aboutsummaryrefslogtreecommitdiff
path: root/gcc/input.c
blob: 8fe5d4282c6f4f62a561e1f97fed68c1754aae05 (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
/* Data and functions related to line maps and input files.
   Copyright (C) 2004-2020 Free Software Foundation, Inc.

This file is part of GCC.

GCC 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.

GCC 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 GCC; see the file COPYING3.  If not see
<http://www.gnu.org/licenses/>.  */

#include "config.h"
#include "system.h"
#include "coretypes.h"
#include "intl.h"
#include "diagnostic.h"
#include "diagnostic-core.h"
#include "selftest.h"
#include "cpplib.h"

#ifndef HAVE_ICONV
#define HAVE_ICONV 0
#endif

/* This is a cache used by get_next_line to store the content of a
   file to be searched for file lines.  */
class fcache
{
public:
  /* These are information used to store a line boundary.  */
  class line_info
  {
  public:
    /* The line number.  It starts from 1.  */
    size_t line_num;

    /* The position (byte count) of the beginning of the line,
       relative to the file data pointer.  This starts at zero.  */
    size_t start_pos;

    /* The position (byte count) of the last byte of the line.  This
       normally points to the '\n' character, or to one byte after the
       last byte of the file, if the file doesn't contain a '\n'
       character.  */
    size_t end_pos;

    line_info (size_t l, size_t s, size_t e)
      : line_num (l), start_pos (s), end_pos (e)
    {}

    line_info ()
      :line_num (0), start_pos (0), end_pos (0)
    {}
  };

  /* The number of time this file has been accessed.  This is used
     to designate which file cache to evict from the cache
     array.  */
  unsigned use_count;

  /* The file_path is the key for identifying a particular file in
     the cache.
     For libcpp-using code, the underlying buffer for this field is
     owned by the corresponding _cpp_file within the cpp_reader.  */
  const char *file_path;

  FILE *fp;

  /* This points to the content of the file that we've read so
     far.  */
  char *data;

  /*  The size of the DATA array above.*/
  size_t size;

  /* The number of bytes read from the underlying file so far.  This
     must be less (or equal) than SIZE above.  */
  size_t nb_read;

  /* The index of the beginning of the current line.  */
  size_t line_start_idx;

  /* The number of the previous line read.  This starts at 1.  Zero
     means we've read no line so far.  */
  size_t line_num;

  /* This is the total number of lines of the current file.  At the
     moment, we try to get this information from the line map
     subsystem.  Note that this is just a hint.  When using the C++
     front-end, this hint is correct because the input file is then
     completely tokenized before parsing starts; so the line map knows
     the number of lines before compilation really starts.  For e.g,
     the C front-end, it can happen that we start emitting diagnostics
     before the line map has seen the end of the file.  */
  size_t total_lines;

  /* Could this file be missing a trailing newline on its final line?
     Initially true (to cope with empty files), set to true/false
     as each line is read.  */
  bool missing_trailing_newline;

  /* This is a record of the beginning and end of the lines we've seen
     while reading the file.  This is useful to avoid walking the data
     from the beginning when we are asked to read a line that is
     before LINE_START_IDX above.  Note that the maximum size of this
     record is fcache_line_record_size, so that the memory consumption
     doesn't explode.  We thus scale total_lines down to
     fcache_line_record_size.  */
  vec<line_info, va_heap> line_record;

  fcache ();
  ~fcache ();
};

/* Current position in real source file.  */

location_t input_location = UNKNOWN_LOCATION;

class line_maps *line_table;

/* A stashed copy of "line_table" for use by selftest::line_table_test.
   This needs to be a global so that it can be a GC root, and thus
   prevent the stashed copy from being garbage-collected if the GC runs
   during a line_table_test.  */

class line_maps *saved_line_table;

static fcache *fcache_tab;
static const size_t fcache_tab_size = 16;
static const size_t fcache_buffer_size = 4 * 1024;
static const size_t fcache_line_record_size = 100;

/* Expand the source location LOC into a human readable location.  If
   LOC resolves to a builtin location, the file name of the readable
   location is set to the string "<built-in>". If EXPANSION_POINT_P is
   TRUE and LOC is virtual, then it is resolved to the expansion
   point of the involved macro.  Otherwise, it is resolved to the
   spelling location of the token.

   When resolving to the spelling location of the token, if the
   resulting location is for a built-in location (that is, it has no
   associated line/column) in the context of a macro expansion, the
   returned location is the first one (while unwinding the macro
   location towards its expansion point) that is in real source
   code.

   ASPECT controls which part of the location to use.  */

static expanded_location
expand_location_1 (location_t loc,
		   bool expansion_point_p,
		   enum location_aspect aspect)
{
  expanded_location xloc;
  const line_map_ordinary *map;
  enum location_resolution_kind lrk = LRK_MACRO_EXPANSION_POINT;
  tree block = NULL;

  if (IS_ADHOC_LOC (loc))
    {
      block = LOCATION_BLOCK (loc);
      loc = LOCATION_LOCUS (loc);
    }

  memset (&xloc, 0, sizeof (xloc));

  if (loc >= RESERVED_LOCATION_COUNT)
    {
      if (!expansion_point_p)
	{
	  /* We want to resolve LOC to its spelling location.

	     But if that spelling location is a reserved location that
	     appears in the context of a macro expansion (like for a
	     location for a built-in token), let's consider the first
	     location (toward the expansion point) that is not reserved;
	     that is, the first location that is in real source code.  */
	  loc = linemap_unwind_to_first_non_reserved_loc (line_table,
							  loc, NULL);
	  lrk = LRK_SPELLING_LOCATION;
	}
      loc = linemap_resolve_location (line_table, loc, lrk, &map);

      /* loc is now either in an ordinary map, or is a reserved location.
	 If it is a compound location, the caret is in a spelling location,
	 but the start/finish might still be a virtual location.
	 Depending of what the caller asked for, we may need to recurse
	 one level in order to resolve any virtual locations in the
	 end-points.  */
      switch (aspect)
	{
	default:
	  gcc_unreachable ();
	  /* Fall through.  */
	case LOCATION_ASPECT_CARET:
	  break;
	case LOCATION_ASPECT_START:
	  {
	    location_t start = get_start (loc);
	    if (start != loc)
	      return expand_location_1 (start, expansion_point_p, aspect);
	  }
	  break;
	case LOCATION_ASPECT_FINISH:
	  {
	    location_t finish = get_finish (loc);
	    if (finish != loc)
	      return expand_location_1 (finish, expansion_point_p, aspect);
	  }
	  break;
	}
      xloc = linemap_expand_location (line_table, map, loc);
    }

  xloc.data = block;
  if (loc <= BUILTINS_LOCATION)
    xloc.file = loc == UNKNOWN_LOCATION ? NULL : _("<built-in>");

  return xloc;
}

/* Initialize the set of cache used for files accessed by caret
   diagnostic.  */

static void
diagnostic_file_cache_init (void)
{
  if (fcache_tab == NULL)
    fcache_tab = new fcache[fcache_tab_size];
}

/* Free the resources used by the set of cache used for files accessed
   by caret diagnostic.  */

void
diagnostic_file_cache_fini (void)
{
  if (fcache_tab)
    {
      delete [] (fcache_tab);
      fcache_tab = NULL;
    }
}

/* Return the total lines number that have been read so far by the
   line map (in the preprocessor) so far.  For languages like C++ that
   entirely preprocess the input file before starting to parse, this
   equals the actual number of lines of the file.  */

static size_t
total_lines_num (const char *file_path)
{
  size_t r = 0;
  location_t l = 0;
  if (linemap_get_file_highest_location (line_table, file_path, &l))
    {
      gcc_assert (l >= RESERVED_LOCATION_COUNT);
      expanded_location xloc = expand_location (l);
      r = xloc.line;
    }
  return r;
}

/* Lookup the cache used for the content of a given file accessed by
   caret diagnostic.  Return the found cached file, or NULL if no
   cached file was found.  */

static fcache*
lookup_file_in_cache_tab (const char *file_path)
{
  if (file_path == NULL)
    return NULL;

  diagnostic_file_cache_init ();

  /* This will contain the found cached file.  */
  fcache *r = NULL;
  for (unsigned i = 0; i < fcache_tab_size; ++i)
    {
      fcache *c = &fcache_tab[i];
      if (c->file_path && !strcmp (c->file_path, file_path))
	{
	  ++c->use_count;
	  r = c;
	}
    }

  if (r)
    ++r->use_count;

  return r;
}

/* Purge any mention of FILENAME from the cache of files used for
   printing source code.  For use in selftests when working
   with tempfiles.  */

void
diagnostics_file_cache_forcibly_evict_file (const char *file_path)
{
  gcc_assert (file_path);

  fcache *r = lookup_file_in_cache_tab (file_path);
  if (!r)
    /* Not found.  */
    return;

  r->file_path = NULL;
  if (r->fp)
    fclose (r->fp);
  r->fp = NULL;
  r->nb_read = 0;
  r->line_start_idx = 0;
  r->line_num = 0;
  r->line_record.truncate (0);
  r->use_count = 0;
  r->total_lines = 0;
  r->missing_trailing_newline = true;
}

/* Return the file cache that has been less used, recently, or the
   first empty one.  If HIGHEST_USE_COUNT is non-null,
   *HIGHEST_USE_COUNT is set to the highest use count of the entries
   in the cache table.  */

static fcache*
evicted_cache_tab_entry (unsigned *highest_use_count)
{
  diagnostic_file_cache_init ();

  fcache *to_evict = &fcache_tab[0];
  unsigned huc = to_evict->use_count;
  for (unsigned i = 1; i < fcache_tab_size; ++i)
    {
      fcache *c = &fcache_tab[i];
      bool c_is_empty = (c->file_path == NULL);

      if (c->use_count < to_evict->use_count
	  || (to_evict->file_path && c_is_empty))
	/* We evict C because it's either an entry with a lower use
	   count or one that is empty.  */
	to_evict = c;

      if (huc < c->use_count)
	huc = c->use_count;

      if (c_is_empty)
	/* We've reached the end of the cache; subsequent elements are
	   all empty.  */
	break;
    }

  if (highest_use_count)
    *highest_use_count = huc;

  return to_evict;
}

/* Create the cache used for the content of a given file to be
   accessed by caret diagnostic.  This cache is added to an array of
   cache and can be retrieved by lookup_file_in_cache_tab.  This
   function returns the created cache.  Note that only the last
   fcache_tab_size files are cached.  */

static fcache*
add_file_to_cache_tab (const char *file_path)
{

  FILE *fp = fopen (file_path, "r");
  if (fp == NULL)
    return NULL;

  unsigned highest_use_count = 0;
  fcache *r = evicted_cache_tab_entry (&highest_use_count);
  r->file_path = file_path;
  if (r->fp)
    fclose (r->fp);
  r->fp = fp;
  r->nb_read = 0;
  r->line_start_idx = 0;
  r->line_num = 0;
  r->line_record.truncate (0);
  /* Ensure that this cache entry doesn't get evicted next time
     add_file_to_cache_tab is called.  */
  r->use_count = ++highest_use_count;
  r->total_lines = total_lines_num (file_path);
  r->missing_trailing_newline = true;

  return r;
}

/* Lookup the cache used for the content of a given file accessed by
   caret diagnostic.  If no cached file was found, create a new cache
   for this file, add it to the array of cached file and return
   it.  */

static fcache*
lookup_or_add_file_to_cache_tab (const char *file_path)
{
  fcache *r = lookup_file_in_cache_tab (file_path);
  if (r == NULL)
    r = add_file_to_cache_tab (file_path);
  return r;
}

/* Default constructor for a cache of file used by caret
   diagnostic.  */

fcache::fcache ()
: use_count (0), file_path (NULL), fp (NULL), data (0),
  size (0), nb_read (0), line_start_idx (0), line_num (0),
  total_lines (0), missing_trailing_newline (true)
{
  line_record.create (0);
}

/* Destructor for a cache of file used by caret diagnostic.  */

fcache::~fcache ()
{
  if (fp)
    {
      fclose (fp);
      fp = NULL;
    }
  if (data)
    {
      XDELETEVEC (data);
      data = 0;
    }
  line_record.release ();
}

/* Returns TRUE iff the cache would need to be filled with data coming
   from the file.  That is, either the cache is empty or full or the
   current line is empty.  Note that if the cache is full, it would
   need to be extended and filled again.  */

static bool
needs_read (fcache *c)
{
  return (c->nb_read == 0
	  || c->nb_read == c->size
	  || (c->line_start_idx >= c->nb_read - 1));
}

/*  Return TRUE iff the cache is full and thus needs to be
    extended.  */

static bool
needs_grow (fcache *c)
{
  return c->nb_read == c->size;
}

/* Grow the cache if it needs to be extended.  */

static void
maybe_grow (fcache *c)
{
  if (!needs_grow (c))
    return;

  size_t size = c->size == 0 ? fcache_buffer_size : c->size * 2;
  c->data = XRESIZEVEC (char, c->data, size);
  c->size = size;
}

/*  Read more data into the cache.  Extends the cache if need be.
    Returns TRUE iff new data could be read.  */

static bool
read_data (fcache *c)
{
  if (feof (c->fp) || ferror (c->fp))
    return false;

  maybe_grow (c);

  char * from = c->data + c->nb_read;
  size_t to_read = c->size - c->nb_read;
  size_t nb_read = fread (from, 1, to_read, c->fp);

  if (ferror (c->fp))
    return false;

  c->nb_read += nb_read;
  return !!nb_read;
}

/* Read new data iff the cache needs to be filled with more data
   coming from the file FP.  Return TRUE iff the cache was filled with
   mode data.  */

static bool
maybe_read_data (fcache *c)
{
  if (!needs_read (c))
    return false;
  return read_data (c);
}

/* Read a new line from file FP, using C as a cache for the data
   coming from the file.  Upon successful completion, *LINE is set to
   the beginning of the line found.  *LINE points directly in the
   line cache and is only valid until the next call of get_next_line.
   *LINE_LEN is set to the length of the line.  Note that the line
   does not contain any terminal delimiter.  This function returns
   true if some data was read or process from the cache, false
   otherwise.  Note that subsequent calls to get_next_line might
   make the content of *LINE invalid.  */

static bool
get_next_line (fcache *c, char **line, ssize_t *line_len)
{
  /* Fill the cache with data to process.  */
  maybe_read_data (c);

  size_t remaining_size = c->nb_read - c->line_start_idx;
  if (remaining_size == 0)
    /* There is no more data to process.  */
    return false;

  char *line_start = c->data + c->line_start_idx;

  char *next_line_start = NULL;
  size_t len = 0;
  char *line_end = (char *) memchr (line_start, '\n', remaining_size);
  if (line_end == NULL)
    {
      /* We haven't found the end-of-line delimiter in the cache.
	 Fill the cache with more data from the file and look for the
	 '\n'.  */
      while (maybe_read_data (c))
	{
	  line_start = c->data + c->line_start_idx;
	  remaining_size = c->nb_read - c->line_start_idx;
	  line_end = (char *) memchr (line_start, '\n', remaining_size);
	  if (line_end != NULL)
	    {
	      next_line_start = line_end + 1;
	      break;
	    }
	}
      if (line_end == NULL)
	{
	  /* We've loadded all the file into the cache and still no
	     '\n'.  Let's say the line ends up at one byte passed the
	     end of the file.  This is to stay consistent with the case
	     of when the line ends up with a '\n' and line_end points to
	     that terminal '\n'.  That consistency is useful below in
	     the len calculation.  */
	  line_end = c->data + c->nb_read ;
	  c->missing_trailing_newline = true;
	}
      else
	c->missing_trailing_newline = false;
    }
  else
    {
      next_line_start = line_end + 1;
      c->missing_trailing_newline = false;
    }

  if (ferror (c->fp))
    return false;

