_cpp_extend_buff (cpp_reader *pfile, _cpp_buff **pbuff, size_t min_extra)
{
  _cpp_buff *new_buff, *old_buff = *pbuff;
  size_t size = EXTENDED_BUFF_SIZE (old_buff, min_extra);

  new_buff = _cpp_get_buff (pfile, size);
  memcpy (new_buff->base, old_buff->cur, BUFF_ROOM (old_buff));
  new_buff->next = old_buff;
  *pbuff = new_buff;
}

/* Free a chain of buffers starting at BUFF.  */
void
_cpp_free_buff (_cpp_buff *buff)
{
  _cpp_buff *next;

  for (; buff; buff = next)
    {
      next = buff->next;
#ifdef ENABLE_VALGRIND_ANNOTATIONS
      free (buff);
#else
      free (buff->base);
#endif
    }
}

/* Allocate permanent, unaligned storage of length LEN.  */
unsigned char *
_cpp_unaligned_alloc (cpp_reader *pfile, size_t len)
{
  _cpp_buff *buff = pfile->u_buff;
  unsigned char *result = buff->cur;

  if (len > (size_t) (buff->limit - result))
    {
      buff = _cpp_get_buff (pfile, len);
      buff->next = pfile->u_buff;
      pfile->u_buff = buff;
      result = buff->cur;
    }

  buff->cur = result + len;
  return result;
}

/* Allocate permanent, unaligned storage of length LEN from a_buff.
   That buffer is used for growing allocations when saving macro
   replacement lists in a #define, and when parsing an answer to an
   assertion in #assert, #unassert or #if (and therefore possibly
   whilst expanding macros).  It therefore must not be used by any
   code that they might call: specifically the lexer and the guts of
   the macro expander.

   All existing other uses clearly fit this restriction: storing
   registered pragmas during initialization.  */
unsigned char *
_cpp_aligned_alloc (cpp_reader *pfile, size_t len)
{
  _cpp_buff *buff = pfile->a_buff;
  unsigned char *result = buff->cur;

  if (len > (size_t) (buff->limit - result))
    {
      buff = _cpp_get_buff (pfile, len);
      buff->next = pfile->a_buff;
      pfile->a_buff = buff;
      result = buff->cur;
    }

  buff->cur = result + len;
  return result;
}

/* Commit or allocate storage from a buffer.  */

void *
_cpp_commit_buff (cpp_reader *pfile, size_t size)
{
  void *ptr = BUFF_FRONT (pfile->a_buff);

  if (pfile->hash_table->alloc_subobject)
    {
      void *copy = pfile->hash_table->alloc_subobject (size);
      memcpy (copy, ptr, size);
      ptr = copy;
    }
  else
    BUFF_FRONT (pfile->a_buff) += size;

  return ptr;
}

/* Say which field of TOK is in use.  */

enum cpp_token_fld_kind
cpp_token_val_index (const cpp_token *tok)
{
  switch (TOKEN_SPELL (tok))
    {
    case SPELL_IDENT:
      return CPP_TOKEN_FLD_NODE;
    case SPELL_LITERAL:
      return CPP_TOKEN_FLD_STR;
    case SPELL_OPERATOR:
      /* Operands which were originally spelled as ident keep around
         the node for the exact spelling.  */
      if (tok->flags & NAMED_OP)
	return CPP_TOKEN_FLD_NODE;
      else if (tok->type == CPP_PASTE)
	return CPP_TOKEN_FLD_TOKEN_NO;
      else
	return CPP_TOKEN_FLD_NONE;
    case SPELL_NONE:
      if (tok->type == CPP_MACRO_ARG)
	return CPP_TOKEN_FLD_ARG_NO;
      else if (tok->type == CPP_PADDING)
	return CPP_TOKEN_FLD_SOURCE;
      else if (tok->type == CPP_PRAGMA)
	return CPP_TOKEN_FLD_PRAGMA;
      /* fall through */
    default:
      return CPP_TOKEN_FLD_NONE;
    }
}

