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
|
import argparse
import bisect
import collections
import copy
import glob
import os
import re
import subprocess
import sys
import shlex
from typing import List, Mapping, Set
##### Common utilities for update_*test_checks.py
_verbose = False
_prefix_filecheck_ir_name = ""
"""
Version changelog:
1: Initial version, used by tests that don't specify --version explicitly.
2: --function-signature is now enabled by default and also checks return
type/attributes.
3: Opening parenthesis of function args is kept on the first LABEL line
in case arguments are split to a separate SAME line.
4: --check-globals now has a third option ('smart'). The others are now called
'none' and 'all'. 'smart' is the default.
5: Basic block labels are matched by FileCheck expressions
"""
DEFAULT_VERSION = 5
SUPPORTED_ANALYSES = {
"Branch Probability Analysis",
"Cost Model Analysis",
"Dependence Analysis",
"Loop Access Analysis",
"Scalar Evolution Analysis",
}
class Regex(object):
"""Wrap a compiled regular expression object to allow deep copy of a regexp.
This is required for the deep copy done in do_scrub.
"""
def __init__(self, regex):
self.regex = regex
def __deepcopy__(self, memo):
result = copy.copy(self)
result.regex = self.regex
return result
def search(self, line):
return self.regex.search(line)
def sub(self, repl, line):
return self.regex.sub(repl, line)
def pattern(self):
return self.regex.pattern
def flags(self):
return self.regex.flags
class Filter(Regex):
"""Augment a Regex object with a flag indicating whether a match should be
added (!is_filter_out) or removed (is_filter_out) from the generated checks.
"""
def __init__(self, regex, is_filter_out, is_filter_out_after):
super(Filter, self).__init__(regex)
if is_filter_out and is_filter_out_after:
raise ValueError("cannot use both --filter-out and --filter-out-after")
self.is_filter_out = is_filter_out
self.is_filter_out_after = is_filter_out_after
def __deepcopy__(self, memo):
result = copy.deepcopy(super(Filter, self), memo)
result.is_filter_out = copy.deepcopy(self.is_filter_out, memo)
result.is_filter_out_after = copy.deepcopy(self.is_filter_out_after, memo)
return result
def parse_commandline_args(parser):
class RegexAction(argparse.Action):
"""Add a regular expression option value to a list of regular expressions.
This compiles the expression, wraps it in a Regex and adds it to the option
value list."""
def __init__(self, option_strings, dest, nargs=None, **kwargs):
if nargs is not None:
raise ValueError("nargs not allowed")
super(RegexAction, self).__init__(option_strings, dest, **kwargs)
def do_call(self, namespace, values, flags):
value_list = getattr(namespace, self.dest)
if value_list is None:
value_list = []
try:
value_list.append(Regex(re.compile(values, flags)))
except re.error as error:
raise ValueError(
"{}: Invalid regular expression '{}' ({})".format(
option_string, error.pattern, error.msg
)
)
setattr(namespace, self.dest, value_list)
def __call__(self, parser, namespace, values, option_string=None):
self.do_call(namespace, values, 0)
class FilterAction(RegexAction):
"""Add a filter to a list of filter option values."""
def __init__(self, option_strings, dest, nargs=None, **kwargs):
super(FilterAction, self).__init__(option_strings, dest, nargs, **kwargs)
def __call__(self, parser, namespace, values, option_string=None):
super(FilterAction, self).__call__(parser, namespace, values, option_string)
value_list = getattr(namespace, self.dest)
is_filter_out = option_string == "--filter-out"
is_filter_out_after = option_string == "--filter-out-after"
value_list[-1] = Filter(
value_list[-1].regex, is_filter_out, is_filter_out_after
)
setattr(namespace, self.dest, value_list)
filter_group = parser.add_argument_group(
"filtering",
"""Filters are applied to each output line according to the order given. The
first matching filter terminates filter processing for that current line.""",
)
filter_group.add_argument(
"--filter",
action=FilterAction,
dest="filters",
metavar="REGEX",
help="Only include lines matching REGEX (may be specified multiple times)",
)
filter_group.add_argument(
"--filter-out",
action=FilterAction,
dest="filters",
metavar="REGEX",
help="Exclude lines matching REGEX",
)
filter_group.add_argument(
"--filter-out-after",
action=FilterAction,
dest="filters",
metavar="REGEX",
help="Exclude all lines within a given function after line matching REGEX",
)
parser.add_argument(
"--include-generated-funcs",
action="store_true",
help="Output checks for functions not in source",
)
parser.add_argument(
"-v", "--verbose", action="store_true", help="Show verbose output"
)
parser.add_argument(
"-u",
"--update-only",
action="store_true",
help="Only update test if it was already autogened",
)
parser.add_argument(
"--force-update",
action="store_true",
help="Update test even if it was autogened by a different script",
)
parser.add_argument(
"--enable",
action="store_true",
dest="enabled",
default=True,
help="Activate CHECK line generation from this point forward",
)
parser.add_argument(
"--disable",
action="store_false",
dest="enabled",
help="Deactivate CHECK line generation from this point forward",
)
parser.add_argument(
"--replace-value-regex",
nargs="+",
default=[],
help="List of regular expressions to replace matching value names",
)
parser.add_argument(
"--prefix-filecheck-ir-name",
default="",
help="Add a prefix to FileCheck IR value names to avoid conflicts with scripted names",
)
parser.add_argument(
"--global-value-regex",
nargs="+",
default=[],
help="List of regular expressions that a global value declaration must match to generate a check (has no effect if checking globals is not enabled)",
)
parser.add_argument(
"--global-hex-value-regex",
nargs="+",
default=[],
help="List of regular expressions such that, for matching global value declarations, literal integer values should be encoded in hex in the associated FileCheck directives",
)