  /* At this point, we've found the end of the of line.  It either
     points to the '\n' or to one byte after the last byte of the
     file.  */
  gcc_assert (line_end != NULL);

  len = line_end - line_start;

  if (c->line_start_idx < c->nb_read)
    *line = line_start;

  ++c->line_num;

  /* Before we update our line record, make sure the hint about the
     total number of lines of the file is correct.  If it's not, then
     we give up recording line boundaries from now on.  */
  bool update_line_record = true;
  if (c->line_num > c->total_lines)
    update_line_record = false;

    /* Now update our line record so that re-reading lines from the
     before c->line_start_idx is faster.  */
  if (update_line_record
      && c->line_record.length () < fcache_line_record_size)
    {
      /* If the file lines fits in the line record, we just record all
	 its lines ...*/
      if (c->total_lines <= fcache_line_record_size
	  && c->line_num > c->line_record.length ())
	c->line_record.safe_push (fcache::line_info (c->line_num,
						 c->line_start_idx,
						 line_end - c->data));
      else if (c->total_lines > fcache_line_record_size)
	{
	  /* ... otherwise, we just scale total_lines down to
	     (fcache_line_record_size lines.  */
	  size_t n = (c->line_num * fcache_line_record_size) / c->total_lines;
	  if (c->line_record.length () == 0
	      || n >= c->line_record.length ())
	    c->line_record.safe_push (fcache::line_info (c->line_num,
						     c->line_start_idx,
						     line_end - c->data));
	}
    }

  /* Update c->line_start_idx so that it points to the next line to be
     read.  */
  if (next_line_start)
    c->line_start_idx = next_line_start - c->data;
  else
    /* We didn't find any terminal '\n'.  Let's consider that the end
       of line is the end of the data in the cache.  The next
       invocation of get_next_line will either read more data from the
       underlying file or return false early because we've reached the
       end of the file.  */
    c->line_start_idx = c->nb_read;

  *line_len = len;

  return true;
}

/* Consume the next bytes coming from the cache (or from its
   underlying file if there are remaining unread bytes in the file)
   until we reach the next end-of-line (or end-of-file).  There is no
   copying from the cache involved.  Return TRUE upon successful
   completion.  */

static bool
goto_next_line (fcache *cache)
{
  char *l;
  ssize_t len;

  return get_next_line (cache, &l, &len);
}

/* Read an arbitrary line number LINE_NUM from the file cached in C.
   If the line was read successfully, *LINE points to the beginning
   of the line in the file cache and *LINE_LEN is the length of the
   line.  *LINE is not nul-terminated, but may contain zero bytes.
   *LINE is only valid until the next call of read_line_num.
   This function returns bool if a line was read.  */

static bool
read_line_num (fcache *c, size_t line_num,
	       char **line, ssize_t *line_len)
{
  gcc_assert (line_num > 0);

  if (line_num <= c->line_num)
    {
      /* We've been asked to read lines that are before c->line_num.
	 So lets use our line record (if it's not empty) to try to
	 avoid re-reading the file from the beginning again.  */

      if (c->line_record.is_empty ())
	{
	  c->line_start_idx = 0;
	  c->line_num = 0;
	}
      else
	{
	  fcache::line_info *i = NULL;
	  if (c->total_lines <= fcache_line_record_size)
	    {
	      /* In languages where the input file is not totally
		 preprocessed up front, the c->total_lines hint
		 can be smaller than the number of lines of the
		 file.  In that case, only the first
		 c->total_lines have been recorded.

		 Otherwise, the first c->total_lines we've read have
		 their start/end recorded here.  */
	      i = (line_num <= c->total_lines)
		? &c->line_record[line_num - 1]
		: &c->line_record[c->total_lines - 1];
	      gcc_assert (i->line_num <= line_num);
	    }
	  else
	    {
	      /*  So the file had more lines than our line record
		  size.  Thus the number of lines we've recorded has
		  been scaled down to fcache_line_reacord_size.  Let's
		  pick the start/end of the recorded line that is
		  closest to line_num.  */
	      size_t n = (line_num <= c->total_lines)
		? line_num * fcache_line_record_size / c->total_lines
		: c ->line_record.length () - 1;
	      if (n < c->line_record.length ())
		{
		  i = &c->line_record[n];
		  gcc_assert (i->line_num <= line_num);
		}
	    }

	  if (i && i->line_num == line_num)
	    {
	      /* We have the start/end of the line.  */
	      *line = c->data + i->start_pos;
	      *line_len = i->end_pos - i->start_pos;
	      return true;
	    }

	  if (i)
	    {
	      c->line_start_idx = i->start_pos;
	      c->line_num = i->line_num - 1;
	    }
	  else
	    {
	      c->line_start_idx = 0;
	      c->line_num = 0;
	    }
	}
    }

  /*  Let's walk from line c->line_num up to line_num - 1, without
      copying any line.  */
  while (c->line_num < line_num - 1)
    if (!goto_next_line (c))
      return false;

  /* The line we want is the next one.  Let's read and copy it back to
     the caller.  */
  return get_next_line (c, line, line_len);
}

/* Return the physical source line that corresponds to FILE_PATH/LINE.
   The line is not nul-terminated.  The returned pointer is only
   valid until the next call of location_get_source_line.
   Note that the line can contain several null characters,
   so the returned value's length has the actual length of the line.
   If the function fails, a NULL char_span is returned.  */

char_span
location_get_source_line (const char *file_path, int line)
{
  char *buffer = NULL;
  ssize_t len;

  if (line == 0)
    return char_span (NULL, 0);

  fcache *c = lookup_or_add_file_to_cache_tab (file_path);
  if (c == NULL)
    return char_span (NULL, 0);

  bool read = read_line_num (c, line, &buffer, &len);
  if (!read)
    return char_span (NULL, 0);

  return char_span (buffer, len);
}

/* Determine if FILE_PATH missing a trailing newline on its final line.
   Only valid to call once all of the file has been loaded, by
   requesting a line number beyond the end of the file.  */

bool
location_missing_trailing_newline (const char *file_path)
{
  fcache *c = lookup_or_add_file_to_cache_tab (file_path);
  if (c == NULL)
    return false;

  return c->missing_trailing_newline;
}

/* Test if the location originates from the spelling location of a
   builtin-tokens.  That is, return TRUE if LOC is a (possibly
   virtual) location of a built-in token that appears in the expansion
   list of a macro.  Please note that this function also works on
   tokens that result from built-in tokens.  For instance, the
   function would return true if passed a token "4" that is the result
   of the expansion of the built-in __LINE__ macro.  */
bool
is_location_from_builtin_token (location_t loc)
{
  const line_map_ordinary *map = NULL;
  loc = linemap_resolve_location (line_table, loc,
				  LRK_SPELLING_LOCATION, &map);
  return loc == BUILTINS_LOCATION;
}

/* Expand the source location LOC into a human readable location.  If
   LOC is virtual, it resolves to the expansion point of the involved
   macro.  If LOC resolves to a builtin location, the file name of the
   readable location is set to the string "<built-in>".  */

expanded_location
expand_location (location_t loc)
{
  return expand_location_1 (loc, /*expansion_point_p=*/true,
			    LOCATION_ASPECT_CARET);
}

/* Expand the source location LOC into a human readable location.  If
   LOC is virtual, it resolves to the expansion location of the
   relevant macro.  If LOC resolves to a builtin location, the file
   name of the readable location is set to the string
   "<built-in>".  */

expanded_location
expand_location_to_spelling_point (location_t loc,
				   enum location_aspect aspect)
{
  return expand_location_1 (loc, /*expansion_point_p=*/false, aspect);
}

/* The rich_location class within libcpp requires a way to expand
   location_t instances, and relies on the client code
   providing a symbol named
     linemap_client_expand_location_to_spelling_point
   to do this.

   This is the implementation for libcommon.a (all host binaries),
   which simply calls into expand_location_1.  */

expanded_location
linemap_client_expand_location_to_spelling_point (location_t loc,
						  enum location_aspect aspect)
{
  return expand_location_1 (loc, /*expansion_point_p=*/false, aspect);
}


/* If LOCATION is in a system header and if it is a virtual location for
   a token coming from the expansion of a macro, unwind it to the
   location of the expansion point of the macro.  Otherwise, just return
   LOCATION.

   This is used for instance when we want to emit diagnostics about a
   token that may be located in a macro that is itself defined in a
   system header, for example, for the NULL macro.  In such a case, if
   LOCATION were passed directly to diagnostic functions such as
   warning_at, the diagnostic would be suppressed (unless
   -Wsystem-headers).  */

location_t
expansion_point_location_if_in_system_header (location_t location)
{
  if (in_system_header_at (location))
    location = linemap_resolve_location (line_table, location,
					 LRK_MACRO_EXPANSION_POINT,
					 NULL);
  return location;
}

/* If LOCATION is a virtual location for a token coming from the expansion
   of a macro, unwind to the location of the expansion point of the macro.  */

location_t
expansion_point_location (location_t location)
{
  return linemap_resolve_location (line_table, location,
				   LRK_MACRO_EXPANSION_POINT, NULL);
}

/* Construct a location with caret at CARET, ranging from START to
   finish e.g.

                 11111111112
        12345678901234567890
     522
     523   return foo + bar;
                  ~~~~^~~~~
     524

   The location's caret is at the "+", line 523 column 15, but starts
   earlier, at the "f" of "foo" at column 11.  The finish is at the "r"
   of "bar" at column 19.  */

location_t
make_location (location_t caret, location_t start, location_t finish)
{
  location_t pure_loc = get_pure_location (caret);
  source_range src_range;
  src_range.m_start = get_start (start);
  src_range.m_finish = get_finish (finish);
  location_t combined_loc = COMBINE_LOCATION_DATA (line_table,
						   pure_loc,
						   src_range,
						   NULL);
  return combined_loc;
}

/* Same as above, but taking a source range rather than two locations.  */

location_t
make_location (location_t caret, source_range src_range)
{
  location_t pure_loc = get_pure_location (caret);
  return COMBINE_LOCATION_DATA (line_table, pure_loc, src_range, NULL);
}

/* An expanded_location stores the column in byte units.  This function
   converts that column to display units.  That requires reading the associated
   source line in order to calculate the display width.  If that cannot be done
   for any reason, then returns the byte column as a fallback.  */
int
location_compute_display_column (expanded_location exploc)
{
  if (!(exploc.file && *exploc.file && exploc.line && exploc.column))
    return exploc.column;
  char_span line = location_get_source_line (exploc.file, exploc.line);
  /* If line is NULL, this function returns exploc.column which is the
     desired fallback.  */
  return cpp_byte_column_to_display_column (line.get_buffer (), line.length (),
					    exploc.column);
}

/* Dump statistics to stderr about the memory usage of the line_table
   set of line maps.  This also displays some statistics about macro
   expansion.  */

void
dump_line_table_statistics (void)
{
  struct linemap_stats s;
  long total_used_map_size,
    macro_maps_size,
    total_allocated_map_size;

  memset (&s, 0, sizeof (s));

  linemap_get_statistics (line_table, &s);

  macro_maps_size = s.macro_maps_used_size
    + s.macro_maps_locations_size;

  total_allocated_map_size = s.ordinary_maps_allocated_size
    + s.macro_maps_allocated_size
    + s.macro_maps_locations_size;

  total_used_map_size = s.ordinary_maps_used_size
    + s.macro_maps_used_size
    + s.macro_maps_locations_size;

  fprintf (stderr, "Number of expanded macros:                     %5ld\n",
           s.num_expanded_macros);
  if (s.num_expanded_macros != 0)
    fprintf (stderr, "Average number of tokens per macro expansion:  %5ld\n",
             s.num_macro_tokens / s.num_expanded_macros);
  fprintf (stderr,
           "\nLine Table allocations during the "
	   "compilation process\n");
  fprintf (stderr, "Number of ordinary maps used:        " PRsa (5) "\n",
	   SIZE_AMOUNT (s.num_ordinary_maps_used));
  fprintf (stderr, "Ordinary map used size:              " PRsa (5) "\n",
	   SIZE_AMOUNT (s.ordinary_maps_used_size));
  fprintf (stderr, "Number of ordinary maps allocated:   " PRsa (5) "\n",
	   SIZE_AMOUNT (s.num_ordinary_maps_allocated));
  fprintf (stderr, "Ordinary maps allocated size:        " PRsa (5) "\n",
	   SIZE_AMOUNT (s.ordinary_maps_allocated_size));
  fprintf (stderr, "Number of macro maps used:           " PRsa (5) "\n",
	   SIZE_AMOUNT (s.num_macro_maps_used));
  fprintf (stderr, "Macro maps used size:                " PRsa (5) "\n",
	   SIZE_AMOUNT (s.macro_maps_used_size));
  fprintf (stderr, "Macro maps locations size:           " PRsa (5) "\n",
	   SIZE_AMOUNT (s.macro_maps_locations_size));
  fprintf (stderr, "Macro maps size:                     " PRsa (5) "\n",
	   SIZE_AMOUNT (macro_maps_size));
  fprintf (stderr, "Duplicated maps locations size:      " PRsa (5) "\n",
	   SIZE_AMOUNT (s.duplicated_macro_maps_locations_size));
  fprintf (stderr, "Total allocated maps size:           " PRsa (5) "\n",
	   SIZE_AMOUNT (total_allocated_map_size));
  fprintf (stderr, "Total used maps size:                " PRsa (5) "\n",
	   SIZE_AMOUNT (total_used_map_size));
  fprintf (stderr, "Ad-hoc table size:                   " PRsa (5) "\n",
	   SIZE_AMOUNT (s.adhoc_table_size));
  fprintf (stderr, "Ad-hoc table entries used:           " PRsa (5) "\n",
	   SIZE_AMOUNT (s.adhoc_table_entries_used));
  fprintf (stderr, "optimized_ranges:                    " PRsa (5) "\n",
	   SIZE_AMOUNT (line_table->num_optimized_ranges));
  fprintf (stderr, "unoptimized_ranges:                  " PRsa (5) "\n",
	   SIZE_AMOUNT (line_table->num_unoptimized_ranges));

  fprintf (stderr, "\n");
}

/* Get location one beyond the final location in ordinary map IDX.  */

static location_t
get_end_location (class line_maps *set, unsigned int idx)
{
  if (idx == LINEMAPS_ORDINARY_USED (set) - 1)
    return set->highest_location;

  struct line_map *next_map = LINEMAPS_ORDINARY_MAP_AT (set, idx + 1);
  return MAP_START_LOCATION (next_map);
}

/* Helper function for write_digit_row.  */

static void
write_digit (FILE *stream, int digit)
{
  fputc ('0' + (digit % 10), stream);
}

/* Helper function for dump_location_info.
   Write a row of numbers to STREAM, numbering a source line,
   giving the units, tens, hundreds etc of the column number.  */

static void
write_digit_row (FILE *stream, int indent,
		 const line_map_ordinary *map,
		 location_t loc, int max_col, int divisor)
{
  fprintf (stream, "%*c", indent, ' ');
  fprintf (stream, "|");
  for (int column = 1; column < max_col; column++)
    {
      location_t column_loc = loc + (column << map->m_range_bits);
      write_digit (stream, column_loc / divisor);
    }
  fprintf (stream, "\n");
}

/* Write a half-closed (START) / half-open (END) interval of
   location_t to STREAM.  */

static void
dump_location_range (FILE *stream,
		     location_t start, location_t end)
{
  fprintf (stream,
	   "  location_t interval: %u <= loc < %u\n",
	   start, end);
}