/* All tokens lexed in R after calling this function will be forced to
   have their location_t to be P, until
   cpp_stop_forcing_token_locations is called for R.  */

void
cpp_force_token_locations (cpp_reader *r, location_t loc)
{
  r->forced_token_location = loc;
}

/* Go back to assigning locations naturally for lexed tokens.  */

void
cpp_stop_forcing_token_locations (cpp_reader *r)
{
  r->forced_token_location = 0;
}

/* We're looking at \, if it's escaping EOL, look past it.  If at
   LIMIT, don't advance.  */

static const unsigned char *
do_peek_backslash (const unsigned char *peek, const unsigned char *limit)
{
  const unsigned char *probe = peek;

  if (__builtin_expect (peek[1] == '\n', true))
    {
    eol:
      probe += 2;
      if (__builtin_expect (probe < limit, true))
	{
	  peek = probe;
	  if (*peek == '\\')
	    /* The user might be perverse.  */
	    return do_peek_backslash (peek, limit);
	}
    }
  else if (__builtin_expect (peek[1] == '\r', false))
    {
      if (probe[2] == '\n')
	probe++;
      goto eol;
    }

  return peek;
}

static const unsigned char *
do_peek_next (const unsigned char *peek, const unsigned char *limit)
{
  if (__builtin_expect (*peek == '\\', false))
    peek = do_peek_backslash (peek, limit);
  return peek;
}

static const unsigned char *
do_peek_prev (const unsigned char *peek, const unsigned char *bound)
{
  if (peek == bound)
    return NULL;

  unsigned char c = *--peek;
  if (__builtin_expect (c == '\n', false)
      || __builtin_expect (c == 'r', false))
    {
      if (peek == bound)
	return peek;
      int ix = -1;
      if (c == '\n' && peek[ix] == '\r')
	{
	  if (peek + ix == bound)
	    return peek;
	  ix--;
	}

      if (peek[ix] == '\\')
	return do_peek_prev (peek + ix, bound);

      return peek;
    }
  else
    return peek;
}

/* If PEEK[-1] is identifier MATCH, scan past it and trailing white
   space.  Otherwise return NULL.  */

static const unsigned char *
do_peek_ident (const char *match, const unsigned char *peek,
	       const unsigned char *limit)
{
  for (; *++match; peek++)
    if (*peek != *match)
      {
	peek = do_peek_next (peek, limit);
	if (*peek != *match)
	  return NULL;
      }

  /* Must now not be looking at an identifier char.  */
  peek = do_peek_next (peek, limit);
  if (ISIDNUM (*peek))
    return NULL;

  /* Skip control-line whitespace.  */
 ws:
  while (*peek == ' ' || *peek == '\t')
    peek++;
  if (__builtin_expect (*peek == '\\', false))
    {
      peek = do_peek_backslash (peek, limit);
      if (*peek != '\\')
	goto ws;
    }

  return peek;
}

/* Are we looking at a module control line starting as PEEK - 1?  */

static bool
do_peek_module (cpp_reader *pfile, unsigned char c,
		const unsigned char *peek, const unsigned char *limit)
{
  bool import = false;

  if (__builtin_expect (c == 'e', false))
    {
      if (!((peek[0] == 'x' || peek[0] == '\\')
	    && (peek = do_peek_ident ("export", peek, limit))))
	return false;