# FIXME: in 3.9, we can use argparse.BooleanOptionalAction. At that point,
# we need to rename the flag to just -generate-body-for-unused-prefixes.
parser.add_argument(
"--no-generate-body-for-unused-prefixes",
action="store_false",
dest="gen_unused_prefix_body",
default=True,
help="Generate a function body that always matches for unused prefixes. This is useful when unused prefixes are desired, and it avoids needing to annotate each FileCheck as allowing them.",
)
# This is the default when regenerating existing tests. The default when
# generating new tests is determined by DEFAULT_VERSION.
parser.add_argument(
"--version", type=int, default=1, help="The version of output format"
)
args = parser.parse_args()
# TODO: This should not be handled differently from the other options
global _verbose, _global_value_regex, _global_hex_value_regex
_verbose = args.verbose
_global_value_regex = args.global_value_regex
_global_hex_value_regex = args.global_hex_value_regex
return args
def parse_args(parser, argv):
args = parser.parse_args(argv)
if args.version >= 2:
args.function_signature = True
# TODO: This should not be handled differently from the other options
global _verbose, _global_value_regex, _global_hex_value_regex
_verbose = args.verbose
_global_value_regex = args.global_value_regex
_global_hex_value_regex = args.global_hex_value_regex
if "check_globals" in args and args.check_globals == "default":
args.check_globals = "none" if args.version < 4 else "smart"
return args
class InputLineInfo(object):
def __init__(self, line, line_number, args, argv):
self.line = line
self.line_number = line_number
self.args = args
self.argv = argv
class TestInfo(object):
def __init__(
self,
test,
parser,
script_name,
input_lines,
args,
argv,
comment_prefix,
argparse_callback,
):
self.parser = parser
self.argparse_callback = argparse_callback
self.path = test
self.args = args
if args.prefix_filecheck_ir_name:
global _prefix_filecheck_ir_name
_prefix_filecheck_ir_name = args.prefix_filecheck_ir_name
self.argv = argv
self.input_lines = input_lines
self.run_lines = find_run_lines(test, self.input_lines)
self.comment_prefix = comment_prefix
if self.comment_prefix is None:
if self.path.endswith(".mir") or self.path.endswith(".txt"):
self.comment_prefix = "#"
elif self.path.endswith(".s"):
self.comment_prefix = "//"
else:
self.comment_prefix = ";"
self.autogenerated_note_prefix = self.comment_prefix + " " + UTC_ADVERT
self.test_autogenerated_note = self.autogenerated_note_prefix + script_name
self.test_autogenerated_note += get_autogennote_suffix(parser, self.args)
self.test_unused_note = (
self.comment_prefix + self.comment_prefix + " " + UNUSED_NOTE
)
def ro_iterlines(self):
for line_num, input_line in enumerate(self.input_lines):
args, argv = check_for_command(
input_line, self.parser, self.args, self.argv, self.argparse_callback
)
yield InputLineInfo(input_line, line_num, args, argv)
def iterlines(self, output_lines):
output_lines.append(self.test_autogenerated_note)
for line_info in self.ro_iterlines():
input_line = line_info.line
# Discard any previous script advertising.
if input_line.startswith(self.autogenerated_note_prefix):
continue
self.args = line_info.args
self.argv = line_info.argv
if not self.args.enabled:
output_lines.append(input_line)
continue
yield line_info
def get_checks_for_unused_prefixes(
self, run_list, used_prefixes: List[str]
) -> List[str]:
run_list = [element for element in run_list if element[0] is not None]
unused_prefixes = set(
[prefix for sublist in run_list for prefix in sublist[0]]
).difference(set(used_prefixes))
ret = []
if not unused_prefixes:
return ret
ret.append(self.test_unused_note)
for unused in sorted(unused_prefixes):
ret.append(
"{comment} {prefix}: {match_everything}".format(
comment=self.comment_prefix,
prefix=unused,
match_everything=r"""{{.*}}""",
)
)
return ret
def itertests(
test_patterns, parser, script_name, comment_prefix=None, argparse_callback=None
):
for pattern in test_patterns:
# On Windows we must expand the patterns ourselves.
tests_list = glob.glob(pattern)
if not tests_list:
warn("Test file pattern '%s' was not found. Ignoring it." % (pattern,))
continue
for test in tests_list:
with open(test) as f:
input_lines = [l.rstrip() for l in f]
first_line = input_lines[0] if input_lines else ""
if UTC_AVOID in first_line:
warn("Skipping test that must not be autogenerated: " + test)
continue
is_regenerate = UTC_ADVERT in first_line
# If we're generating a new test, set the default version to the latest.
argv = sys.argv[:]
if not is_regenerate:
argv.insert(1, "--version=" + str(DEFAULT_VERSION))
args = parse_args(parser, argv[1:])
if argparse_callback is not None:
argparse_callback(args)
if is_regenerate:
if script_name not in first_line and not args.force_update:
warn(
"Skipping test which wasn't autogenerated by " + script_name,
test,
)
continue
args, argv = check_for_command(
first_line, parser, args, argv, argparse_callback
)
elif args.update_only:
assert UTC_ADVERT not in first_line
warn("Skipping test which isn't autogenerated: " + test)
continue
final_input_lines = []
for l in input_lines:
if UNUSED_NOTE in l:
break
final_input_lines.append(l)
yield TestInfo(
test,
parser,
script_name,
final_input_lines,
args,
argv,
comment_prefix,
argparse_callback,
)
def should_add_line_to_output(
input_line,
prefix_set,
*,
skip_global_checks=False,
skip_same_checks=False,
comment_marker=";",
):
# Skip any blank comment lines in the IR.
if not skip_global_checks and input_line.strip() == comment_marker:
return False
# Skip a special double comment line we use as a separator.
if input_line.strip() == comment_marker + SEPARATOR:
return False
# Skip any blank lines in the IR.
# if input_line.strip() == '':
# return False
# And skip any CHECK lines. We're building our own.
m = CHECK_RE.match(input_line)
if m and m.group(1) in prefix_set:
if skip_same_checks and CHECK_SAME_RE.match(input_line):
# The previous CHECK line was removed, so don't leave this dangling
return False
if skip_global_checks:
# Skip checks only if they are of global value definitions
global_ir_value_re = re.compile(r"(\[\[|@)", flags=(re.M))
is_global = global_ir_value_re.search(input_line)
return not is_global
return False
return True
def collect_original_check_lines(ti: TestInfo, prefix_set: set):
"""
Collect pre-existing check lines into a dictionary `result` which is
returned.
result[func_name][prefix] is filled with a list of right-hand-sides of check
lines.
"""
result = collections.defaultdict(lambda: {})
current_prefix = None
current_function = None
for input_line_info in ti.ro_iterlines():
input_line = input_line_info.line
if input_line.lstrip().startswith(";"):
m = CHECK_RE.match(input_line)
if m is not None:
prefix = m.group(1)
check_kind = m.group(2)
line = input_line[m.end() :].strip()
if prefix != current_prefix:
current_function = None
current_prefix = None
if check_kind not in ["LABEL", "SAME"]:
if current_function is not None:
current_function.append(line)
continue
if check_kind == "SAME":
continue
if check_kind == "LABEL":
m = IR_FUNCTION_LABEL_RE.match(line)
if m is not None:
func_name = m.group(1)
if (
ti.args.function is not None
and func_name != ti.args.function
):
# When filtering on a specific function, skip all others.
continue
current_prefix = prefix
current_function = result[func_name][prefix] = []
continue
current_function = None
return result
# Perform lit-like substitutions
def getSubstitutions(sourcepath):
sourcedir = os.path.dirname(sourcepath)
return [
("%s", sourcepath),
("%S", sourcedir),
("%p", sourcedir),
("%{pathsep}", os.pathsep),
]
def applySubstitutions(s, substitutions):
for a, b in substitutions:
s = s.replace(a, b)
return s
# Invoke the tool that is being tested.
def invoke_tool(exe, cmd_args, ir, preprocess_cmd=None, verbose=False):
with open(ir) as ir_file:
substitutions = getSubstitutions(ir)
# TODO Remove the str form which is used by update_test_checks.py and
# update_llc_test_checks.py
# The safer list form is used by update_cc_test_checks.py
if preprocess_cmd:
# Allow pre-processing the IR file (e.g. using sed):
assert isinstance(
preprocess_cmd, str
) # TODO: use a list instead of using shell
preprocess_cmd = applySubstitutions(preprocess_cmd, substitutions).strip()
if verbose:
print(
"Pre-processing input file: ",
ir,
" with command '",
preprocess_cmd,
"'",
sep="",
file=sys.stderr,
)
pp = subprocess.Popen(
preprocess_cmd,
shell=True,
stdin=subprocess.DEVNULL,
stdout=subprocess.PIPE,
)
ir_file = pp.stdout
if isinstance(cmd_args, list):
args = [applySubstitutions(a, substitutions) for a in cmd_args]
stdout = subprocess.check_output([exe] + args, stdin=ir_file)
else:
stdout = subprocess.check_output(
exe + " " + applySubstitutions(cmd_args, substitutions),
shell=True,
stdin=ir_file,
)
if sys.version_info[0] > 2:
# FYI, if you crashed here with a decode error, your run line probably
# results in bitcode or other binary format being written to the pipe.
# For an opt test, you probably want to add -S or -disable-output.
stdout = stdout.decode()
# Fix line endings to unix CR style.
return stdout.replace("\r\n", "\n")
##### LLVM IR parser
RUN_LINE_RE = re.compile(r"^\s*(?://|[;#])\s*RUN:\s*(.*)$")
CHECK_PREFIX_RE = re.compile(r"--?check-prefix(?:es)?[= ](\S+)")
PREFIX_RE = re.compile("^[a-zA-Z0-9_-]+$")
CHECK_RE = re.compile(
r"^\s*(?://|[;#])\s*([^:]+?)(?:-(NEXT|NOT|DAG|LABEL|SAME|EMPTY))?:"
)
CHECK_SAME_RE = re.compile(r"^\s*(?://|[;#])\s*([^:]+?)(?:-SAME)?:")
UTC_ARGS_KEY = "UTC_ARGS:"
UTC_ARGS_CMD = re.compile(r".*" + UTC_ARGS_KEY + r"\s*(?P<cmd>.*)\s*$")
UTC_ADVERT = "NOTE: Assertions have been autogenerated by "
UTC_AVOID = "NOTE: Do not autogenerate"
UNUSED_NOTE = "NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:"
DATA_LAYOUT_RE = re.compile(
r"target\s+datalayout\s+=\s+\"(?P<layout>.+)\"$", flags=(re.M | re.S)
)
OPT_FUNCTION_RE = re.compile(