/* Write a labelled description of a half-closed (START) / half-open (END)
   interval of location_t to STREAM.  */

static void
dump_labelled_location_range (FILE *stream,
			      const char *name,
			      location_t start, location_t end)
{
  fprintf (stream, "%s\n", name);
  dump_location_range (stream, start, end);
  fprintf (stream, "\n");
}

/* Write a visualization of the locations in the line_table to STREAM.  */

void
dump_location_info (FILE *stream)
{
  /* Visualize the reserved locations.  */
  dump_labelled_location_range (stream, "RESERVED LOCATIONS",
				0, RESERVED_LOCATION_COUNT);

  /* Visualize the ordinary line_map instances, rendering the sources. */
  for (unsigned int idx = 0; idx < LINEMAPS_ORDINARY_USED (line_table); idx++)
    {
      location_t end_location = get_end_location (line_table, idx);
      /* half-closed: doesn't include this one. */

      const line_map_ordinary *map
	= LINEMAPS_ORDINARY_MAP_AT (line_table, idx);
      fprintf (stream, "ORDINARY MAP: %i\n", idx);
      dump_location_range (stream,
			   MAP_START_LOCATION (map), end_location);
      fprintf (stream, "  file: %s\n", ORDINARY_MAP_FILE_NAME (map));
      fprintf (stream, "  starting at line: %i\n",
	       ORDINARY_MAP_STARTING_LINE_NUMBER (map));
      fprintf (stream, "  column and range bits: %i\n",
	       map->m_column_and_range_bits);
      fprintf (stream, "  column bits: %i\n",
	       map->m_column_and_range_bits - map->m_range_bits);
      fprintf (stream, "  range bits: %i\n",
	       map->m_range_bits);
      const char * reason;
      switch (map->reason) {
      case LC_ENTER:
	reason = "LC_ENTER";
	break;
      case LC_LEAVE:
	reason = "LC_LEAVE";
	break;
      case LC_RENAME:
	reason = "LC_RENAME";
	break;
      case LC_RENAME_VERBATIM:
	reason = "LC_RENAME_VERBATIM";
	break;
      case LC_ENTER_MACRO:
	reason = "LC_RENAME_MACRO";
	break;
      default:
	reason = "Unknown";
      }
      fprintf (stream, "  reason: %d (%s)\n", map->reason, reason);

      const line_map_ordinary *includer_map
	= linemap_included_from_linemap (line_table, map);
      fprintf (stream, "  included from location: %d",
	       linemap_included_from (map));
      if (includer_map) {
	fprintf (stream, " (in ordinary map %d)",
		 int (includer_map - line_table->info_ordinary.maps));
      }
      fprintf (stream, "\n");

      /* Render the span of source lines that this "map" covers.  */
      for (location_t loc = MAP_START_LOCATION (map);
	   loc < end_location;
	   loc += (1 << map->m_range_bits) )
	{
	  gcc_assert (pure_location_p (line_table, loc) );

	  expanded_location exploc
	    = linemap_expand_location (line_table, map, loc);

	  if (exploc.column == 0)
	    {
	      /* Beginning of a new source line: draw the line.  */

	      char_span line_text = location_get_source_line (exploc.file,
							      exploc.line);
	      if (!line_text)
		break;
	      fprintf (stream,
		       "%s:%3i|loc:%5i|%.*s\n",
		       exploc.file, exploc.line,
		       loc,
		       (int)line_text.length (), line_text.get_buffer ());

	      /* "loc" is at column 0, which means "the whole line".
		 Render the locations *within* the line, by underlining
		 it, showing the location_t numeric values
		 at each column.  */
	      size_t max_col = (1 << map->m_column_and_range_bits) - 1;
	      if (max_col > line_text.length ())
		max_col = line_text.length () + 1;

	      int len_lnum = num_digits (exploc.line);
	      if (len_lnum < 3)
		len_lnum = 3;
	      int len_loc = num_digits (loc);
	      if (len_loc < 5)
		len_loc = 5;

	      int indent = 6 + strlen (exploc.file) + len_lnum + len_loc;

	      /* Thousands.  */
	      if (end_location > 999)
		write_digit_row (stream, indent, map, loc, max_col, 1000);

	      /* Hundreds.  */
	      if (end_location > 99)
		write_digit_row (stream, indent, map, loc, max_col, 100);

	      /* Tens.  */
	      write_digit_row (stream, indent, map, loc, max_col, 10);

	      /* Units.  */
	      write_digit_row (stream, indent, map, loc, max_col, 1);
	    }
	}
      fprintf (stream, "\n");
    }

  /* Visualize unallocated values.  */
  dump_labelled_location_range (stream, "UNALLOCATED LOCATIONS",
				line_table->highest_location,
				LINEMAPS_MACRO_LOWEST_LOCATION (line_table));

  /* Visualize the macro line_map instances, rendering the sources. */
  for (unsigned int i = 0; i < LINEMAPS_MACRO_USED (line_table); i++)
    {
      /* Each macro map that is allocated owns location_t values
	 that are *lower* that the one before them.
	 Hence it's meaningful to view them either in order of ascending
	 source locations, or in order of ascending macro map index.  */
      const bool ascending_location_ts = true;
      unsigned int idx = (ascending_location_ts
			  ? (LINEMAPS_MACRO_USED (line_table) - (i + 1))
			  : i);
      const line_map_macro *map = LINEMAPS_MACRO_MAP_AT (line_table, idx);
      fprintf (stream, "MACRO %i: %s (%u tokens)\n",
	       idx,
	       linemap_map_get_macro_name (map),
	       MACRO_MAP_NUM_MACRO_TOKENS (map));
      dump_location_range (stream,
			   map->start_location,
			   (map->start_location
			    + MACRO_MAP_NUM_MACRO_TOKENS (map)));
      inform (MACRO_MAP_EXPANSION_POINT_LOCATION (map),
	      "expansion point is location %i",
	      MACRO_MAP_EXPANSION_POINT_LOCATION (map));
      fprintf (stream, "  map->start_location: %u\n",
	       map->start_location);

      fprintf (stream, "  macro_locations:\n");
      for (unsigned int i = 0; i < MACRO_MAP_NUM_MACRO_TOKENS (map); i++)
	{
	  location_t x = MACRO_MAP_LOCATIONS (map)[2 * i];
	  location_t y = MACRO_MAP_LOCATIONS (map)[(2 * i) + 1];

	  /* linemap_add_macro_token encodes token numbers in an expansion
	     by putting them after MAP_START_LOCATION. */

	  /* I'm typically seeing 4 uninitialized entries at the end of
	     0xafafafaf.
	     This appears to be due to macro.c:replace_args
	     adding 2 extra args for padding tokens; presumably there may
	     be a leading and/or trailing padding token injected,
	     each for 2 more location slots.
	     This would explain there being up to 4 location_ts slots
	     that may be uninitialized.  */

	  fprintf (stream, "    %u: %u, %u\n",
		   i,
		   x,
		   y);
	  if (x == y)
	    {
	      if (x < MAP_START_LOCATION (map))
		inform (x, "token %u has %<x-location == y-location == %u%>",
			i, x);
	      else
		fprintf (stream,
			 "x-location == y-location == %u encodes token # %u\n",
			 x, x - MAP_START_LOCATION (map));
		}
	  else
	    {
	      inform (x, "token %u has %<x-location == %u%>", i, x);
	      inform (x, "token %u has %<y-location == %u%>", i, y);
	    }
	}
      fprintf (stream, "\n");
    }

  /* It appears that MAX_LOCATION_T itself is never assigned to a
     macro map, presumably due to an off-by-one error somewhere
     between the logic in linemap_enter_macro and
     LINEMAPS_MACRO_LOWEST_LOCATION.  */
  dump_labelled_location_range (stream, "MAX_LOCATION_T",
				MAX_LOCATION_T,
				MAX_LOCATION_T + 1);

  /* Visualize ad-hoc values.  */
  dump_labelled_location_range (stream, "AD-HOC LOCATIONS",
				MAX_LOCATION_T + 1, UINT_MAX);
}

/* string_concat's constructor.  */

string_concat::string_concat (int num, location_t *locs)
  : m_num (num)
{
  m_locs = ggc_vec_alloc <location_t> (num);
  for (int i = 0; i < num; i++)
    m_locs[i] = locs[i];
}

/* string_concat_db's constructor.  */

string_concat_db::string_concat_db ()
{
  m_table = hash_map <location_hash, string_concat *>::create_ggc (64);
}

/* Record that a string concatenation occurred, covering NUM
   string literal tokens.  LOCS is an array of size NUM, containing the
   locations of the tokens.  A copy of LOCS is taken.  */

void
string_concat_db::record_string_concatenation (int num, location_t *locs)
{
  gcc_assert (num > 1);
  gcc_assert (locs);

  location_t key_loc = get_key_loc (locs[0]);

  string_concat *concat
    = new (ggc_alloc <string_concat> ()) string_concat (num, locs);
  m_table->put (key_loc, concat);
}

/* Determine if LOC was the location of the the initial token of a
   concatenation of string literal tokens.
   If so, *OUT_NUM is written to with the number of tokens, and
   *OUT_LOCS with the location of an array of locations of the
   tokens, and return true.  *OUT_LOCS is a borrowed pointer to
   storage owned by the string_concat_db.
   Otherwise, return false.  */

bool
string_concat_db::get_string_concatenation (location_t loc,
					    int *out_num,
					    location_t **out_locs)
{
  gcc_assert (out_num);
  gcc_assert (out_locs);

  location_t key_loc = get_key_loc (loc);

  string_concat **concat = m_table->get (key_loc);
  if (!concat)
    return false;

  *out_num = (*concat)->m_num;
  *out_locs =(*concat)->m_locs;
  return true;
}

/* Internal function.  Canonicalize LOC into a form suitable for
   use as a key within the database, stripping away macro expansion,
   ad-hoc information, and range information, using the location of
   the start of LOC within an ordinary linemap.  */

location_t
string_concat_db::get_key_loc (location_t loc)
{
  loc = linemap_resolve_location (line_table, loc, LRK_SPELLING_LOCATION,
				  NULL);

  loc = get_range_from_loc (line_table, loc).m_start;

  return loc;
}

/* Helper class for use within get_substring_ranges_for_loc.
   An vec of cpp_string with responsibility for releasing all of the
   str->text for each str in the vector.  */

class auto_cpp_string_vec :  public auto_vec <cpp_string>
{
 public:
  auto_cpp_string_vec (int alloc)
    : auto_vec <cpp_string> (alloc) {}

  ~auto_cpp_string_vec ()
  {
    /* Clean up the copies within this vec.  */
    int i;
    cpp_string *str;
    FOR_EACH_VEC_ELT (*this, i, str)
      free (const_cast <unsigned char *> (str->text));
  }
};

/* Attempt to populate RANGES with source location information on the
   individual characters within the string literal found at STRLOC.
   If CONCATS is non-NULL, then any string literals that the token at
   STRLOC  was concatenated with are also added to RANGES.

   Return NULL if successful, or an error message if any errors occurred (in
   which case RANGES may be only partially populated and should not
   be used).

   This is implemented by re-parsing the relevant source line(s).  */

static const char *
get_substring_ranges_for_loc (cpp_reader *pfile,
			      string_concat_db *concats,
			      location_t strloc,
			      enum cpp_ttype type,
			      cpp_substring_ranges &ranges)
{
  gcc_assert (pfile);

  if (strloc == UNKNOWN_LOCATION)
    return "unknown location";

  /* Reparsing the strings requires accurate location information.
     If -ftrack-macro-expansion has been overridden from its default
     of 2, then we might have a location of a macro expansion point,
     rather than the location of the literal itself.
     Avoid this by requiring that we have full macro expansion tracking
     for substring locations to be available.  */
  if (cpp_get_options (pfile)->track_macro_expansion != 2)
    return "track_macro_expansion != 2";

  /* If #line or # 44 "file"-style directives are present, then there's
     no guarantee that the line numbers we have can be used to locate
     the strings.  For example, we might have a .i file with # directives
     pointing back to lines within a .c file, but the .c file might
     have been edited since the .i file was created.
     In such a case, the safest course is to disable on-demand substring
     locations.  */
  if (line_table->seen_line_directive)
    return "seen line directive";

  /* If string concatenation has occurred at STRLOC, get the locations
     of all of the literal tokens making up the compound string.
     Otherwise, just use STRLOC.  */
  int num_locs = 1;
  location_t *strlocs = &strloc;
  if (concats)
    concats->get_string_concatenation (strloc, &num_locs, &strlocs);

  auto_cpp_string_vec strs (num_locs);
  auto_vec <cpp_string_location_reader> loc_readers (num_locs);
  for (int i = 0; i < num_locs; i++)
    {
      /* Get range of strloc.  We will use it to locate the start and finish
	 of the literal token within the line.  */
      source_range src_range = get_range_from_loc (line_table, strlocs[i]);

      if (src_range.m_start >= LINEMAPS_MACRO_LOWEST_LOCATION (line_table))
	{
	  /* If the string token was within a macro expansion, then we can
	     cope with it for the simple case where we have a single token.
	     Otherwise, bail out.  */
	  if (src_range.m_start != src_range.m_finish)
	    return "macro expansion";
	}
      else
	{
	  if (src_range.m_start >= LINE_MAP_MAX_LOCATION_WITH_COLS)
	    /* If so, we can't reliably determine where the token started within
	       its line.  */
	    return "range starts after LINE_MAP_MAX_LOCATION_WITH_COLS";

	  if (src_range.m_finish >= LINE_MAP_MAX_LOCATION_WITH_COLS)
	    /* If so, we can't reliably determine where the token finished
	       within its line.  */
	    return "range ends after LINE_MAP_MAX_LOCATION_WITH_COLS";
	}

      expanded_location start
	= expand_location_to_spelling_point (src_range.m_start,
					     LOCATION_ASPECT_START);
      expanded_location finish
	= expand_location_to_spelling_point (src_range.m_finish,
					     LOCATION_ASPECT_FINISH);
      if (start.file != finish.file)
	return "range endpoints are in different files";
      if (start.line != finish.line)
	return "range endpoints are on different lines";
      if (start.column > finish.column)
	return "range endpoints are reversed";

      char_span line = location_get_source_line (start.file, start.line);
      if (!line)
	return "unable to read source line";

      /* Determine the location of the literal (including quotes
	 and leading prefix chars, such as the 'u' in a u""
	 token).  */
      size_t literal_length = finish.column - start.column + 1;

      /* Ensure that we don't crash if we got the wrong location.  */
      if (line.length () < (start.column - 1 + literal_length))
	return "line is not wide enough";

      char_span literal = line.subspan (start.column - 1, literal_length);

      cpp_string from;
      from.len = literal_length;
      /* Make a copy of the literal, to avoid having to rely on
	 the lifetime of the copy of the line within the cache.
	 This will be released by the auto_cpp_string_vec dtor.  */
      from.text = (unsigned char *)literal.xstrdup ();
      strs.safe_push (from);

      /* For very long lines, a new linemap could have started
	 halfway through the token.
	 Ensure that the loc_reader uses the linemap of the
	 *end* of the token for its start location.  */
      const line_map_ordinary *start_ord_map;
      linemap_resolve_location (line_table, src_range.m_start,
				LRK_SPELLING_LOCATION, &start_ord_map);
      const line_map_ordinary *final_ord_map;
      linemap_resolve_location (line_table, src_range.m_finish,
				LRK_SPELLING_LOCATION, &final_ord_map);
      if (start_ord_map == NULL || final_ord_map == NULL)
	return "failed to get ordinary maps";
      /* Bulletproofing.  We ought to only have different ordinary maps
	 for start vs finish due to line-length jumps.  */
      if (start_ord_map != final_ord_map
	  && start_ord_map->to_file != final_ord_map->to_file)
	return "start and finish are spelled in different ordinary maps";
      /* The file from linemap_resolve_location ought to match that from
	 expand_location_to_spelling_point.  */
      if (start_ord_map->to_file != start.file)
	return "mismatching file after resolving linemap";

      location_t start_loc
	= linemap_position_for_line_and_column (line_table, final_ord_map,
						start.line, start.column);

      cpp_string_location_reader loc_reader (start_loc, line_table);
      loc_readers.safe_push (loc_reader);
    }

  /* Rerun cpp_interpret_string, or rather, a modified version of it.  */
  const char *err = cpp_interpret_string_ranges (pfile, strs.address (),
						 loc_readers.address (),
						 num_locs, &ranges, type);
  if (err)
    return err;

  /* Success: "ranges" should now contain information on the string.  */
  return NULL;
}

/* Attempt to populate *OUT_LOC with source location information on the
   given characters within the string literal found at STRLOC.
   CARET_IDX, START_IDX, and END_IDX refer to offsets within the execution
   character set.