      /* export, peek for import or module.  No need to peek __import
	 here.  */
      if (peek[0] == 'i')
	{
	  if (!((peek[1] == 'm' || peek[1] == '\\')
		&& (peek = do_peek_ident ("import", peek + 1, limit))))
	    return false;
	  import = true;
	}
      else if (peek[0] == 'm')
	{
	  if (!((peek[1] == 'o' || peek[1] == '\\')
		&& (peek = do_peek_ident ("module", peek + 1, limit))))
	    return false;
	}
      else
	return false;
    }
  else if (__builtin_expect (c == 'i', false))
    {
      if (!((peek[0] == 'm' || peek[0] == '\\')
	    && (peek = do_peek_ident ("import", peek, limit))))
	return false;
      import = true;
    }
  else if (__builtin_expect (c == '_', false))
    {
      /* Needed for translated includes.   */
      if (!((peek[0] == '_' || peek[0] == '\\')
	    && (peek = do_peek_ident ("__import", peek, limit))))
	return false;
      import = true;
    }
  else if (__builtin_expect (c == 'm', false))
    {
      if (!((peek[0] == 'o' || peek[0] == '\\')
	    && (peek = do_peek_ident ("module", peek, limit))))
	return false;
    }
  else
    return false;

  /* Peek the next character to see if it's good enough.  We'll be at
     the first non-whitespace char, including skipping an escaped
     newline.  */
  /* ... import followed by identifier, ':', '<' or header-name
     preprocessing tokens, or module followed by identifier, ':' or
     ';' preprocessing tokens.  */
  unsigned char p = *peek++;
      
  /* A character literal is ... single quotes, ... optionally preceded
     by u8, u, U, or L */
  /* A string-literal is a ... double quotes, optionally prefixed by
     R, u8, u8R, u, uR, U, UR, L, or LR */
  if (p == 'u')
    {
      peek = do_peek_next (peek, limit);
      if (*peek == '8')
	{
	  peek++;
	  goto peek_u8;
	}
      goto peek_u;
    }
  else if (p == 'U' || p == 'L')
    {
    peek_u8:
      peek = do_peek_next (peek, limit);
    peek_u:
      if (*peek == '\"' || *peek == '\'')
	return false;

      if (*peek == 'R')
	goto peek_R;
      /* Identifier. Ok.  */
    }
  else if (p == 'R')
    {
    peek_R:
      if (CPP_OPTION (pfile, rliterals))
	{
	  peek = do_peek_next (peek, limit);
	  if (*peek == '\"')
	    return false;
	}
      /* Identifier. Ok.  */
    }
  else if ('Z' - 'A' == 25
	   ? ((p >= 'A' && p <= 'Z') || (p >= 'a' && p <= 'z') || p == '_')
	   : ISIDST (p))
    {
      /* Identifier.  Ok. */
    }
  else if (p == '<')
    {
      /* Maybe angle header, ok for import.  Reject
	 '<=', '<<' digraph:'<:'.  */
      if (!import)
	return false;
      peek = do_peek_next (peek, limit);
      if (*peek == '=' || *peek == '<'
	  || (*peek == ':' && CPP_OPTION (pfile, digraphs)))
	return false;
    }
  else if (p == ';')
    {
      /* SEMICOLON, ok for module.  */
      if (import)
	return false;
    }
  else if (p == '"')
    {
      /* STRING, ok for import.  */
      if (!import)
	return false;
    }
  else if (p == ':')
    {
      /* Maybe COLON, ok.  Reject '::', digraph:':>'.  */
      peek = do_peek_next (peek, limit);
      if (*peek == ':' || (*peek == '>' && CPP_OPTION (pfile, digraphs)))
	return false;
    }
  else
    /* FIXME: Detect a unicode character, excluding those not
       permitted as the initial character. [lex.name]/1.  I presume
       we need to check the \[uU] spellings, and directly using
       Unicode in say UTF8 form?  Or perhaps we do the phase-1
       conversion of UTF8 to universal-character-names?  */
    return false;

  return true;
}

/* Directives-only scanning.  Somewhat more relaxed than correct
   parsing -- some ill-formed programs will not be rejected.  */

void
cpp_directive_only_process (cpp_reader *pfile,
			    void *data,
			    void (*cb) (cpp_reader *, CPP_DO_task, void *, ...))
{
  bool module_p = CPP_OPTION (pfile, module_directives);