r"^(\s*;\s*Function\sAttrs:\s(?P<attrs>[\w\s():,]+?))?\s*define\s+(?P<funcdef_attrs_and_ret>[^@]*)@(?P<func>[\w.$-]+?)\s*"
r"(?P<args_and_sig>\((\)|(.*?[\w.-]+?)\))[^{]*\{)\n(?P<body>.*?)^\}$",
flags=(re.M | re.S),
)
ANALYZE_FUNCTION_RE = re.compile(
r"^\s*\'(?P<analysis>[\w\s-]+?)\'\s+for\s+function\s+\'(?P<func>[\w.$-]+?)\':"
r"\s*\n(?P<body>.*)$",
flags=(re.X | re.S),
)
LOOP_PASS_DEBUG_RE = re.compile(
r"^\s*\'(?P<func>[\w.$-]+?)\'[^\n]*" r"\s*\n(?P<body>.*)$", flags=(re.X | re.S)
)
IR_FUNCTION_RE = re.compile(r'^\s*define\s+(?:internal\s+)?[^@]*@"?([\w.$-]+)"?\s*\(')
IR_FUNCTION_LABEL_RE = re.compile(
r'^\s*(?:define\s+(?:internal\s+)?[^@]*)?@"?([\w.$-]+)"?\s*\('
)
TRIPLE_IR_RE = re.compile(r'^\s*target\s+triple\s*=\s*"([^"]+)"$')
TRIPLE_ARG_RE = re.compile(r"-m?triple[= ]([^ ]+)")
MARCH_ARG_RE = re.compile(r"-march[= ]([^ ]+)")
DEBUG_ONLY_ARG_RE = re.compile(r"-debug-only[= ]([^ ]+)")
IS_DEBUG_RECORD_RE = re.compile(r"^(\s+)#dbg_")
SCRUB_LEADING_WHITESPACE_RE = re.compile(r"^(\s+)")
SCRUB_WHITESPACE_RE = re.compile(r"(?!^(| \w))[ \t]+", flags=re.M)
SCRUB_PRESERVE_LEADING_WHITESPACE_RE = re.compile(r"((?!^)[ \t]*(\S))[ \t]+")
SCRUB_TRAILING_WHITESPACE_RE = re.compile(r"[ \t]+$", flags=re.M)
SCRUB_TRAILING_WHITESPACE_TEST_RE = SCRUB_TRAILING_WHITESPACE_RE
SCRUB_TRAILING_WHITESPACE_AND_ATTRIBUTES_RE = re.compile(
r"([ \t]|(#[0-9]+))+$", flags=re.M
)
SCRUB_KILL_COMMENT_RE = re.compile(r"^ *#+ +kill:.*\n")
SCRUB_LOOP_COMMENT_RE = re.compile(
r"# =>This Inner Loop Header:.*|# in Loop:.*", flags=re.M
)
SCRUB_TAILING_COMMENT_TOKEN_RE = re.compile(r"(?<=\S)+[ \t]*#$", flags=re.M)
SEPARATOR = "."
def error(msg, test_file=None):
if test_file:
msg = "{}: {}".format(msg, test_file)
print("ERROR: {}".format(msg), file=sys.stderr)
def warn(msg, test_file=None):
if test_file:
msg = "{}: {}".format(msg, test_file)
print("WARNING: {}".format(msg), file=sys.stderr)
def debug(*args, **kwargs):
# Python2 does not allow def debug(*args, file=sys.stderr, **kwargs):
if "file" not in kwargs:
kwargs["file"] = sys.stderr
if _verbose:
print(*args, **kwargs)
def find_run_lines(test, lines):
debug("Scanning for RUN lines in test file:", test)
raw_lines = [m.group(1) for m in [RUN_LINE_RE.match(l) for l in lines] if m]
run_lines = [raw_lines[0]] if len(raw_lines) > 0 else []
for l in raw_lines[1:]:
if run_lines[-1].endswith("\\"):
run_lines[-1] = run_lines[-1].rstrip("\\") + " " + l
else:
run_lines.append(l)
debug("Found {} RUN lines in {}:".format(len(run_lines), test))
for l in run_lines:
debug(" RUN: {}".format(l))
return run_lines
def get_triple_from_march(march):
triples = {
"amdgcn": "amdgcn",
"r600": "r600",
"mips": "mips",
"nvptx64": "nvptx64",
"sparc": "sparc",
"hexagon": "hexagon",
"ve": "ve",
}
for prefix, triple in triples.items():
if march.startswith(prefix):
return triple
print("Cannot find a triple. Assume 'x86'", file=sys.stderr)
return "x86"
def get_globals_name_prefix(raw_tool_output):
m = DATA_LAYOUT_RE.search(raw_tool_output)
if not m:
return None
data_layout = m.group("layout")
idx = data_layout.find("m:")
if idx < 0:
return None
ch = data_layout[idx + 2]
return "_" if ch == "o" or ch == "x" else None
def apply_filters(line, filters):
has_filter = False
for f in filters:
if f.is_filter_out_after:
continue
if not f.is_filter_out:
has_filter = True
if f.search(line):
return False if f.is_filter_out else True
# If we only used filter-out, keep the line, otherwise discard it since no
# filter matched.
return False if has_filter else True
def has_filter_out_after(filters):
for f in filters:
if f.is_filter_out_after:
return True
return False
def filter_out_after(body, filters):
lines = []
for line in body.splitlines():
lines.append(line)
for f in filters:
if f.is_filter_out_after:
if f.search(line):
return lines
return lines
def do_filter(body, filters):
if not filters:
return body
filter_out_after_flag = has_filter_out_after(filters)
lines = []
if filter_out_after_flag:
lines = filter_out_after(body, filters)
else:
lines = body.splitlines()
return "\n".join(filter(lambda line: apply_filters(line, filters), lines))
def scrub_body(body):
# Scrub runs of whitespace out of the assembly, but leave the leading
# whitespace in place.
body = SCRUB_PRESERVE_LEADING_WHITESPACE_RE.sub(lambda m: m.group(2) + " ", body)