   For example, given CARET_IDX = 4, START_IDX = 3, END_IDX  = 7
   and string literal "012345\n789"
   *OUT_LOC is written to with:
     "012345\n789"
         ~^~~~~

   If CONCATS is non-NULL, then any string literals that the token at
   STRLOC was concatenated with are also considered.

   This is implemented by re-parsing the relevant source line(s).

   Return NULL if successful, or an error message if any errors occurred.
   Error messages are intended for GCC developers (to help debugging) rather
   than for end-users.  */

const char *
get_location_within_string (cpp_reader *pfile,
			    string_concat_db *concats,
			    location_t strloc,
			    enum cpp_ttype type,
			    int caret_idx, int start_idx, int end_idx,
			    location_t *out_loc)
{
  gcc_checking_assert (caret_idx >= 0);
  gcc_checking_assert (start_idx >= 0);
  gcc_checking_assert (end_idx >= 0);
  gcc_assert (out_loc);

  cpp_substring_ranges ranges;
  const char *err
    = get_substring_ranges_for_loc (pfile, concats, strloc, type, ranges);
  if (err)
    return err;

  if (caret_idx >= ranges.get_num_ranges ())
    return "caret_idx out of range";
  if (start_idx >= ranges.get_num_ranges ())
    return "start_idx out of range";
  if (end_idx >= ranges.get_num_ranges ())
    return "end_idx out of range";

  *out_loc = make_location (ranges.get_range (caret_idx).m_start,
			    ranges.get_range (start_idx).m_start,
			    ranges.get_range (end_idx).m_finish);
  return NULL;
}

#if CHECKING_P

namespace selftest {

/* Selftests of location handling.  */

/* Attempt to populate *OUT_RANGE with source location information on the
   given character within the string literal found at STRLOC.
   CHAR_IDX refers to an offset within the execution character set.
   If CONCATS is non-NULL, then any string literals that the token at
   STRLOC was concatenated with are also considered.

   This is implemented by re-parsing the relevant source line(s).

   Return NULL if successful, or an error message if any errors occurred.
   Error messages are intended for GCC developers (to help debugging) rather
   than for end-users.  */

static const char *
get_source_range_for_char (cpp_reader *pfile,
			   string_concat_db *concats,
			   location_t strloc,
			   enum cpp_ttype type,
			   int char_idx,
			   source_range *out_range)
{
  gcc_checking_assert (char_idx >= 0);
  gcc_assert (out_range);

  cpp_substring_ranges ranges;
  const char *err
    = get_substring_ranges_for_loc (pfile, concats, strloc, type, ranges);
  if (err)
    return err;

  if (char_idx >= ranges.get_num_ranges ())
    return "char_idx out of range";

  *out_range = ranges.get_range (char_idx);
  return NULL;
}

/* As get_source_range_for_char, but write to *OUT the number
   of ranges that are available.  */

static const char *
get_num_source_ranges_for_substring (cpp_reader *pfile,
				     string_concat_db *concats,
				     location_t strloc,
				     enum cpp_ttype type,
				     int *out)
{
  gcc_assert (out);

  cpp_substring_ranges ranges;
  const char *err
    = get_substring_ranges_for_loc (pfile, concats, strloc, type, ranges);

  if (err)
    return err;

  *out = ranges.get_num_ranges ();
  return NULL;
}

/* Selftests of location handling.  */

/* Verify that compare() on linenum_type handles comparisons over the full
   range of the type.  */

static void
test_linenum_comparisons ()
{
  linenum_type min_line (0);
  linenum_type max_line (0xffffffff);
  ASSERT_EQ (0, compare (min_line, min_line));
  ASSERT_EQ (0, compare (max_line, max_line));

  ASSERT_GT (compare (max_line, min_line), 0);
  ASSERT_LT (compare (min_line, max_line), 0);
}

/* Helper function for verifying location data: when location_t
   values are > LINE_MAP_MAX_LOCATION_WITH_COLS, they are treated
   as having column 0.  */

static bool
should_have_column_data_p (location_t loc)
{
  if (IS_ADHOC_LOC (loc))
    loc = get_location_from_adhoc_loc (line_table, loc);
  if (loc > LINE_MAP_MAX_LOCATION_WITH_COLS)
    return false;
  return true;
}

/* Selftest for should_have_column_data_p.  */

static void
test_should_have_column_data_p ()
{
  ASSERT_TRUE (should_have_column_data_p (RESERVED_LOCATION_COUNT));
  ASSERT_TRUE
    (should_have_column_data_p (LINE_MAP_MAX_LOCATION_WITH_COLS));
  ASSERT_FALSE
    (should_have_column_data_p (LINE_MAP_MAX_LOCATION_WITH_COLS + 1));
}

/* Verify the result of LOCATION_FILE/LOCATION_LINE/LOCATION_COLUMN
   on LOC.  */

static void
assert_loceq (const char *exp_filename, int exp_linenum, int exp_colnum,
	      location_t loc)
{
  ASSERT_STREQ (exp_filename, LOCATION_FILE (loc));
  ASSERT_EQ (exp_linenum, LOCATION_LINE (loc));
  /* If location_t values are sufficiently high, then column numbers
     will be unavailable and LOCATION_COLUMN (loc) will be 0.
     When close to the threshold, column numbers *may* be present: if
     the final linemap before the threshold contains a line that straddles
     the threshold, locations in that line have column information.  */
  if (should_have_column_data_p (loc))
    ASSERT_EQ (exp_colnum, LOCATION_COLUMN (loc));
}

/* Various selftests involve constructing a line table and one or more
   line maps within it.

   For maximum test coverage we want to run these tests with a variety
   of situations:
   - line_table->default_range_bits: some frontends use a non-zero value
   and others use zero
   - the fallback modes within line-map.c: there are various threshold
   values for location_t beyond line-map.c changes
   behavior (disabling of the range-packing optimization, disabling
   of column-tracking).  We can exercise these by starting the line_table
   at interesting values at or near these thresholds.

   The following struct describes a particular case within our test
   matrix.  */

class line_table_case
{
public:
  line_table_case (int default_range_bits, int base_location)
  : m_default_range_bits (default_range_bits),
    m_base_location (base_location)
  {}

  int m_default_range_bits;
  int m_base_location;
};

/* Constructor.  Store the old value of line_table, and create a new
   one, using sane defaults.  */

line_table_test::line_table_test ()
{
  gcc_assert (saved_line_table == NULL);
  saved_line_table = line_table;
  line_table = ggc_alloc<line_maps> ();
  linemap_init (line_table, BUILTINS_LOCATION);
  gcc_assert (saved_line_table->reallocator);
  line_table->reallocator = saved_line_table->reallocator;
  gcc_assert (saved_line_table->round_alloc_size);
  line_table->round_alloc_size = saved_line_table->round_alloc_size;
  line_table->default_range_bits = 0;
}

/* Constructor.  Store the old value of line_table, and create a new
   one, using the sitation described in CASE_.  */

line_table_test::line_table_test (const line_table_case &case_)
{
  gcc_assert (saved_line_table == NULL);
  saved_line_table = line_table;
  line_table = ggc_alloc<line_maps> ();
  linemap_init (line_table, BUILTINS_LOCATION);
  gcc_assert (saved_line_table->reallocator);
  line_table->reallocator = saved_line_table->reallocator;
  gcc_assert (saved_line_table->round_alloc_size);
  line_table->round_alloc_size = saved_line_table->round_alloc_size;
  line_table->default_range_bits = case_.m_default_range_bits;
  if (case_.m_base_location)
    {
      line_table->highest_location = case_.m_base_location;
      line_table->highest_line = case_.m_base_location;
    }
}

/* Destructor.  Restore the old value of line_table.  */

line_table_test::~line_table_test ()
{
  gcc_assert (saved_line_table != NULL);
  line_table = saved_line_table;
  saved_line_table = NULL;
}

/* Verify basic operation of ordinary linemaps.  */

static void
test_accessing_ordinary_linemaps (const line_table_case &case_)
{
  line_table_test ltt (case_);

  /* Build a simple linemap describing some locations. */
  linemap_add (line_table, LC_ENTER, false, "foo.c", 0);

  linemap_line_start (line_table, 1, 100);
  location_t loc_a = linemap_position_for_column (line_table, 1);
  location_t loc_b = linemap_position_for_column (line_table, 23);

  linemap_line_start (line_table, 2, 100);
  location_t loc_c = linemap_position_for_column (line_table, 1);
  location_t loc_d = linemap_position_for_column (line_table, 17);

  /* Example of a very long line.  */
  linemap_line_start (line_table, 3, 2000);
  location_t loc_e = linemap_position_for_column (line_table, 700);

  /* Transitioning back to a short line.  */
  linemap_line_start (line_table, 4, 0);
  location_t loc_back_to_short = linemap_position_for_column (line_table, 100);

  if (should_have_column_data_p (loc_back_to_short))
    {
      /* Verify that we switched to short lines in the linemap.  */
      line_map_ordinary *map = LINEMAPS_LAST_ORDINARY_MAP (line_table);
      ASSERT_EQ (7, map->m_column_and_range_bits - map->m_range_bits);
    }

  /* Example of a line that will eventually be seen to be longer
     than LINE_MAP_MAX_COLUMN_NUMBER; the initially seen width is
     below that.  */
  linemap_line_start (line_table, 5, 2000);

  location_t loc_start_of_very_long_line
    = linemap_position_for_column (line_table, 2000);
  location_t loc_too_wide
    = linemap_position_for_column (line_table, 4097);
  location_t loc_too_wide_2
    = linemap_position_for_column (line_table, 4098);

  /* ...and back to a sane line length.  */
  linemap_line_start (line_table, 6, 100);
  location_t loc_sane_again = linemap_position_for_column (line_table, 10);

  linemap_add (line_table, LC_LEAVE, false, NULL, 0);

  /* Multiple files.  */
  linemap_add (line_table, LC_ENTER, false, "bar.c", 0);
  linemap_line_start (line_table, 1, 200);
  location_t loc_f = linemap_position_for_column (line_table, 150);
  linemap_add (line_table, LC_LEAVE, false, NULL, 0);

  /* Verify that we can recover the location info.  */
  assert_loceq ("foo.c", 1, 1, loc_a);
  assert_loceq ("foo.c", 1, 23, loc_b);
  assert_loceq ("foo.c", 2, 1, loc_c);
  assert_loceq ("foo.c", 2, 17, loc_d);
  assert_loceq ("foo.c", 3, 700, loc_e);
  assert_loceq ("foo.c", 4, 100, loc_back_to_short);

  /* In the very wide line, the initial location should be fully tracked.  */
  assert_loceq ("foo.c", 5, 2000, loc_start_of_very_long_line);
  /* ...but once we exceed LINE_MAP_MAX_COLUMN_NUMBER column-tracking should
     be disabled.  */
  assert_loceq ("foo.c", 5, 0, loc_too_wide);
  assert_loceq ("foo.c", 5, 0, loc_too_wide_2);
  /*...and column-tracking should be re-enabled for subsequent lines.  */
  assert_loceq ("foo.c", 6, 10, loc_sane_again);

  assert_loceq ("bar.c", 1, 150, loc_f);

  ASSERT_FALSE (is_location_from_builtin_token (loc_a));
  ASSERT_TRUE (pure_location_p (line_table, loc_a));

  /* Verify using make_location to build a range, and extracting data
     back from it.  */
  location_t range_c_b_d = make_location (loc_c, loc_b, loc_d);
  ASSERT_FALSE (pure_location_p (line_table, range_c_b_d));
  ASSERT_EQ (loc_c, get_location_from_adhoc_loc (line_table, range_c_b_d));
  source_range src_range = get_range_from_loc (line_table, range_c_b_d);
  ASSERT_EQ (loc_b, src_range.m_start);
  ASSERT_EQ (loc_d, src_range.m_finish);
}

/* Verify various properties of UNKNOWN_LOCATION.  */

static void
test_unknown_location ()
{
  ASSERT_EQ (NULL, LOCATION_FILE (UNKNOWN_LOCATION));
  ASSERT_EQ (0, LOCATION_LINE (UNKNOWN_LOCATION));
  ASSERT_EQ (0, LOCATION_COLUMN (UNKNOWN_LOCATION));
}

/* Verify various properties of BUILTINS_LOCATION.  */

static void
test_builtins ()
{
  assert_loceq (_("<built-in>"), 0, 0, BUILTINS_LOCATION);
  ASSERT_PRED1 (is_location_from_builtin_token, BUILTINS_LOCATION);
}

/* Regression test for make_location.
   Ensure that we use pure locations for the start/finish of the range,
   rather than storing a packed or ad-hoc range as the start/finish.  */

static void
test_make_location_nonpure_range_endpoints (const line_table_case &case_)
{
  /* Issue seen with testsuite/c-c++-common/Wlogical-not-parentheses-2.c
     with C++ frontend.
     ....................0000000001111111111222.
     ....................1234567890123456789012.  */
  const char *content = "     r += !aaa == bbb;\n";
  temp_source_file tmp (SELFTEST_LOCATION, ".C", content);
  line_table_test ltt (case_);
  linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 1);

  const location_t c11 = linemap_position_for_column (line_table, 11);
  const location_t c12 = linemap_position_for_column (line_table, 12);
  const location_t c13 = linemap_position_for_column (line_table, 13);
  const location_t c14 = linemap_position_for_column (line_table, 14);
  const location_t c21 = linemap_position_for_column (line_table, 21);

  if (c21 > LINE_MAP_MAX_LOCATION_WITH_COLS)
    return;

  /* Use column 13 for the caret location, arbitrarily, to verify that we
     handle start != caret.  */
  const location_t aaa = make_location (c13, c12, c14);
  ASSERT_EQ (c13, get_pure_location (aaa));
  ASSERT_EQ (c12, get_start (aaa));
  ASSERT_FALSE (IS_ADHOC_LOC (get_start (aaa)));
  ASSERT_EQ (c14, get_finish (aaa));
  ASSERT_FALSE (IS_ADHOC_LOC (get_finish (aaa)));

  /* Make a location using a location with a range as the start-point.  */
  const location_t not_aaa = make_location (c11, aaa, c14);
  ASSERT_EQ (c11, get_pure_location (not_aaa));
  /* It should use the start location of the range, not store the range
     itself.  */
  ASSERT_EQ (c12, get_start (not_aaa));
  ASSERT_FALSE (IS_ADHOC_LOC (get_start (not_aaa)));
  ASSERT_EQ (c14, get_finish (not_aaa));
  ASSERT_FALSE (IS_ADHOC_LOC (get_finish (not_aaa)));