  do
    {
    restart:
      /* Buffer initialization, but no line cleaning. */
      cpp_buffer *buffer = pfile->buffer;
      buffer->cur_note = buffer->notes_used = 0;
      buffer->cur = buffer->line_base = buffer->next_line;
      buffer->need_line = false;
      /* Files always end in a newline or carriage return.  We rely on this for
	 character peeking safety.  */
      gcc_assert (buffer->rlimit[0] == '\n' || buffer->rlimit[0] == '\r');

      const unsigned char *base = buffer->cur;
      unsigned line_count = 0;
      const unsigned char *line_start = base;

      bool bol = true;
      bool raw = false;

      const unsigned char *lwm = base;
      for (const unsigned char *pos = base, *limit = buffer->rlimit;
	   pos < limit;)
	{
	  unsigned char c = *pos++;
	  /* This matches the switch in _cpp_lex_direct.  */
	  switch (c)
	    {
	    case ' ': case '\t': case '\f': case '\v':
	      /* Whitespace, do nothing.  */
	      break;

	    case '\r': /* MAC line ending, or Windows \r\n  */
	      if (*pos == '\n')
		pos++;
	      /* FALLTHROUGH */

	    case '\n':
	      bol = true;

	    next_line:
	      CPP_INCREMENT_LINE (pfile, 0);
	      line_count++;
	      line_start = pos;
	      break;

	    case '\\':
	      /* <backslash><newline> is removed, and doesn't undo any
		 preceeding escape or whatnot.  */
	      if (*pos == '\n')
		{
		  pos++;
		  goto next_line;
		}
	      else if (*pos == '\r')
		{
		  if (pos[1] == '\n')
		    pos++;
		  pos++;
		  goto next_line;
		}
	      goto dflt;
	      
	    case '#':
	      if (bol)
		{
		  /* Line directive.  */
		  if (pos - 1 > base && !pfile->state.skipping)
		    cb (pfile, CPP_DO_print, data,
			line_count, base, pos - 1 - base);

		  /* Prep things for directive handling. */
		  buffer->next_line = pos;
		  buffer->need_line = true;
		  bool ok = _cpp_get_fresh_line (pfile);
		  gcc_checking_assert (ok);

		  /* Ensure proper column numbering for generated
		     error messages. */
		  buffer->line_base -= pos - line_start;

		  _cpp_handle_directive (pfile, line_start + 1 != pos);

		  /* Sanitize the line settings.  Duplicate #include's can
		     mess things up. */
		  // FIXME: Necessary?
		  pfile->line_table->highest_location
		    = pfile->line_table->highest_line;

		  if (!pfile->state.skipping
		      && pfile->buffer->next_line < pfile->buffer->rlimit)
		    cb (pfile, CPP_DO_location, data,
			pfile->line_table->highest_line);

		  goto restart;
		}
	      goto dflt;

	    case '/':
	      {
		const unsigned char *peek = do_peek_next (pos, limit);
		if (!(*peek == '/' || *peek == '*'))
		  goto dflt;

		/* Line or block comment  */
		bool is_block = *peek == '*';
		bool star = false;
		bool esc = false;
		location_t sloc
		  = linemap_position_for_column (pfile->line_table,
						 pos - line_start);

		while (pos < limit)
		  {
		    char c = *pos++;
		    switch (c)
		      {
		      case '\\':
			esc = true;
			break;

		      case '\r':
			if (*pos == '\n')
			  pos++;
			/* FALLTHROUGH  */

		      case '\n':
			{
			  CPP_INCREMENT_LINE (pfile, 0);
			  line_count++;
			  line_start = pos;
			  if (!esc && !is_block)
			    {
			      bol = true;
			      goto done_comment;
			    }
			}
			if (!esc)
			  star = false;
			esc = false;
			break;

		      case '*':
			if (pos > peek)
			  star = is_block;
			esc = false;
			break;

		      case '/':
			if (star)
			  goto done_comment;
			/* FALLTHROUGH  */

		      default:
			star = false;
			esc = false;
			break;
		      }
		  }
		if (pos < limit || is_block)
		  cpp_error_with_line (pfile, CPP_DL_ERROR, sloc, 0,
				       "unterminated comment");
	      done_comment:
		lwm = pos;
		break;
	      }

	    case '\'':
	      if (!CPP_OPTION (pfile, digit_separators))
		goto delimited_string;