# Expand the tabs used for indentation.
body = str.expandtabs(body, 2)
# Strip trailing whitespace.
body = SCRUB_TRAILING_WHITESPACE_TEST_RE.sub(r"", body)
return body
def do_scrub(body, scrubber, scrubber_args, extra):
if scrubber_args:
local_args = copy.deepcopy(scrubber_args)
local_args[0].extra_scrub = extra
return scrubber(body, *local_args)
return scrubber(body, *scrubber_args)
# Build up a dictionary of all the function bodies.
class function_body(object):
def __init__(
self,
string,
extra,
funcdef_attrs_and_ret,
args_and_sig,
attrs,
func_name_separator,
ginfo,
):
self.scrub = string
self.extrascrub = extra
self.funcdef_attrs_and_ret = funcdef_attrs_and_ret
self.args_and_sig = args_and_sig
self.attrs = attrs
self.func_name_separator = func_name_separator
self._ginfo = ginfo
def is_same_except_arg_names(
self, extrascrub, funcdef_attrs_and_ret, args_and_sig, attrs
):
arg_names = set()
def drop_arg_names(match):
nameless_value = self._ginfo.get_nameless_value_from_match(match)
if nameless_value.check_key == "%":
arg_names.add(self._ginfo.get_name_from_match(match))
substitute = ""
else:
substitute = match.group(2)
return match.group(1) + substitute + match.group(match.lastindex)
def repl_arg_names(match):
nameless_value = self._ginfo.get_nameless_value_from_match(match)
if (
nameless_value.check_key == "%"
and self._ginfo.get_name_from_match(match) in arg_names
):
return match.group(1) + match.group(match.lastindex)
return match.group(1) + match.group(2) + match.group(match.lastindex)
if self.funcdef_attrs_and_ret != funcdef_attrs_and_ret:
return False
if self.attrs != attrs:
return False
regexp = self._ginfo.get_regexp()
ans0 = regexp.sub(drop_arg_names, self.args_and_sig)
ans1 = regexp.sub(drop_arg_names, args_and_sig)
if ans0 != ans1:
return False
if self._ginfo.is_asm():
# Check without replacements, the replacements are not applied to the
# body for backend checks.
return self.extrascrub == extrascrub
es0 = regexp.sub(repl_arg_names, self.extrascrub)
es1 = regexp.sub(repl_arg_names, extrascrub)
es0 = SCRUB_IR_COMMENT_RE.sub(r"", es0)
es1 = SCRUB_IR_COMMENT_RE.sub(r"", es1)
return es0 == es1
def __str__(self):
return self.scrub
class FunctionTestBuilder:
def __init__(self, run_list, flags, scrubber_args, path, ginfo):
self._verbose = flags.verbose
self._record_args = flags.function_signature
self._check_attributes = flags.check_attributes
# Strip double-quotes if input was read by UTC_ARGS
self._filters = (
list(
map(
lambda f: Filter(
re.compile(f.pattern().strip('"'), f.flags()),
f.is_filter_out,
f.is_filter_out_after,
),
flags.filters,
)
)
if flags.filters
else []
)
self._scrubber_args = scrubber_args
self._path = path
self._ginfo = ginfo
# Strip double-quotes if input was read by UTC_ARGS
self._replace_value_regex = list(
map(lambda x: x.strip('"'), flags.replace_value_regex)
)
self._func_dict = {}
self._func_order = {}
self._global_var_dict = {}
self._processed_prefixes = set()
for tuple in run_list:
for prefix in tuple[0]:
self._func_dict.update({prefix: dict()})
self._func_order.update({prefix: []})
self._global_var_dict.update({prefix: dict()})
def finish_and_get_func_dict(self):
for prefix in self.get_failed_prefixes():
warn(
"Prefix %s had conflicting output from different RUN lines for all functions in test %s"
% (
prefix,
self._path,
)
)
return self._func_dict
def func_order(self):
return self._func_order
def global_var_dict(self):
return self._global_var_dict
def is_filtered(self):
for f in self._filters:
if not f.is_filter_out_after:
return True
return False
def process_run_line(self, function_re, scrubber, raw_tool_output, prefixes):
build_global_values_dictionary(
self._global_var_dict, raw_tool_output, prefixes, self._ginfo
)
for m in function_re.finditer(raw_tool_output):
if not m:
continue
func = m.group("func")
body = m.group("body")
# func_name_separator is the string that is placed right after function name at the
# beginning of assembly function definition. In most assemblies, that is just a
# colon: `foo:`. But, for example, in nvptx it is a brace: `foo(`. If is_backend is
# False, just assume that separator is an empty string.
if self._ginfo.is_asm():
# Use ':' as default separator.
func_name_separator = (
m.group("func_name_separator")
if "func_name_separator" in m.groupdict()
else ":"
)
else:
func_name_separator = ""
attrs = m.group("attrs") if self._check_attributes else ""
funcdef_attrs_and_ret = (
m.group("funcdef_attrs_and_ret") if self._record_args else ""
)
# Determine if we print arguments, the opening brace, or nothing after the
# function name
if self._record_args and "args_and_sig" in m.groupdict():
args_and_sig = scrub_body(m.group("args_and_sig").strip())
elif "args_and_sig" in m.groupdict():
args_and_sig = "("
else:
args_and_sig = ""
filtered_body = do_filter(body, self._filters)
scrubbed_body = do_scrub(
filtered_body, scrubber, self._scrubber_args, extra=False
)
scrubbed_extra = do_scrub(
filtered_body, scrubber, self._scrubber_args, extra=True
)
if "analysis" in m.groupdict():
analysis = m.group("analysis")
if analysis not in SUPPORTED_ANALYSES:
warn("Unsupported analysis mode: %r!" % (analysis,))
if func.startswith("stress"):