  /* Similarly, make a location with a range as the end-point.  */
  const location_t aaa_eq_bbb = make_location (c12, c12, c21);
  ASSERT_EQ (c12, get_pure_location (aaa_eq_bbb));
  ASSERT_EQ (c12, get_start (aaa_eq_bbb));
  ASSERT_FALSE (IS_ADHOC_LOC (get_start (aaa_eq_bbb)));
  ASSERT_EQ (c21, get_finish (aaa_eq_bbb));
  ASSERT_FALSE (IS_ADHOC_LOC (get_finish (aaa_eq_bbb)));
  const location_t not_aaa_eq_bbb = make_location (c11, c12, aaa_eq_bbb);
  /* It should use the finish location of the range, not store the range
     itself.  */
  ASSERT_EQ (c11, get_pure_location (not_aaa_eq_bbb));
  ASSERT_EQ (c12, get_start (not_aaa_eq_bbb));
  ASSERT_FALSE (IS_ADHOC_LOC (get_start (not_aaa_eq_bbb)));
  ASSERT_EQ (c21, get_finish (not_aaa_eq_bbb));
  ASSERT_FALSE (IS_ADHOC_LOC (get_finish (not_aaa_eq_bbb)));
}

/* Verify reading of input files (e.g. for caret-based diagnostics).  */

static void
test_reading_source_line ()
{
  /* Create a tempfile and write some text to it.  */
  temp_source_file tmp (SELFTEST_LOCATION, ".txt",
			"01234567890123456789\n"
			"This is the test text\n"
			"This is the 3rd line");

  /* Read back a specific line from the tempfile.  */
  char_span source_line = location_get_source_line (tmp.get_filename (), 3);
  ASSERT_TRUE (source_line);
  ASSERT_TRUE (source_line.get_buffer () != NULL);
  ASSERT_EQ (20, source_line.length ());
  ASSERT_TRUE (!strncmp ("This is the 3rd line",
			 source_line.get_buffer (), source_line.length ()));

  source_line = location_get_source_line (tmp.get_filename (), 2);
  ASSERT_TRUE (source_line);
  ASSERT_TRUE (source_line.get_buffer () != NULL);
  ASSERT_EQ (21, source_line.length ());
  ASSERT_TRUE (!strncmp ("This is the test text",
			 source_line.get_buffer (), source_line.length ()));

  source_line = location_get_source_line (tmp.get_filename (), 4);
  ASSERT_FALSE (source_line);
  ASSERT_TRUE (source_line.get_buffer () == NULL);
}

/* Tests of lexing.  */

/* Verify that token TOK from PARSER has cpp_token_as_text
   equal to EXPECTED_TEXT.  */

#define ASSERT_TOKEN_AS_TEXT_EQ(PARSER, TOK, EXPECTED_TEXT)		\
  SELFTEST_BEGIN_STMT							\
    unsigned char *actual_txt = cpp_token_as_text ((PARSER), (TOK));	\
    ASSERT_STREQ ((EXPECTED_TEXT), (const char *)actual_txt);		\
  SELFTEST_END_STMT

/* Verify that TOK's src_loc is within EXP_FILENAME at EXP_LINENUM,
   and ranges from EXP_START_COL to EXP_FINISH_COL.
   Use LOC as the effective location of the selftest.  */

static void
assert_token_loc_eq (const location &loc,
		     const cpp_token *tok,
		     const char *exp_filename, int exp_linenum,
		     int exp_start_col, int exp_finish_col)
{
  location_t tok_loc = tok->src_loc;
  ASSERT_STREQ_AT (loc, exp_filename, LOCATION_FILE (tok_loc));
  ASSERT_EQ_AT (loc, exp_linenum, LOCATION_LINE (tok_loc));

  /* If location_t values are sufficiently high, then column numbers
     will be unavailable.  */
  if (!should_have_column_data_p (tok_loc))
    return;

  ASSERT_EQ_AT (loc, exp_start_col, LOCATION_COLUMN (tok_loc));
  source_range tok_range = get_range_from_loc (line_table, tok_loc);
  ASSERT_EQ_AT (loc, exp_start_col, LOCATION_COLUMN (tok_range.m_start));
  ASSERT_EQ_AT (loc, exp_finish_col, LOCATION_COLUMN (tok_range.m_finish));
}

/* Use assert_token_loc_eq to verify the TOK->src_loc, using
   SELFTEST_LOCATION as the effective location of the selftest.  */

#define ASSERT_TOKEN_LOC_EQ(TOK, EXP_FILENAME, EXP_LINENUM, \
			    EXP_START_COL, EXP_FINISH_COL) \
  assert_token_loc_eq (SELFTEST_LOCATION, (TOK), (EXP_FILENAME), \
		       (EXP_LINENUM), (EXP_START_COL), (EXP_FINISH_COL))

/* Test of lexing a file using libcpp, verifying tokens and their
   location information.  */

static void
test_lexer (const line_table_case &case_)
{
  /* Create a tempfile and write some text to it.  */
  const char *content =
    /*00000000011111111112222222222333333.3333444444444.455555555556
      12345678901234567890123456789012345.6789012345678.901234567890.  */
    ("test_name /* c-style comment */\n"
     "                                  \"test literal\"\n"
     " // test c++-style comment\n"
     "   42\n");
  temp_source_file tmp (SELFTEST_LOCATION, ".txt", content);

  line_table_test ltt (case_);

  cpp_reader *parser = cpp_create_reader (CLK_GNUC89, NULL, line_table);

  const char *fname = cpp_read_main_file (parser, tmp.get_filename ());
  ASSERT_NE (fname, NULL);

  /* Verify that we get the expected tokens back, with the correct
     location information.  */

  location_t loc;
  const cpp_token *tok;
  tok = cpp_get_token_with_location (parser, &loc);
  ASSERT_NE (tok, NULL);
  ASSERT_EQ (tok->type, CPP_NAME);
  ASSERT_TOKEN_AS_TEXT_EQ (parser, tok, "test_name");
  ASSERT_TOKEN_LOC_EQ (tok, tmp.get_filename (), 1, 1, 9);

  tok = cpp_get_token_with_location (parser, &loc);
  ASSERT_NE (tok, NULL);
  ASSERT_EQ (tok->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (parser, tok, "\"test literal\"");
  ASSERT_TOKEN_LOC_EQ (tok, tmp.get_filename (), 2, 35, 48);

  tok = cpp_get_token_with_location (parser, &loc);
  ASSERT_NE (tok, NULL);
  ASSERT_EQ (tok->type, CPP_NUMBER);
  ASSERT_TOKEN_AS_TEXT_EQ (parser, tok, "42");
  ASSERT_TOKEN_LOC_EQ (tok, tmp.get_filename (), 4, 4, 5);

  tok = cpp_get_token_with_location (parser, &loc);
  ASSERT_NE (tok, NULL);
  ASSERT_EQ (tok->type, CPP_EOF);

  cpp_finish (parser, NULL);
  cpp_destroy (parser);
}

/* Forward decls.  */

class lexer_test;
class lexer_test_options;

/* A class for specifying options of a lexer_test.
   The "apply" vfunc is called during the lexer_test constructor.  */

class lexer_test_options
{
 public:
  virtual void apply (lexer_test &) = 0;
};

/* Wrapper around an cpp_reader *, which calls cpp_finish and cpp_destroy
   in its dtor.

   This is needed by struct lexer_test to ensure that the cleanup of the
   cpp_reader happens *after* the cleanup of the temp_source_file.  */

class cpp_reader_ptr
{
 public:
  cpp_reader_ptr (cpp_reader *ptr) : m_ptr (ptr) {}

  ~cpp_reader_ptr ()
  {
    cpp_finish (m_ptr, NULL);
    cpp_destroy (m_ptr);
  }

  operator cpp_reader * () const { return m_ptr; }

 private:
  cpp_reader *m_ptr;
};

/* A struct for writing lexer tests.  */

class lexer_test
{
public:
  lexer_test (const line_table_case &case_, const char *content,
	      lexer_test_options *options);
  ~lexer_test ();

  const cpp_token *get_token ();

  /* The ordering of these fields matters.
     The line_table_test must be first, since the cpp_reader_ptr
     uses it.
     The cpp_reader must be cleaned up *after* the temp_source_file
     since the filenames in input.c's input cache are owned by the
     cpp_reader; in particular, when ~temp_source_file evicts the
     filename the filenames must still be alive.  */
  line_table_test m_ltt;
  cpp_reader_ptr m_parser;
  temp_source_file m_tempfile;
  string_concat_db m_concats;
  bool m_implicitly_expect_EOF;
};

/* Use an EBCDIC encoding for the execution charset, specifically
   IBM1047-encoded (aka "EBCDIC 1047", or "Code page 1047").

   This exercises iconv integration within libcpp.
   Not every build of iconv supports the given charset,
   so we need to flag this error and handle it gracefully.  */

class ebcdic_execution_charset : public lexer_test_options
{
 public:
  ebcdic_execution_charset () : m_num_iconv_errors (0)
    {
      gcc_assert (s_singleton == NULL);
      s_singleton = this;
    }
  ~ebcdic_execution_charset ()
    {
      gcc_assert (s_singleton == this);
      s_singleton = NULL;
    }

  void apply (lexer_test &test) FINAL OVERRIDE
  {
    cpp_options *cpp_opts = cpp_get_options (test.m_parser);
    cpp_opts->narrow_charset = "IBM1047";

    cpp_callbacks *callbacks = cpp_get_callbacks (test.m_parser);
    callbacks->diagnostic = on_diagnostic;
  }

  static bool on_diagnostic (cpp_reader *pfile ATTRIBUTE_UNUSED,
			     enum cpp_diagnostic_level level ATTRIBUTE_UNUSED,
			     enum cpp_warning_reason reason ATTRIBUTE_UNUSED,
			     rich_location *richloc ATTRIBUTE_UNUSED,
			     const char *msgid, va_list *ap ATTRIBUTE_UNUSED)
    ATTRIBUTE_FPTR_PRINTF(5,0)
  {
    gcc_assert (s_singleton);
    /* Avoid exgettext from picking this up, it is translated in libcpp.  */
    const char *msg = "conversion from %s to %s not supported by iconv";
#ifdef ENABLE_NLS
    msg = dgettext ("cpplib", msg);
#endif
    /* Detect and record errors emitted by libcpp/charset.c:init_iconv_desc
       when the local iconv build doesn't support the conversion.  */
    if (strcmp (msgid, msg) == 0)
      {
	s_singleton->m_num_iconv_errors++;
	return true;
      }

    /* Otherwise, we have an unexpected error.  */
    abort ();
  }

  bool iconv_errors_occurred_p () const { return m_num_iconv_errors > 0; }

 private:
  static ebcdic_execution_charset *s_singleton;
  int m_num_iconv_errors;
};

ebcdic_execution_charset *ebcdic_execution_charset::s_singleton;

/* A lexer_test_options subclass that records a list of diagnostic
   messages emitted by the lexer.  */

class lexer_diagnostic_sink : public lexer_test_options
{
 public:
  lexer_diagnostic_sink ()
  {
    gcc_assert (s_singleton == NULL);
    s_singleton = this;
  }
  ~lexer_diagnostic_sink ()
  {
    gcc_assert (s_singleton == this);
    s_singleton = NULL;

    int i;
    char *str;
    FOR_EACH_VEC_ELT (m_diagnostics, i, str)
      free (str);
  }

  void apply (lexer_test &test) FINAL OVERRIDE
  {
    cpp_callbacks *callbacks = cpp_get_callbacks (test.m_parser);
    callbacks->diagnostic = on_diagnostic;
  }

  static bool on_diagnostic (cpp_reader *pfile ATTRIBUTE_UNUSED,
			     enum cpp_diagnostic_level level ATTRIBUTE_UNUSED,
			     enum cpp_warning_reason reason ATTRIBUTE_UNUSED,
			     rich_location *richloc ATTRIBUTE_UNUSED,
			     const char *msgid, va_list *ap)
    ATTRIBUTE_FPTR_PRINTF(5,0)
  {
    char *msg = xvasprintf (msgid, *ap);
    s_singleton->m_diagnostics.safe_push (msg);
    return true;
  }

  auto_vec<char *> m_diagnostics;

 private:
  static lexer_diagnostic_sink *s_singleton;
};

lexer_diagnostic_sink *lexer_diagnostic_sink::s_singleton;

/* Constructor.  Override line_table with a new instance based on CASE_,
   and write CONTENT to a tempfile.  Create a cpp_reader, and use it to
   start parsing the tempfile.  */

lexer_test::lexer_test (const line_table_case &case_, const char *content,
			lexer_test_options *options)
: m_ltt (case_),
  m_parser (cpp_create_reader (CLK_GNUC99, NULL, line_table)),
  /* Create a tempfile and write the text to it.  */
  m_tempfile (SELFTEST_LOCATION, ".c", content),
  m_concats (),
  m_implicitly_expect_EOF (true)
{
  if (options)
    options->apply (*this);

  cpp_init_iconv (m_parser);

  /* Parse the file.  */
  const char *fname = cpp_read_main_file (m_parser,
					  m_tempfile.get_filename ());
  ASSERT_NE (fname, NULL);
}

/* Destructor.  By default, verify that the next token in m_parser is EOF.  */

lexer_test::~lexer_test ()
{
  location_t loc;
  const cpp_token *tok;

  if (m_implicitly_expect_EOF)
    {
      tok = cpp_get_token_with_location (m_parser, &loc);
      ASSERT_NE (tok, NULL);
      ASSERT_EQ (tok->type, CPP_EOF);
    }
}

/* Get the next token from m_parser.  */

const cpp_token *
lexer_test::get_token ()
{
  location_t loc;
  const cpp_token *tok;

  tok = cpp_get_token_with_location (m_parser, &loc);
  ASSERT_NE (tok, NULL);
  return tok;
}

/* Verify that locations within string literals are correctly handled.  */

/* Verify get_source_range_for_substring for token(s) at STRLOC,
   using the string concatenation database for TEST.

   Assert that the character at index IDX is on EXPECTED_LINE,
   and that it begins at column EXPECTED_START_COL and ends at
   EXPECTED_FINISH_COL (unless the locations are beyond
   LINE_MAP_MAX_LOCATION_WITH_COLS, in which case don't check their
   columns).  */

static void
assert_char_at_range (const location &loc,
		      lexer_test& test,
		      location_t strloc, enum cpp_ttype type, int idx,
		      int expected_line, int expected_start_col,
		      int expected_finish_col)
{
  cpp_reader *pfile = test.m_parser;
  string_concat_db *concats = &test.m_concats;

  source_range actual_range = source_range();
  const char *err
    = get_source_range_for_char (pfile, concats, strloc, type, idx,
				 &actual_range);
  if (should_have_column_data_p (strloc))
    ASSERT_EQ_AT (loc, NULL, err);
  else
    {
      ASSERT_STREQ_AT (loc,
		       "range starts after LINE_MAP_MAX_LOCATION_WITH_COLS",
		       err);
      return;
    }

  int actual_start_line = LOCATION_LINE (actual_range.m_start);
  ASSERT_EQ_AT (loc, expected_line, actual_start_line);
  int actual_finish_line = LOCATION_LINE (actual_range.m_finish);
  ASSERT_EQ_AT (loc, expected_line, actual_finish_line);

  if (should_have_column_data_p (actual_range.m_start))
    {
      int actual_start_col = LOCATION_COLUMN (actual_range.m_start);
      ASSERT_EQ_AT (loc, expected_start_col, actual_start_col);
    }
  if (should_have_column_data_p (actual_range.m_finish))
    {
      int actual_finish_col = LOCATION_COLUMN (actual_range.m_finish);
      ASSERT_EQ_AT (loc, expected_finish_col, actual_finish_col);
    }
}

/* Macro for calling assert_char_at_range, supplying SELFTEST_LOCATION for
   the effective location of any errors.  */

#define ASSERT_CHAR_AT_RANGE(LEXER_TEST, STRLOC, TYPE, IDX, EXPECTED_LINE, \
			     EXPECTED_START_COL, EXPECTED_FINISH_COL)	\
  assert_char_at_range (SELFTEST_LOCATION, (LEXER_TEST), (STRLOC), (TYPE), \
			(IDX), (EXPECTED_LINE), (EXPECTED_START_COL), \
			(EXPECTED_FINISH_COL))

/* Verify get_num_source_ranges_for_substring for token(s) at STRLOC,
   using the string concatenation database for TEST.