	      /* Possibly a number punctuator.  */
	      if (!ISIDNUM (*do_peek_next (pos, limit)))
		goto delimited_string;

	      goto quote_peek;

	    case '\"':
	      if (!CPP_OPTION (pfile, rliterals))
		goto delimited_string;

	    quote_peek:
	      {
		/* For ' see if it's a number punctuator
		   \.?<digit>(<digit>|<identifier-nondigit>
		   |'<digit>|'<nondigit>|[eEpP]<sign>|\.)* */
		/* For " see if it's a raw string
		   {U,L,u,u8}R.  This includes CPP_NUMBER detection,
		   because that could be 0e+R.  */
		const unsigned char *peek = pos - 1;
		bool quote_first = c == '"';
		bool quote_eight = false;
		bool maybe_number_start = false;
		bool want_number = false;

		while ((peek = do_peek_prev (peek, lwm)))
		  {
		    unsigned char p = *peek;
		    if (quote_first)
		      {
			if (!raw)
			  {
			    if (p != 'R')
			      break;
			    raw = true;
			    continue;
			  }

			quote_first = false;
			if (p == 'L' || p == 'U' || p == 'u')
			  ;
			else if (p == '8')
			  quote_eight = true;
			else
			  goto second_raw;
		      }
		    else if (quote_eight)
		      {
			if (p != 'u')
			  {
			    raw = false;
			    break;
			  }
			quote_eight = false;
		      }
		    else if (c == '"')
		      {
		      second_raw:;
			if (!want_number && ISIDNUM (p))
			  {
			    raw = false;
			    break;
			  }
		      }

		    if (ISDIGIT (p))
		      maybe_number_start = true;
		    else if (p == '.')
		      want_number = true;
		    else if (ISIDNUM (p))
		      maybe_number_start = false;
		    else if (p == '+' || p == '-')
		      {
			if (const unsigned char *peek_prev
			    = do_peek_prev (peek, lwm))
			  {
			    p = *peek_prev;
			    if (p == 'e' || p == 'E'
				|| p == 'p' || p == 'P')
			      {
				want_number = true;
				maybe_number_start = false;
			      }
			    else
			      break;
			  }
			else
			  break;
		      }
		    else if (p == '\'' || p == '\"')
		      {
			/* If this is lwm, this must be the end of a
			   previous string.  So this is a trailing
			   literal type, (a) if those are allowed,
			     and (b) maybe_start is false.  Otherwise
			     this must be a CPP_NUMBER because we've
			     met another ', and we'd have checked that
			     in its own right.  */
			if (peek == lwm && CPP_OPTION (pfile, uliterals))
			  {
			    if  (!maybe_number_start && !want_number)
			      /* Must be a literal type.  */
			      raw = false;
			  }
			else if (p == '\''
				 && CPP_OPTION (pfile, digit_separators))
			  maybe_number_start = true;
			break;
		      }
		    else if (c == '\'')
		      break;
		    else if (!quote_first && !quote_eight)
		      break;
		  }

		if (maybe_number_start)
		  {
		    if (c == '\'')
		      /* A CPP NUMBER.  */
		      goto dflt;
		    raw = false;
		  }

		goto delimited_string;
	      }

	    delimited_string:
	      {
		/* (Possibly raw) string or char literal.  */
		unsigned char end = c;
		int delim_len = -1;
		const unsigned char *delim = NULL;
		location_t sloc = linemap_position_for_column (pfile->line_table,
							       pos - line_start);
		int esc = 0;