# We only use the last line of the function body for stress tests.
scrubbed_body = "\n".join(scrubbed_body.splitlines()[-1:])
if self._verbose:
print("Processing function: " + func, file=sys.stderr)
for l in scrubbed_body.splitlines():
print(" " + l, file=sys.stderr)
for prefix in prefixes:
# Replace function names matching the regex.
for regex in self._replace_value_regex:
# Pattern that matches capture groups in the regex in leftmost order.
group_regex = re.compile(r"\(.*?\)")
# Replace function name with regex.
match = re.match(regex, func)
if match:
func_repl = regex
# Replace any capture groups with their matched strings.
for g in match.groups():
func_repl = group_regex.sub(
re.escape(g), func_repl, count=1
)
func = re.sub(func_repl, "{{" + func_repl + "}}", func)
# Replace all calls to regex matching functions.
matches = re.finditer(regex, scrubbed_body)
for match in matches:
func_repl = regex
# Replace any capture groups with their matched strings.
for g in match.groups():
func_repl = group_regex.sub(
re.escape(g), func_repl, count=1
)
# Substitute function call names that match the regex with the same
# capture groups set.
scrubbed_body = re.sub(
func_repl, "{{" + func_repl + "}}", scrubbed_body
)
if func in self._func_dict[prefix]:
if self._func_dict[prefix][func] is not None and (
str(self._func_dict[prefix][func]) != scrubbed_body
or self._func_dict[prefix][func].args_and_sig != args_and_sig
or self._func_dict[prefix][func].attrs != attrs
or self._func_dict[prefix][func].funcdef_attrs_and_ret
!= funcdef_attrs_and_ret
):
if self._func_dict[prefix][func].is_same_except_arg_names(
scrubbed_extra,
funcdef_attrs_and_ret,
args_and_sig,
attrs,
):
self._func_dict[prefix][func].scrub = scrubbed_extra
self._func_dict[prefix][func].args_and_sig = args_and_sig
else:
# This means a previous RUN line produced a body for this function
# that is different from the one produced by this current RUN line,
# so the body can't be common across RUN lines. We use None to
# indicate that.
self._func_dict[prefix][func] = None
else:
if prefix not in self._processed_prefixes:
self._func_dict[prefix][func] = function_body(
scrubbed_body,
scrubbed_extra,
funcdef_attrs_and_ret,
args_and_sig,
attrs,
func_name_separator,
self._ginfo,
)
self._func_order[prefix].append(func)
else:
# An earlier RUN line used this check prefixes but didn't produce
# a body for this function. This happens in Clang tests that use
# preprocesser directives to exclude individual functions from some
# RUN lines.
self._func_dict[prefix][func] = None
def processed_prefixes(self, prefixes):
"""
Mark a set of prefixes as having had at least one applicable RUN line fully
processed. This is used to filter out function bodies that don't have
outputs for all RUN lines.
"""
self._processed_prefixes.update(prefixes)
def get_failed_prefixes(self):
# This returns the list of those prefixes that failed to match any function,
# because there were conflicting bodies produced by different RUN lines, in
# all instances of the prefix.
for prefix in self._func_dict:
if self._func_dict[prefix] and (
not [
fct
for fct in self._func_dict[prefix]
if self._func_dict[prefix][fct] is not None
]
):
yield prefix
##### Generator of LLVM IR CHECK lines
SCRUB_IR_COMMENT_RE = re.compile(r"\s*;.*")
SCRUB_IR_FUNC_META_RE = re.compile(r"((?:\!(?!dbg\b)[a-zA-Z_]\w*(?:\s+![0-9]+)?)\s*)+")
# TODO: We should also derive check lines for global, debug, loop declarations, etc..
class NamelessValue:
"""
A NamelessValue object represents a type of value in the IR whose "name" we
generalize in the generated check lines; where the "name" could be an actual
name (as in e.g. `@some_global` or `%x`) or just a number (as in e.g. `%12`
or `!4`).
"""
def __init__(
self,
check_prefix,
check_key,
ir_prefix,
ir_regexp,
global_ir_rhs_regexp,
*,
is_before_functions=False,
is_number=False,
replace_number_with_counter=False,
match_literally=False,
interlaced_with_previous=False,
ir_suffix=r"",
):
self.check_prefix = check_prefix
self.check_key = check_key
self.ir_prefix = ir_prefix
self.ir_regexp = ir_regexp
self.ir_suffix = ir_suffix
self.global_ir_rhs_regexp = global_ir_rhs_regexp
self.is_before_functions = is_before_functions
self.is_number = is_number
# Some variable numbers (e.g. MCINST1234) will change based on unrelated
# modifications to LLVM, replace those with an incrementing counter.
self.replace_number_with_counter = replace_number_with_counter
self.match_literally = match_literally
self.interlaced_with_previous = interlaced_with_previous
self.variable_mapping = {}
# Return true if this kind of IR value is defined "locally" to functions,
# which we assume is only the case precisely for LLVM IR local values.
def is_local_def_ir_value(self):
return self.check_key == "%"
# Return the IR regexp we use for this kind or IR value, e.g., [\w.-]+? for locals
def get_ir_regex(self):
# for backwards compatibility we check locals with '.*'
if self.is_local_def_ir_value():
return ".*"
return self.ir_regexp
# Create a FileCheck variable name based on an IR name.
def get_value_name(self, var: str, check_prefix: str):
var = var.replace("!", "")
if self.replace_number_with_counter:
assert var
replacement = self.variable_mapping.get(var, None)
if replacement is None:
# Replace variable with an incrementing counter
replacement = str(len(self.variable_mapping) + 1)