   Assert that the token(s) at STRLOC contain EXPECTED_NUM_RANGES.  */

static void
assert_num_substring_ranges (const location &loc,
			     lexer_test& test,
			     location_t strloc,
			     enum cpp_ttype type,
			     int expected_num_ranges)
{
  cpp_reader *pfile = test.m_parser;
  string_concat_db *concats = &test.m_concats;

  int actual_num_ranges = -1;
  const char *err
    = get_num_source_ranges_for_substring (pfile, concats, strloc, type,
					   &actual_num_ranges);
  if (should_have_column_data_p (strloc))
    ASSERT_EQ_AT (loc, NULL, err);
  else
    {
      ASSERT_STREQ_AT (loc,
		       "range starts after LINE_MAP_MAX_LOCATION_WITH_COLS",
		       err);
      return;
    }
  ASSERT_EQ_AT (loc, expected_num_ranges, actual_num_ranges);
}

/* Macro for calling assert_num_substring_ranges, supplying
   SELFTEST_LOCATION for the effective location of any errors.  */

#define ASSERT_NUM_SUBSTRING_RANGES(LEXER_TEST, STRLOC, TYPE, \
				    EXPECTED_NUM_RANGES)		\
  assert_num_substring_ranges (SELFTEST_LOCATION, (LEXER_TEST), (STRLOC), \
			       (TYPE), (EXPECTED_NUM_RANGES))


/* Verify that get_num_source_ranges_for_substring for token(s) at STRLOC
   returns an error (using the string concatenation database for TEST).  */

static void
assert_has_no_substring_ranges (const location &loc,
				lexer_test& test,
				location_t strloc,
				enum cpp_ttype type,
				const char *expected_err)
{
  cpp_reader *pfile = test.m_parser;
  string_concat_db *concats = &test.m_concats;
  cpp_substring_ranges ranges;
  const char *actual_err
    = get_substring_ranges_for_loc (pfile, concats, strloc,
				    type, ranges);
  if (should_have_column_data_p (strloc))
    ASSERT_STREQ_AT (loc, expected_err, actual_err);
  else
    ASSERT_STREQ_AT (loc,
		     "range starts after LINE_MAP_MAX_LOCATION_WITH_COLS",
		     actual_err);
}

#define ASSERT_HAS_NO_SUBSTRING_RANGES(LEXER_TEST, STRLOC, TYPE, ERR)    \
    assert_has_no_substring_ranges (SELFTEST_LOCATION, (LEXER_TEST), \
				    (STRLOC), (TYPE), (ERR))

/* Lex a simple string literal.  Verify the substring location data, before
   and after running cpp_interpret_string on it.  */

static void
test_lexer_string_locations_simple (const line_table_case &case_)
{
  /* Digits 0-9 (with 0 at column 10), the simple way.
     ....................000000000.11111111112.2222222223333333333
     ....................123456789.01234567890.1234567890123456789
     We add a trailing comment to ensure that we correctly locate
     the end of the string literal token.  */
  const char *content = "        \"0123456789\" /* not a string */\n";
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back, with the correct
     location information.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "\"0123456789\"");
  ASSERT_TOKEN_LOC_EQ (tok, test.m_tempfile.get_filename (), 1, 9, 20);

  /* At this point in lexing, the quote characters are treated as part of
     the string (they are stripped off by cpp_interpret_string).  */

  ASSERT_EQ (tok->val.str.len, 12);

  /* Verify that cpp_interpret_string works.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);
  ASSERT_STREQ ("0123456789", (const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  /* Verify ranges of individual characters.  This no longer includes the
     opening quote, but does include the closing quote.  */
  for (int i = 0; i <= 10; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1,
			  10 + i, 10 + i);

  ASSERT_NUM_SUBSTRING_RANGES (test, tok->src_loc, type, 11);
}

/* As test_lexer_string_locations_simple, but use an EBCDIC execution
   encoding.  */

static void
test_lexer_string_locations_ebcdic (const line_table_case &case_)
{
  /* EBCDIC support requires iconv.  */
  if (!HAVE_ICONV)
    return;

  /* Digits 0-9 (with 0 at column 10), the simple way.
     ....................000000000.11111111112.2222222223333333333
     ....................123456789.01234567890.1234567890123456789
     We add a trailing comment to ensure that we correctly locate
     the end of the string literal token.  */
  const char *content = "        \"0123456789\" /* not a string */\n";
  ebcdic_execution_charset use_ebcdic;
  lexer_test test (case_, content, &use_ebcdic);

  /* Verify that we get the expected token back, with the correct
     location information.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "\"0123456789\"");
  ASSERT_TOKEN_LOC_EQ (tok, test.m_tempfile.get_filename (), 1, 9, 20);

  /* At this point in lexing, the quote characters are treated as part of
     the string (they are stripped off by cpp_interpret_string).  */

  ASSERT_EQ (tok->val.str.len, 12);

  /* The remainder of the test requires an iconv implementation that
     can convert from UTF-8 to the EBCDIC encoding requested above.  */
  if (use_ebcdic.iconv_errors_occurred_p ())
    return;

  /* Verify that cpp_interpret_string works.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);
  /* We should now have EBCDIC-encoded text, specifically
     IBM1047-encoded (aka "EBCDIC 1047", or "Code page 1047").
     The digits 0-9 are encoded as 240-249 i.e. 0xf0-0xf9.  */
  ASSERT_STREQ ("\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9",
		(const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  /* Verify that we don't attempt to record substring location information
     for such cases.  */
  ASSERT_HAS_NO_SUBSTRING_RANGES
    (test, tok->src_loc, type,
     "execution character set != source character set");
}

/* Lex a string literal containing a hex-escaped character.
   Verify the substring location data, before and after running
   cpp_interpret_string on it.  */

static void
test_lexer_string_locations_hex (const line_table_case &case_)
{
  /* Digits 0-9, expressing digit 5 in ASCII as "\x35"
     and with a space in place of digit 6, to terminate the escaped
     hex code.
     ....................000000000.111111.11112222.
     ....................123456789.012345.67890123.  */
  const char *content = "        \"01234\\x35 789\"\n";
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back, with the correct
     location information.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "\"01234\\x35 789\"");
  ASSERT_TOKEN_LOC_EQ (tok, test.m_tempfile.get_filename (), 1, 9, 23);

  /* At this point in lexing, the quote characters are treated as part of
     the string (they are stripped off by cpp_interpret_string).  */
  ASSERT_EQ (tok->val.str.len, 15);

  /* Verify that cpp_interpret_string works.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);
  ASSERT_STREQ ("012345 789", (const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  /* Verify ranges of individual characters.  This no longer includes the
     opening quote, but does include the closing quote.  */
  for (int i = 0; i <= 4; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 10 + i, 10 + i);
  ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, 5, 1, 15, 18);
  for (int i = 6; i <= 10; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 13 + i, 13 + i);

  ASSERT_NUM_SUBSTRING_RANGES (test, tok->src_loc, type, 11);
}

/* Lex a string literal containing an octal-escaped character.
   Verify the substring location data after running cpp_interpret_string
   on it.  */

static void
test_lexer_string_locations_oct (const line_table_case &case_)
{
  /* Digits 0-9, expressing digit 5 in ASCII as "\065"
     and with a space in place of digit 6, to terminate the escaped
     octal code.
     ....................000000000.111111.11112222.2222223333333333444
     ....................123456789.012345.67890123.4567890123456789012  */
  const char *content = "        \"01234\\065 789\" /* not a string */\n";
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back, with the correct
     location information.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "\"01234\\065 789\"");

  /* Verify that cpp_interpret_string works.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);
  ASSERT_STREQ ("012345 789", (const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  /* Verify ranges of individual characters.  This no longer includes the
     opening quote, but does include the closing quote.  */
  for (int i = 0; i < 5; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 10 + i, 10 + i);
  ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, 5, 1, 15, 18);
  for (int i = 6; i <= 10; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 13 + i, 13 + i);

  ASSERT_NUM_SUBSTRING_RANGES (test, tok->src_loc, type, 11);
}

/* Test of string literal containing letter escapes.  */

static void
test_lexer_string_locations_letter_escape_1 (const line_table_case &case_)
{
  /* The string "\tfoo\\\nbar" i.e. tab, "foo", backslash, newline, bar.
     .....................000000000.1.11111.1.1.11222.22222223333333
     .....................123456789.0.12345.6.7.89012.34567890123456.  */
  const char *content = ("        \"\\tfoo\\\\\\nbar\" /* non-str */\n");
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected tokens back.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "\"\\tfoo\\\\\\nbar\"");

  /* Verify ranges of individual characters. */
  /* "\t".  */
  ASSERT_CHAR_AT_RANGE (test, tok->src_loc, CPP_STRING,
			0, 1, 10, 11);
  /* "foo". */
  for (int i = 1; i <= 3; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, CPP_STRING,
			  i, 1, 11 + i, 11 + i);
  /* "\\" and "\n".  */
  ASSERT_CHAR_AT_RANGE (test, tok->src_loc, CPP_STRING,
			4, 1, 15, 16);
  ASSERT_CHAR_AT_RANGE (test, tok->src_loc, CPP_STRING,
			5, 1, 17, 18);

  /* "bar" and closing quote for nul-terminator.  */
  for (int i = 6; i <= 9; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, CPP_STRING,
			  i, 1, 13 + i, 13 + i);

  ASSERT_NUM_SUBSTRING_RANGES (test, tok->src_loc, CPP_STRING, 10);
}

/* Another test of a string literal containing a letter escape.
   Based on string seen in
     printf ("%-%\n");
   in gcc.dg/format/c90-printf-1.c.  */

static void
test_lexer_string_locations_letter_escape_2 (const line_table_case &case_)
{
  /* .....................000000000.1111.11.1111.22222222223.
     .....................123456789.0123.45.6789.01234567890.  */
  const char *content = ("        \"%-%\\n\" /* non-str */\n");
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected tokens back.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "\"%-%\\n\"");

  /* Verify ranges of individual characters. */
  /* "%-%".  */
  for (int i = 0; i < 3; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, CPP_STRING,
			  i, 1, 10 + i, 10 + i);
  /* "\n".  */
  ASSERT_CHAR_AT_RANGE (test, tok->src_loc, CPP_STRING,
			3, 1, 13, 14);

  /* Closing quote for nul-terminator.  */
  ASSERT_CHAR_AT_RANGE (test, tok->src_loc, CPP_STRING,
			4, 1, 15, 15);

  ASSERT_NUM_SUBSTRING_RANGES (test, tok->src_loc, CPP_STRING, 5);
}

/* Lex a string literal containing UCN 4 characters.
   Verify the substring location data after running cpp_interpret_string
   on it.  */

static void
test_lexer_string_locations_ucn4 (const line_table_case &case_)
{
  /* Digits 0-9, expressing digits 5 and 6 as Roman numerals expressed
     as UCN 4.
     ....................000000000.111111.111122.222222223.33333333344444
     ....................123456789.012345.678901.234567890.12345678901234  */
  const char *content = "        \"01234\\u2174\\u2175789\" /* non-str */\n";
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back, with the correct
     location information.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "\"01234\\u2174\\u2175789\"");

  /* Verify that cpp_interpret_string works.
     The string should be encoded in the execution character
     set.  Assuming that that is UTF-8, we should have the following:
     -----------  ----  -----  -------  ----------------
     Byte offset  Byte  Octal  Unicode  Source Column(s)
     -----------  ----  -----  -------  ----------------
     0            0x30         '0'      10
     1            0x31         '1'      11
     2            0x32         '2'      12
     3            0x33         '3'      13
     4            0x34         '4'      14
     5            0xE2  \342   U+2174   15-20
     6            0x85  \205    (cont)  15-20
     7            0xB4  \264    (cont)  15-20
     8            0xE2  \342   U+2175   21-26
     9            0x85  \205    (cont)  21-26
     10           0xB5  \265    (cont)  21-26
     11           0x37         '7'      27
     12           0x38         '8'      28
     13           0x39         '9'      29
     14           0x00                  30 (closing quote)
     -----------  ----  -----  -------  ---------------.  */

  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);
  ASSERT_STREQ ("01234\342\205\264\342\205\265789",
		(const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  /* Verify ranges of individual characters.  This no longer includes the
     opening quote, but does include the closing quote.
     '01234'.  */
  for (int i = 0; i <= 4; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 10 + i, 10 + i);
  /* U+2174.  */
  for (int i = 5; i <= 7; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 15, 20);
  /* U+2175.  */
  for (int i = 8; i <= 10; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 21, 26);
  /* '789' and nul terminator  */
  for (int i = 11; i <= 14; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 16 + i, 16 + i);

  ASSERT_NUM_SUBSTRING_RANGES (test, tok->src_loc, type, 15);
}

/* Lex a string literal containing UCN 8 characters.
   Verify the substring location data after running cpp_interpret_string
   on it.  */

static void
test_lexer_string_locations_ucn8 (const line_table_case &case_)
{
  /* Digits 0-9, expressing digits 5 and 6 as Roman numerals as UCN 8.
     ....................000000000.111111.1111222222.2222333333333.344444
     ....................123456789.012345.6789012345.6789012345678.901234  */
  const char *content = "        \"01234\\U00002174\\U00002175789\" /* */\n";
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back, with the correct
     location information.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok,
			   "\"01234\\U00002174\\U00002175789\"");

  /* Verify that cpp_interpret_string works.
     The UTF-8 encoding of the string is identical to that from
     the ucn4 testcase above; the only difference is the column
     locations.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);
  ASSERT_STREQ ("01234\342\205\264\342\205\265789",
		(const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  /* Verify ranges of individual characters.  This no longer includes the
     opening quote, but does include the closing quote.
     '01234'.  */
  for (int i = 0; i <= 4; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 10 + i, 10 + i);
  /* U+2174.  */
  for (int i = 5; i <= 7; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 15, 24);
  /* U+2175.  */
  for (int i = 8; i <= 10; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 25, 34);
  /* '789' at columns 35-37  */
  for (int i = 11; i <= 13; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 24 + i, 24 + i);
  /* Closing quote/nul-terminator at column 38.  */
  ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, 14, 1, 38, 38);

  ASSERT_NUM_SUBSTRING_RANGES (test, tok->src_loc, type, 15);
}

/* Fetch a big-endian 32-bit value and convert to host endianness.  */

static uint32_t
uint32_from_big_endian (const uint32_t *ptr_be_value)
{
  const unsigned char *buf = (const unsigned char *)ptr_be_value;
  return (((uint32_t) buf[0] << 24)
	  | ((uint32_t) buf[1] << 16)
	  | ((uint32_t) buf[2] << 8)
	  | (uint32_t) buf[3]);
}

/* Lex a wide string literal and verify that attempts to read substring
   location data from it fail gracefully.  */

static void
test_lexer_string_locations_wide_string (const line_table_case &case_)
{
  /* Digits 0-9.
     ....................000000000.11111111112.22222222233333
     ....................123456789.01234567890.12345678901234  */
  const char *content = "       L\"0123456789\" /* non-str */\n";
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back, with the correct
     location information.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_WSTRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "L\"0123456789\"");