		if (raw)
		  {
		    /* There can be no line breaks in the delimiter.  */
		    delim = pos;
		    for (delim_len = 0; (c = *pos++) != '('; delim_len++)
		      {
			if (delim_len == 16)
			  {
			    cpp_error_with_line (pfile, CPP_DL_ERROR,
						 sloc, 0,
						 "raw string delimiter"
						 " longer than %d"
						 " characters",
						 delim_len);
			    raw = false;
			    pos = delim;
			    break;
			  }
			if (strchr (") \\\t\v\f\n", c))
			  {
			    cpp_error_with_line (pfile, CPP_DL_ERROR,
						 sloc, 0,
						 "invalid character '%c'"
						 " in raw string"
						 " delimiter", c);
			    raw = false;
			    pos = delim;
			    break;
			  }
			if (pos >= limit)
			  goto bad_string;
		      }
		  }

		while (pos < limit)
		  {
		    char c = *pos++;
		    switch (c)
		      {
		      case '\\':
			if (!raw)
			  esc++;
			break;

		      case '\r':
			if (*pos == '\n')
			  pos++;
			/* FALLTHROUGH  */

		      case '\n':
			{
			  CPP_INCREMENT_LINE (pfile, 0);
			  line_count++;
			  line_start = pos;
			}
			if (esc)
			  esc--;
			break;

		      case ')':
			if (raw
			    && pos + delim_len + 1 < limit
			    && pos[delim_len] == end
			    && !memcmp (delim, pos, delim_len))
			  {
			    pos += delim_len + 1;
			    raw = false;
			    goto done_string;
			  }
			break;

		      default:
			if (!raw && !(esc & 1) && c == end)
			  goto done_string;
			esc = 0;
			break;
		      }
		  }
	      bad_string:
		cpp_error_with_line (pfile, CPP_DL_ERROR, sloc, 0,
				     "unterminated literal");
		
	      done_string:
		raw = false;
		lwm = pos - 1;
	      }
	      goto dflt;

	    case '_':
	    case 'e':
	    case 'i':
	    case 'm':
	      if (bol && module_p && !pfile->state.skipping
		  && do_peek_module (pfile, c, pos, limit))
		{
		  /* We've seen the start of a module control line.
		     Start up the tokenizer.  */
		  pos--; /* Backup over the first character.  */

		  /* Backup over whitespace to start of line.  */
		  while (pos > line_start
			 && (pos[-1] == ' ' || pos[-1] == '\t'))
		    pos--;

		  if (pos > base)
		    cb (pfile, CPP_DO_print, data, line_count, base, pos - base);

		  /* Prep things for directive handling. */
		  buffer->next_line = pos;
		  buffer->need_line = true;

		  /* Now get tokens until the PRAGMA_EOL.  */
		  do
		    {
		      location_t spelling;
		      const cpp_token *tok
			= cpp_get_token_with_location (pfile, &spelling);

		      gcc_assert (pfile->state.in_deferred_pragma
				  || tok->type == CPP_PRAGMA_EOL);
		      cb (pfile, CPP_DO_token, data, tok, spelling);
		    }
		  while (pfile->state.in_deferred_pragma);

		  if (pfile->buffer->next_line < pfile->buffer->rlimit)
		    cb (pfile, CPP_DO_location, data,
			pfile->line_table->highest_line);

		  pfile->mi_valid = false;
		  goto restart;
		}
	      goto dflt;

	    default:
	    dflt:
	      bol = false;
	      pfile->mi_valid = false;
	      break;
	    }
	}

      if (buffer->rlimit > base && !pfile->state.skipping)
	{
	  const unsigned char *limit = buffer->rlimit;
	  /* If the file was not newline terminated, add rlimit, which is
	     guaranteed to point to a newline, to the end of our range.  */
	  if (limit[-1] != '\n')
	    {
	      limit++;
	      CPP_INCREMENT_LINE (pfile, 0);
	      line_count++;
	    }
	  cb (pfile, CPP_DO_print, data, line_count, base, limit - base);
	}

      _cpp_pop_buffer (pfile);
    }
  while (pfile->buffer);
}