self.variable_mapping[var] = replacement
var = replacement
# This is a nameless value, prepend check_prefix.
if var.isdigit():
var = check_prefix + var
else:
# This is a named value that clashes with the check_prefix, prepend with
# _prefix_filecheck_ir_name, if it has been defined.
if (
may_clash_with_default_check_prefix_name(check_prefix, var)
and _prefix_filecheck_ir_name
):
var = _prefix_filecheck_ir_name + var
var = var.replace(".", "_")
var = var.replace("-", "_")
return var.upper()
def get_affixes_from_match(self, match):
prefix = re.match(self.ir_prefix, match.group(2)).group(0)
suffix = re.search(self.ir_suffix + "$", match.group(2)).group(0)
return prefix, suffix
class GeneralizerInfo:
"""
A GeneralizerInfo object holds information about how check lines should be generalized
(e.g., variable names replaced by FileCheck meta variables) as well as per-test-file
state (e.g. information about IR global variables).
"""
MODE_IR = 0
MODE_ASM = 1
MODE_ANALYZE = 2
def __init__(
self,
version,
mode,
nameless_values: List[NamelessValue],
regexp_prefix,
regexp_suffix,
no_meta_details=False,
):
self._version = version
self._mode = mode
self._nameless_values = nameless_values
self._regexp_prefix = regexp_prefix
self._regexp_suffix = regexp_suffix
self._no_meta_details = no_meta_details
self._regexp, _ = self._build_regexp(False, False)
(
self._unstable_globals_regexp,
self._unstable_globals_values,
) = self._build_regexp(True, True)
def _build_regexp(self, globals_only, unstable_only):
matches = []
values = []
for nameless_value in self._nameless_values:
is_global = nameless_value.global_ir_rhs_regexp is not None
if globals_only and not is_global:
continue
if unstable_only and nameless_value.match_literally:
continue
match = f"(?:{nameless_value.ir_prefix}({nameless_value.ir_regexp}){nameless_value.ir_suffix})"
if self.is_ir() and not globals_only and is_global:
match = "^" + match
matches.append(match)
values.append(nameless_value)
regexp_string = r"|".join(matches)
return (
re.compile(
self._regexp_prefix + r"(" + regexp_string + r")" + self._regexp_suffix
),
values,
)
def get_version(self):
return self._version
def is_ir(self):
return self._mode == GeneralizerInfo.MODE_IR
def is_asm(self):
return self._mode == GeneralizerInfo.MODE_ASM
def is_analyze(self):
return self._mode == GeneralizerInfo.MODE_ANALYZE
def get_nameless_values(self):
return self._nameless_values
def get_regexp(self):
return self._regexp
def get_unstable_globals_regexp(self):
return self._unstable_globals_regexp
def no_meta_details(self):
return self._no_meta_details
# The entire match is group 0, the prefix has one group (=1), the entire
# IR_VALUE_REGEXP_STRING is one group (=2), and then the nameless values start.
FIRST_NAMELESS_GROUP_IN_MATCH = 3
def get_match_info(self, match):
"""
Returns (name, nameless_value) for the given match object
"""
if match.re == self._regexp:
values = self._nameless_values
else:
match.re == self._unstable_globals_regexp
values = self._unstable_globals_values
for i in range(len(values)):
g = match.group(i + GeneralizerInfo.FIRST_NAMELESS_GROUP_IN_MATCH)
if g is not None:
return g, values[i]
error("Unable to identify the kind of IR value from the match!")
return None, None
# See get_idx_from_match
def get_name_from_match(self, match):
return self.get_match_info(match)[0]
def get_nameless_value_from_match(self, match) -> NamelessValue:
return self.get_match_info(match)[1]
def make_ir_generalizer(version, no_meta_details):
values = []
if version >= 5:
values += [
NamelessValue(r"BB", "%", r"label %", r"[\w$.-]+?", None),
NamelessValue(r"BB", "%", r"^", r"[\w$.-]+?", None, ir_suffix=r":"),
]
values += [
# check_prefix check_key ir_prefix ir_regexp global_ir_rhs_regexp
NamelessValue(r"TMP", "%", r"%", r"[\w$.-]+?", None),
NamelessValue(r"ATTR", "#", r"#", r"[0-9]+", None),
NamelessValue(r"ATTR", "#", r"attributes #", r"[0-9]+", r"{[^}]*}"),
NamelessValue(r"GLOB", "@", r"@", r"[0-9]+", None),
NamelessValue(r"GLOB", "@", r"@", r"[0-9]+", r".+", is_before_functions=True),
NamelessValue(
r"GLOBNAMED",
"@",
r"@",
r"[a-zA-Z0-9_$\"\\.-]*[a-zA-Z_$\"\\.-][a-zA-Z0-9_$\"\\.-]*",
r".+",
is_before_functions=True,
match_literally=True,
interlaced_with_previous=True,
),
NamelessValue(r"DBG", "!", r"!dbg ", r"![0-9]+", None),
NamelessValue(r"DIASSIGNID", "!", r"!DIAssignID ", r"![0-9]+", None),
NamelessValue(r"PROF", "!", r"!prof ", r"![0-9]+", None),
NamelessValue(r"TBAA", "!", r"!tbaa ", r"![0-9]+", None),
NamelessValue(r"TBAA_STRUCT", "!", r"!tbaa.struct ", r"![0-9]+", None),
NamelessValue(r"RNG", "!", r"!range ", r"![0-9]+", None),
NamelessValue(r"LOOP", "!", r"!llvm.loop ", r"![0-9]+", None),
NamelessValue(r"META", "!", r"", r"![0-9]+", r"(?:distinct |)!.*"),
NamelessValue(r"ACC_GRP", "!", r"!llvm.access.group ", r"![0-9]+", None),
NamelessValue(r"META", "!", r"![a-z.]+ ", r"![0-9]+", None),
NamelessValue(r"META", "!", r"[, (]", r"![0-9]+", None),
]
prefix = r"(\s*)"
suffix = r"([,\s\(\)\}]|\Z)"
# values = [
# nameless_value
# for nameless_value in IR_NAMELESS_VALUES
# if not (globals_only and nameless_value.global_ir_rhs_regexp is None) and
# not (unstable_ids_only and nameless_value.match_literally)
# ]
return GeneralizerInfo(
version, GeneralizerInfo.MODE_IR, values, prefix, suffix, no_meta_details
)
def make_asm_generalizer(version):
values = [
NamelessValue(
r"MCINST",
"Inst#",
"<MCInst #",
r"\d+",
r".+",
is_number=True,
replace_number_with_counter=True,
),
NamelessValue(
r"MCREG",
"Reg:",
"<MCOperand Reg:",
r"\d+",
r".+",
is_number=True,
replace_number_with_counter=True,
),
]
prefix = r"((?:#|//)\s*)"
suffix = r"([>\s]|\Z)"
return GeneralizerInfo(version, GeneralizerInfo.MODE_ASM, values, prefix, suffix)