  /* Verify that cpp_interpret_string works, using CPP_WSTRING.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_WSTRING;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);
  /* The cpp_reader defaults to big-endian with
     CHAR_BIT * sizeof (int) for the wchar_precision, so dst_string should
     now be encoded as UTF-32BE.  */
  const uint32_t *be32_chars = (const uint32_t *)dst_string.text;
  ASSERT_EQ ('0', uint32_from_big_endian (&be32_chars[0]));
  ASSERT_EQ ('5', uint32_from_big_endian (&be32_chars[5]));
  ASSERT_EQ ('9', uint32_from_big_endian (&be32_chars[9]));
  ASSERT_EQ (0, uint32_from_big_endian (&be32_chars[10]));
  free (const_cast <unsigned char *> (dst_string.text));

  /* We don't yet support generating substring location information
     for L"" strings.  */
  ASSERT_HAS_NO_SUBSTRING_RANGES
    (test, tok->src_loc, type,
     "execution character set != source character set");
}

/* Fetch a big-endian 16-bit value and convert to host endianness.  */

static uint16_t
uint16_from_big_endian (const uint16_t *ptr_be_value)
{
  const unsigned char *buf = (const unsigned char *)ptr_be_value;
  return ((uint16_t) buf[0] << 8) | (uint16_t) buf[1];
}

/* Lex a u"" string literal and verify that attempts to read substring
   location data from it fail gracefully.  */

static void
test_lexer_string_locations_string16 (const line_table_case &case_)
{
  /* Digits 0-9.
     ....................000000000.11111111112.22222222233333
     ....................123456789.01234567890.12345678901234  */
  const char *content = "       u\"0123456789\" /* non-str */\n";
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back, with the correct
     location information.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING16);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "u\"0123456789\"");

  /* Verify that cpp_interpret_string works, using CPP_STRING16.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING16;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);

  /* The cpp_reader defaults to big-endian, so dst_string should
     now be encoded as UTF-16BE.  */
  const uint16_t *be16_chars = (const uint16_t *)dst_string.text;
  ASSERT_EQ ('0', uint16_from_big_endian (&be16_chars[0]));
  ASSERT_EQ ('5', uint16_from_big_endian (&be16_chars[5]));
  ASSERT_EQ ('9', uint16_from_big_endian (&be16_chars[9]));
  ASSERT_EQ (0, uint16_from_big_endian (&be16_chars[10]));
  free (const_cast <unsigned char *> (dst_string.text));

  /* We don't yet support generating substring location information
     for L"" strings.  */
  ASSERT_HAS_NO_SUBSTRING_RANGES
    (test, tok->src_loc, type,
     "execution character set != source character set");
}

/* Lex a U"" string literal and verify that attempts to read substring
   location data from it fail gracefully.  */

static void
test_lexer_string_locations_string32 (const line_table_case &case_)
{
  /* Digits 0-9.
     ....................000000000.11111111112.22222222233333
     ....................123456789.01234567890.12345678901234  */
  const char *content = "       U\"0123456789\" /* non-str */\n";
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back, with the correct
     location information.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING32);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "U\"0123456789\"");

  /* Verify that cpp_interpret_string works, using CPP_STRING32.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING32;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);

  /* The cpp_reader defaults to big-endian, so dst_string should
     now be encoded as UTF-32BE.  */
  const uint32_t *be32_chars = (const uint32_t *)dst_string.text;
  ASSERT_EQ ('0', uint32_from_big_endian (&be32_chars[0]));
  ASSERT_EQ ('5', uint32_from_big_endian (&be32_chars[5]));
  ASSERT_EQ ('9', uint32_from_big_endian (&be32_chars[9]));
  ASSERT_EQ (0, uint32_from_big_endian (&be32_chars[10]));
  free (const_cast <unsigned char *> (dst_string.text));

  /* We don't yet support generating substring location information
     for L"" strings.  */
  ASSERT_HAS_NO_SUBSTRING_RANGES
    (test, tok->src_loc, type,
     "execution character set != source character set");
}

/* Lex a u8-string literal.
   Verify the substring location data after running cpp_interpret_string
   on it.  */

static void
test_lexer_string_locations_u8 (const line_table_case &case_)
{
  /* Digits 0-9.
     ....................000000000.11111111112.22222222233333
     ....................123456789.01234567890.12345678901234  */
  const char *content = "      u8\"0123456789\" /* non-str */\n";
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back, with the correct
     location information.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_UTF8STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "u8\"0123456789\"");

  /* Verify that cpp_interpret_string works.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);
  ASSERT_STREQ ("0123456789", (const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  /* Verify ranges of individual characters.  This no longer includes the
     opening quote, but does include the closing quote.  */
  for (int i = 0; i <= 10; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 10 + i, 10 + i);
}

/* Lex a string literal containing UTF-8 source characters.
   Verify the substring location data after running cpp_interpret_string
   on it.  */

static void
test_lexer_string_locations_utf8_source (const line_table_case &case_)
{
 /* This string literal is written out to the source file as UTF-8,
    and is of the form "before mojibake after", where "mojibake"
    is written as the following four unicode code points:
       U+6587 CJK UNIFIED IDEOGRAPH-6587
       U+5B57 CJK UNIFIED IDEOGRAPH-5B57
       U+5316 CJK UNIFIED IDEOGRAPH-5316
       U+3051 HIRAGANA LETTER KE.
     Each of these is 3 bytes wide when encoded in UTF-8, whereas the
     "before" and "after" are 1 byte per unicode character.

     The numbering shown are "columns", which are *byte* numbers within
     the line, rather than unicode character numbers.

     .................... 000000000.1111111.
     .................... 123456789.0123456.  */
  const char *content = ("        \"before "
			 /* U+6587 CJK UNIFIED IDEOGRAPH-6587
			      UTF-8: 0xE6 0x96 0x87
			      C octal escaped UTF-8: \346\226\207
			    "column" numbers: 17-19.  */
			 "\346\226\207"

			 /* U+5B57 CJK UNIFIED IDEOGRAPH-5B57
			      UTF-8: 0xE5 0xAD 0x97
			      C octal escaped UTF-8: \345\255\227
			    "column" numbers: 20-22.  */
			 "\345\255\227"

			 /* U+5316 CJK UNIFIED IDEOGRAPH-5316
			      UTF-8: 0xE5 0x8C 0x96
			      C octal escaped UTF-8: \345\214\226
			    "column" numbers: 23-25.  */
			 "\345\214\226"

			 /* U+3051 HIRAGANA LETTER KE
			      UTF-8: 0xE3 0x81 0x91
			      C octal escaped UTF-8: \343\201\221
			    "column" numbers: 26-28.  */
			 "\343\201\221"

			 /* column numbers 29 onwards
			  2333333.33334444444444
			  9012345.67890123456789. */
			 " after\" /* non-str */\n");
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back, with the correct
     location information.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ
    (test.m_parser, tok,
     "\"before \346\226\207\345\255\227\345\214\226\343\201\221 after\"");

  /* Verify that cpp_interpret_string works.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);
  ASSERT_STREQ
    ("before \346\226\207\345\255\227\345\214\226\343\201\221 after",
     (const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  /* Verify ranges of individual characters.  This no longer includes the
     opening quote, but does include the closing quote.
     Assuming that both source and execution encodings are UTF-8, we have
     a run of 25 octets in each, plus the NUL terminator.  */
  for (int i = 0; i < 25; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, i, 1, 10 + i, 10 + i);
  /* NUL-terminator should use the closing quote at column 35.  */
  ASSERT_CHAR_AT_RANGE (test, tok->src_loc, type, 25, 1, 35, 35);

  ASSERT_NUM_SUBSTRING_RANGES (test, tok->src_loc, type, 26);
}

/* Test of string literal concatenation.  */

static void
test_lexer_string_locations_concatenation_1 (const line_table_case &case_)
{
  /* Digits 0-9.
     .....................000000000.111111.11112222222222
     .....................123456789.012345.67890123456789.  */
  const char *content = ("        \"01234\" /* non-str */\n"
			 "        \"56789\" /* non-str */\n");
  lexer_test test (case_, content, NULL);

  location_t input_locs[2];

  /* Verify that we get the expected tokens back.  */
  auto_vec <cpp_string> input_strings;
  const cpp_token *tok_a = test.get_token ();
  ASSERT_EQ (tok_a->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok_a, "\"01234\"");
  input_strings.safe_push (tok_a->val.str);
  input_locs[0] = tok_a->src_loc;

  const cpp_token *tok_b = test.get_token ();
  ASSERT_EQ (tok_b->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok_b, "\"56789\"");
  input_strings.safe_push (tok_b->val.str);
  input_locs[1] = tok_b->src_loc;

  /* Verify that cpp_interpret_string works.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser,
				      input_strings.address (), 2,
				      &dst_string, type);
  ASSERT_TRUE (result);
  ASSERT_STREQ ("0123456789", (const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  /* Simulate c-lex.c's lex_string in order to record concatenation.  */
  test.m_concats.record_string_concatenation (2, input_locs);

  location_t initial_loc = input_locs[0];

  /* "01234" on line 1.  */
  for (int i = 0; i <= 4; i++)
    ASSERT_CHAR_AT_RANGE (test, initial_loc, type, i, 1, 10 + i, 10 + i);
  /* "56789" in line 2, plus its closing quote for the nul terminator.  */
  for (int i = 5; i <= 10; i++)
    ASSERT_CHAR_AT_RANGE (test, initial_loc, type, i, 2, 5 + i, 5 + i);

  ASSERT_NUM_SUBSTRING_RANGES (test, initial_loc, type, 11);
}

/* Another test of string literal concatenation.  */

static void
test_lexer_string_locations_concatenation_2 (const line_table_case &case_)
{
  /* Digits 0-9.
     .....................000000000.111.11111112222222
     .....................123456789.012.34567890123456.  */
  const char *content = ("        \"01\" /* non-str */\n"
			 "        \"23\" /* non-str */\n"
			 "        \"45\" /* non-str */\n"
			 "        \"67\" /* non-str */\n"
			 "        \"89\" /* non-str */\n");
  lexer_test test (case_, content, NULL);

  auto_vec <cpp_string> input_strings;
  location_t input_locs[5];

  /* Verify that we get the expected tokens back.  */
  for (int i = 0; i < 5; i++)
    {
      const cpp_token *tok = test.get_token ();
      ASSERT_EQ (tok->type, CPP_STRING);
      input_strings.safe_push (tok->val.str);
      input_locs[i] = tok->src_loc;
    }

  /* Verify that cpp_interpret_string works.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser,
				      input_strings.address (), 5,
				      &dst_string, type);
  ASSERT_TRUE (result);
  ASSERT_STREQ ("0123456789", (const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  /* Simulate c-lex.c's lex_string in order to record concatenation.  */
  test.m_concats.record_string_concatenation (5, input_locs);

  location_t initial_loc = input_locs[0];

  /* Within ASSERT_CHAR_AT_RANGE (actually assert_char_at_range), we can
     detect if the initial loc is after LINE_MAP_MAX_LOCATION_WITH_COLS
     and expect get_source_range_for_substring to fail.
     However, for a string concatenation test, we can have a case
     where the initial string is fully before LINE_MAP_MAX_LOCATION_WITH_COLS,
     but subsequent strings can be after it.
     Attempting to detect this within assert_char_at_range
     would overcomplicate the logic for the common test cases, so
     we detect it here.  */
  if (should_have_column_data_p (input_locs[0])
      && !should_have_column_data_p (input_locs[4]))
    {
      /* Verify that get_source_range_for_substring gracefully rejects
	 this case.  */
      source_range actual_range;
      const char *err
	= get_source_range_for_char (test.m_parser, &test.m_concats,
				     initial_loc, type, 0, &actual_range);
      ASSERT_STREQ ("range starts after LINE_MAP_MAX_LOCATION_WITH_COLS", err);
      return;
    }

  for (int i = 0; i < 5; i++)
    for (int j = 0; j < 2; j++)
      ASSERT_CHAR_AT_RANGE (test, initial_loc, type, (i * 2) + j,
			    i + 1, 10 + j, 10 + j);

  /* NUL-terminator should use the final closing quote at line 5 column 12.  */
  ASSERT_CHAR_AT_RANGE (test, initial_loc, type, 10, 5, 12, 12);

  ASSERT_NUM_SUBSTRING_RANGES (test, initial_loc, type, 11);
}

/* Another test of string literal concatenation, this time combined with
   various kinds of escaped characters.  */

static void
test_lexer_string_locations_concatenation_3 (const line_table_case &case_)
{
  /* Digits 0-9, expressing digit 5 in ASCII as hex "\x35"
     digit 6 in ASCII as octal "\066", concatenating multiple strings.  */
  const char *content
    /* .000000000.111111.111.1.2222.222.2.2233.333.3333.34444444444555
       .123456789.012345.678.9.0123.456.7.8901.234.5678.90123456789012. */
    = ("        \"01234\"  \"\\x35\"  \"\\066\"  \"789\" /* non-str */\n");
  lexer_test test (case_, content, NULL);

  auto_vec <cpp_string> input_strings;
  location_t input_locs[4];

  /* Verify that we get the expected tokens back.  */
  for (int i = 0; i < 4; i++)
    {
      const cpp_token *tok = test.get_token ();
      ASSERT_EQ (tok->type, CPP_STRING);
      input_strings.safe_push (tok->val.str);
      input_locs[i] = tok->src_loc;
    }

  /* Verify that cpp_interpret_string works.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser,
				      input_strings.address (), 4,
				      &dst_string, type);
  ASSERT_TRUE (result);
  ASSERT_STREQ ("0123456789", (const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  /* Simulate c-lex.c's lex_string in order to record concatenation.  */
  test.m_concats.record_string_concatenation (4, input_locs);

  location_t initial_loc = input_locs[0];

  for (int i = 0; i <= 4; i++)
    ASSERT_CHAR_AT_RANGE (test, initial_loc, type, i, 1, 10 + i, 10 + i);
  ASSERT_CHAR_AT_RANGE (test, initial_loc, type, 5, 1, 19, 22);
  ASSERT_CHAR_AT_RANGE (test, initial_loc, type, 6, 1, 27, 30);
  for (int i = 7; i <= 9; i++)
    ASSERT_CHAR_AT_RANGE (test, initial_loc, type, i, 1, 28 + i, 28 + i);

  /* NUL-terminator should use the location of the final closing quote.  */
  ASSERT_CHAR_AT_RANGE (test, initial_loc, type, 10, 1, 38, 38);

  ASSERT_NUM_SUBSTRING_RANGES (test, initial_loc, type, 11);
}

/* Test of string literal in a macro.  */

static void
test_lexer_string_locations_macro (const line_table_case &case_)
{
  /* Digits 0-9.
     .....................0000000001111111111.22222222223.
     .....................1234567890123456789.01234567890.  */
  const char *content = ("#define MACRO     \"0123456789\" /* non-str */\n"
			 "  MACRO");
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected tokens back.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_PADDING);

  tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "\"0123456789\"");

  /* Verify ranges of individual characters.  We ought to
     see columns within the macro definition.  */
  for (int i = 0; i <= 10; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, CPP_STRING,
			  i, 1, 20 + i, 20 + i);

  ASSERT_NUM_SUBSTRING_RANGES (test, tok->src_loc, CPP_STRING, 11);

  tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_PADDING);
}

/* Test of stringification of a macro argument.  */

static void
test_lexer_string_locations_stringified_macro_argument
  (const line_table_case &case_)
{
  /* .....................000000000111111111122222222223.
     .....................123456789012345678901234567890.  */
  const char *content = ("#define MACRO(X) #X /* non-str */\n"
			 "MACRO(foo)\n");
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_PADDING);

  tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "\"foo\"");

  /* We don't support getting the location of a stringified macro
     argument.  Verify that it fails gracefully.  */
  ASSERT_HAS_NO_SUBSTRING_RANGES (test, tok->src_loc, CPP_STRING,
				  "cpp_interpret_string_1 failed");

  tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_PADDING);

  tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_PADDING);
}

/* Ensure that we are fail gracefully if something attempts to pass
   in a location that isn't a string literal token.  Seen on this code:

     const char a[] = " %d ";
     __builtin_printf (a, 0.5);
                       ^

   when c-format.c erroneously used the indicated one-character
   location as the format string location, leading to a read past the
   end of a string buffer in cpp_interpret_string_1.  */

static void
test_lexer_string_locations_non_string (const line_table_case &case_)
{
  /* .....................000000000111111111122222222223.
     .....................123456789012345678901234567890.  */
  const char *content = ("         a\n");
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_NAME);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "a");

  /* At this point, libcpp is attempting to interpret the name as a
     string literal, despite it not starting with a quote.  We don't detect
     that, but we should at least fail gracefully.  */
  ASSERT_HAS_NO_SUBSTRING_RANGES (test, tok->src_loc, CPP_STRING,
				  "cpp_interpret_string_1 failed");
}

/* Ensure that we can read substring information for a token which
   starts in one linemap and ends in another .  Adapted from
   gcc.dg/cpp/pr69985.c.  */

static void
test_lexer_string_locations_long_line (const line_table_case &case_)
{
  /* .....................000000.000111111111
     .....................123456.789012346789.  */
  const char *content = ("/* A very long line, so that we start a new line map.  */\n"
			 "     \"0123456789012345678901234567890123456789"
			 "0123456789012345678901234567890123456789"
			 "0123456789012345678901234567890123456789"
			 "0123456789\"\n");

  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);

  if (!should_have_column_data_p (line_table->highest_location))
    return;

  /* Verify ranges of individual characters.  */
  ASSERT_NUM_SUBSTRING_RANGES (test, tok->src_loc, CPP_STRING, 131);
  for (int i = 0; i < 131; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, CPP_STRING,
			  i, 2, 7 + i, 7 + i);
}

/* Test of locations within a raw string that doesn't contain a newline.  */

static void
test_lexer_string_locations_raw_string_one_line (const line_table_case &case_)
{
  /* .....................00.0000000111111111122.
     .....................12.3456789012345678901.  */
  const char *content = ("R\"foo(0123456789)foo\"\n");
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);

  /* Verify that cpp_interpret_string works.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);
  ASSERT_STREQ ("0123456789", (const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  if (!should_have_column_data_p (line_table->highest_location))
    return;

  /* 0-9, plus the nil terminator.  */
  ASSERT_NUM_SUBSTRING_RANGES (test, tok->src_loc, CPP_STRING, 11);
  for (int i = 0; i < 11; i++)
    ASSERT_CHAR_AT_RANGE (test, tok->src_loc, CPP_STRING,
			  i, 1, 7 + i, 7 + i);
}

/* Test of locations within a raw string that contains a newline.  */

static void
test_lexer_string_locations_raw_string_multiline (const line_table_case &case_)
{
  /* .....................00.0000.
     .....................12.3456.  */
  const char *content = ("R\"foo(\n"
  /* .....................00000.
     .....................12345.  */
			 "hello\n"
			 "world\n"
  /* .....................00000.
     .....................12345.  */
			 ")foo\"\n");
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected token back.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_STRING);

  /* Verify that cpp_interpret_string works.  */
  cpp_string dst_string;
  const enum cpp_ttype type = CPP_STRING;
  bool result = cpp_interpret_string (test.m_parser, &tok->val.str, 1,
				      &dst_string, type);
  ASSERT_TRUE (result);
  ASSERT_STREQ ("\nhello\nworld\n", (const char *)dst_string.text);
  free (const_cast <unsigned char *> (dst_string.text));

  if (!should_have_column_data_p (line_table->highest_location))
    return;

  /* Currently we don't support locations within raw strings that
     contain newlines.  */
  ASSERT_HAS_NO_SUBSTRING_RANGES (test, tok->src_loc, tok->type,
				  "range endpoints are on different lines");
}

/* Test of parsing an unterminated raw string.  */

static void
test_lexer_string_locations_raw_string_unterminated (const line_table_case &case_)
{
  const char *content = "R\"ouch()ouCh\" /* etc */";

  lexer_diagnostic_sink diagnostics;
  lexer_test test (case_, content, &diagnostics);
  test.m_implicitly_expect_EOF = false;

  /* Attempt to parse the raw string.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_EOF);

  ASSERT_EQ (1, diagnostics.m_diagnostics.length ());
  /* We expect the message "unterminated raw string"
     in the "cpplib" translation domain.
     It's not clear that dgettext is available on all supported hosts,
     so this assertion is commented-out for now.
       ASSERT_STREQ (dgettext ("cpplib", "unterminated raw string"),
                     diagnostics.m_diagnostics[0]);
  */
}

/* Test of lexing char constants.  */

static void
test_lexer_char_constants (const line_table_case &case_)
{
  /* Various char constants.
     .....................0000000001111111111.22222222223.
     .....................1234567890123456789.01234567890.  */
  const char *content = ("         'a'\n"
			 "        u'a'\n"
			 "        U'a'\n"
			 "        L'a'\n"
			 "         'abc'\n");
  lexer_test test (case_, content, NULL);

  /* Verify that we get the expected tokens back.  */
  /* 'a'.  */
  const cpp_token *tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_CHAR);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "'a'");

  unsigned int chars_seen;
  int unsignedp;
  cppchar_t cc = cpp_interpret_charconst (test.m_parser, tok,
					  &chars_seen, &unsignedp);
  ASSERT_EQ (cc, 'a');
  ASSERT_EQ (chars_seen, 1);

  /* u'a'.  */
  tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_CHAR16);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "u'a'");

  /* U'a'.  */
  tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_CHAR32);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "U'a'");

  /* L'a'.  */
  tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_WCHAR);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "L'a'");

  /* 'abc' (c-char-sequence).  */
  tok = test.get_token ();
  ASSERT_EQ (tok->type, CPP_CHAR);
  ASSERT_TOKEN_AS_TEXT_EQ (test.m_parser, tok, "'abc'");
}
/* A table of interesting location_t values, giving one axis of our test
   matrix.  */

static const location_t boundary_locations[] = {
  /* Zero means "don't override the default values for a new line_table".  */
  0,

  /* An arbitrary non-zero value that isn't close to one of
     the boundary values below.  */
  0x10000,

  /* Values near LINE_MAP_MAX_LOCATION_WITH_PACKED_RANGES.  */
  LINE_MAP_MAX_LOCATION_WITH_PACKED_RANGES - 0x100,
  LINE_MAP_MAX_LOCATION_WITH_PACKED_RANGES - 1,
  LINE_MAP_MAX_LOCATION_WITH_PACKED_RANGES,
  LINE_MAP_MAX_LOCATION_WITH_PACKED_RANGES + 1,
  LINE_MAP_MAX_LOCATION_WITH_PACKED_RANGES + 0x100,

  /* Values near LINE_MAP_MAX_LOCATION_WITH_COLS.  */
  LINE_MAP_MAX_LOCATION_WITH_COLS - 0x100,
  LINE_MAP_MAX_LOCATION_WITH_COLS - 1,
  LINE_MAP_MAX_LOCATION_WITH_COLS,
  LINE_MAP_MAX_LOCATION_WITH_COLS + 1,
  LINE_MAP_MAX_LOCATION_WITH_COLS + 0x100,
};

/* Run TESTCASE multiple times, once for each case in our test matrix.  */

void
for_each_line_table_case (void (*testcase) (const line_table_case &))
{
  /* As noted above in the description of struct line_table_case,
     we want to explore a test matrix of interesting line_table
     situations, running various selftests for each case within the
     matrix.  */

  /* Run all tests with:
     (a) line_table->default_range_bits == 0, and
     (b) line_table->default_range_bits == 5.  */
  int num_cases_tested = 0;
  for (int default_range_bits = 0; default_range_bits <= 5;
       default_range_bits += 5)
    {
      /* ...and use each of the "interesting" location values as
	 the starting location within line_table.  */
      const int num_boundary_locations
	= sizeof (boundary_locations) / sizeof (boundary_locations[0]);
      for (int loc_idx = 0; loc_idx < num_boundary_locations; loc_idx++)
	{
	  line_table_case c (default_range_bits, boundary_locations[loc_idx]);

	  testcase (c);

	  num_cases_tested++;
	}
    }

  /* Verify that we fully covered the test matrix.  */
  ASSERT_EQ (num_cases_tested, 2 * 12);
}

/* Verify that when presented with a consecutive pair of locations with
   a very large line offset, we don't attempt to consolidate them into
   a single ordinary linemap where the line offsets within the line map
   would lead to overflow (PR lto/88147).  */

static void
test_line_offset_overflow ()
{
  line_table_test ltt (line_table_case (5, 0));

  linemap_add (line_table, LC_ENTER, false, "foo.c", 0);
  linemap_line_start (line_table, 1, 100);
  location_t loc_a = linemap_line_start (line_table, 2578, 255);
  assert_loceq ("foo.c", 2578, 0, loc_a);

  const line_map_ordinary *ordmap_a = LINEMAPS_LAST_ORDINARY_MAP (line_table);
  ASSERT_EQ (ordmap_a->m_column_and_range_bits, 13);
  ASSERT_EQ (ordmap_a->m_range_bits, 5);

  location_t loc_b = linemap_line_start (line_table, 404198, 512);
  assert_loceq ("foo.c", 404198, 0, loc_b);

  /* We should have started a new linemap, rather than attempting to store
     a very large line offset.  */
  const line_map_ordinary *ordmap_b = LINEMAPS_LAST_ORDINARY_MAP (line_table);
  ASSERT_NE (ordmap_a, ordmap_b);
}

void test_cpp_utf8 ()
{
  /* Verify that wcwidth of invalid UTF-8 or control bytes is 1.  */
  {
    int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8);
    ASSERT_EQ (8, w_bad);
    int w_ctrl = cpp_display_width ("\r\t\n\v\0\1", 6);
    ASSERT_EQ (6, w_ctrl);
  }

  /* Verify that wcwidth of valid UTF-8 is as expected.  */
  {
    const int w_pi = cpp_display_width ("\xcf\x80", 2);
    ASSERT_EQ (1, w_pi);
    const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4);
    ASSERT_EQ (2, w_emoji);
    const int w_umlaut_precomposed = cpp_display_width ("\xc3\xbf", 2);
    ASSERT_EQ (1, w_umlaut_precomposed);
    const int w_umlaut_combining = cpp_display_width ("y\xcc\x88", 3);
    ASSERT_EQ (1, w_umlaut_combining);
    const int w_han = cpp_display_width ("\xe4\xb8\xba", 3);
    ASSERT_EQ (2, w_han);
    const int w_ascii = cpp_display_width ("GCC", 3);
    ASSERT_EQ (3, w_ascii);
    const int w_mixed = cpp_display_width ("\xcf\x80 = 3.14 \xf0\x9f\x98\x82"
					   "\x9f! \xe4\xb8\xba y\xcc\x88", 24);
    ASSERT_EQ (18, w_mixed);
  }

  /* Verify that cpp_byte_column_to_display_column can go past the end,
     and similar edge cases.  */
  {
    const char *str
      /* Display columns.
         111111112345  */
      = "\xcf\x80 abc";
      /* 111122223456
	 Byte columns.  */

    ASSERT_EQ (5, cpp_display_width (str, 6));
    ASSERT_EQ (105, cpp_byte_column_to_display_column (str, 6, 106));
    ASSERT_EQ (10000, cpp_byte_column_to_display_column (NULL, 0, 10000));
    ASSERT_EQ (0, cpp_byte_column_to_display_column (NULL, 10000, 0));
  }

  /* Verify that cpp_display_column_to_byte_column can go past the end,
     and similar edge cases, and check invertibility.  */
  {
    const char *str
      /* Display columns.
	 000000000000000000000000000000000000011
	 111111112222222234444444455555555678901  */
      = "\xf0\x9f\x98\x82 \xf0\x9f\x98\x82 hello";
      /* 000000000000000000000000000000000111111
	 111122223333444456666777788889999012345
	 Byte columns.  */
    ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2));
    ASSERT_EQ (15, cpp_display_column_to_byte_column (str, 15, 11));
    ASSERT_EQ (115, cpp_display_column_to_byte_column (str, 15, 111));
    ASSERT_EQ (10000, cpp_display_column_to_byte_column (NULL, 0, 10000));
    ASSERT_EQ (0, cpp_display_column_to_byte_column (NULL, 10000, 0));

    /* Verify that we do not interrupt a UTF-8 sequence.  */
    ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1));

    for (int byte_col = 1; byte_col <= 15; ++byte_col)
      {
	const int disp_col = cpp_byte_column_to_display_column (str, 15,
								byte_col);
	const int byte_col2 = cpp_display_column_to_byte_column (str, 15,
								 disp_col);

	/* If we ask for the display column in the middle of a UTF-8
	   sequence, it will return the length of the partial sequence,
	   matching the behavior of GCC before display column support.
	   Otherwise check the round trip was successful.  */
	if (byte_col < 4)
	  ASSERT_EQ (byte_col, disp_col);
	else if (byte_col >= 6 && byte_col < 9)
	  ASSERT_EQ (3 + (byte_col - 5), disp_col);
	else
	  ASSERT_EQ (byte_col2, byte_col);
      }
  }

}

/* Run all of the selftests within this file.  */

void
input_c_tests ()
{
  test_linenum_comparisons ();
  test_should_have_column_data_p ();
  test_unknown_location ();
  test_builtins ();
  for_each_line_table_case (test_make_location_nonpure_range_endpoints);

  for_each_line_table_case (test_accessing_ordinary_linemaps);
  for_each_line_table_case (test_lexer);
  for_each_line_table_case (test_lexer_string_locations_simple);
  for_each_line_table_case (test_lexer_string_locations_ebcdic);
  for_each_line_table_case (test_lexer_string_locations_hex);
  for_each_line_table_case (test_lexer_string_locations_oct);
  for_each_line_table_case (test_lexer_string_locations_letter_escape_1);
  for_each_line_table_case (test_lexer_string_locations_letter_escape_2);
  for_each_line_table_case (test_lexer_string_locations_ucn4);
  for_each_line_table_case (test_lexer_string_locations_ucn8);
  for_each_line_table_case (test_lexer_string_locations_wide_string);
  for_each_line_table_case (test_lexer_string_locations_string16);
  for_each_line_table_case (test_lexer_string_locations_string32);
  for_each_line_table_case (test_lexer_string_locations_u8);
  for_each_line_table_case (test_lexer_string_locations_utf8_source);
  for_each_line_table_case (test_lexer_string_locations_concatenation_1);
  for_each_line_table_case (test_lexer_string_locations_concatenation_2);
  for_each_line_table_case (test_lexer_string_locations_concatenation_3);
  for_each_line_table_case (test_lexer_string_locations_macro);
  for_each_line_table_case (test_lexer_string_locations_stringified_macro_argument);
  for_each_line_table_case (test_lexer_string_locations_non_string);
  for_each_line_table_case (test_lexer_string_locations_long_line);
  for_each_line_table_case (test_lexer_string_locations_raw_string_one_line);
  for_each_line_table_case (test_lexer_string_locations_raw_string_multiline);
  for_each_line_table_case (test_lexer_string_locations_raw_string_unterminated);
  for_each_line_table_case (test_lexer_char_constants);

  test_reading_source_line ();

  test_line_offset_overflow ();

  test_cpp_utf8 ();
}

} // namespace selftest

#endif /* CHECKING_P */