# TODO: This is no longer required. Generalize UTC over an empty GeneralizerInfo.
def make_analyze_generalizer(version):
values = [
NamelessValue(
r"GRP",
"#",
r"",
r"0x[0-9a-f]+",
None,
replace_number_with_counter=True,
),
]
prefix = r"(\s*)"
suffix = r"(\)?:)"
return GeneralizerInfo(
version, GeneralizerInfo.MODE_ANALYZE, values, prefix, suffix
)
# Return true if var clashes with the scripted FileCheck check_prefix.
def may_clash_with_default_check_prefix_name(check_prefix, var):
return check_prefix and re.match(
r"^" + check_prefix + r"[0-9]+?$", var, re.IGNORECASE
)
def find_diff_matching(lhs: List[str], rhs: List[str]) -> List[tuple]:
"""
Find a large ordered matching between strings in lhs and rhs.
Think of this as finding the *unchanged* lines in a diff, where the entries
of lhs and rhs are lines of the files being diffed.
Returns a list of matched (lhs_idx, rhs_idx) pairs.
"""
if not lhs or not rhs:
return []
# Collect matches in reverse order.
matches = []
# First, collect a set of candidate matching edges. We limit this to a
# constant multiple of the input size to avoid quadratic runtime.
patterns = collections.defaultdict(lambda: ([], []))
for idx in range(len(lhs)):
patterns[lhs[idx]][0].append(idx)
for idx in range(len(rhs)):
patterns[rhs[idx]][1].append(idx)
multiple_patterns = []
candidates = []
for pattern in patterns.values():
if not pattern[0] or not pattern[1]:
continue
if len(pattern[0]) == len(pattern[1]) == 1:
candidates.append((pattern[0][0], pattern[1][0]))
else:
multiple_patterns.append(pattern)
multiple_patterns.sort(key=lambda pattern: len(pattern[0]) * len(pattern[1]))
for pattern in multiple_patterns:
if len(candidates) + len(pattern[0]) * len(pattern[1]) > 2 * (
len(lhs) + len(rhs)
):
break
for lhs_idx in pattern[0]:
for rhs_idx in pattern[1]:
candidates.append((lhs_idx, rhs_idx))
if not candidates:
# The LHS and RHS either share nothing in common, or lines are just too
# identical. In that case, let's give up and not match anything.
return []
# Compute a maximal crossing-free matching via an algorithm that is
# inspired by a mixture of dynamic programming and line-sweeping in
# discrete geometry.
#
# I would be surprised if this algorithm didn't exist somewhere in the
# literature, but I found it without consciously recalling any
# references, so you'll have to make do with the explanation below.
# Sorry.
#
# The underlying graph is bipartite:
# - nodes on the LHS represent lines in the original check
# - nodes on the RHS represent lines in the new (updated) check
#
# Nodes are implicitly sorted by the corresponding line number.
# Edges (unique_matches) are sorted by the line number on the LHS.
#
# Here's the geometric intuition for the algorithm.
#
# * Plot the edges as points in the plane, with the original line
# number on the X axis and the updated line number on the Y axis.
# * The goal is to find a longest "chain" of points where each point
# is strictly above and to the right of the previous point.
# * The algorithm proceeds by sweeping a vertical line from left to
# right.
# * The algorithm maintains a table where `table[N]` answers the
# question "What is currently the 'best' way to build a chain of N+1
# points to the left of the vertical line". Here, 'best' means
# that the last point of the chain is a as low as possible (minimal
# Y coordinate).
# * `table[N]` is `(y, point_idx)` where `point_idx` is the index of
# the last point in the chain and `y` is its Y coordinate
# * A key invariant is that the Y values in the table are
# monotonically increasing
# * Thanks to these properties, the table can be used to answer the
# question "What is the longest chain that can be built to the left
# of the vertical line using only points below a certain Y value",
# using a binary search over the table.
# * The algorithm also builds a backlink structure in which every point
# links back to the previous point on a best (longest) chain ending
# at that point
#
# The core loop of the algorithm sweeps the line and updates the table
# and backlink structure for every point that we cross during the sweep.
# Therefore, the algorithm is trivially O(M log M) in the number of
# points.
candidates.sort(key=lambda candidate: (candidate[0], -candidate[1]))
backlinks = []
table_rhs_idx = []
table_candidate_idx = []
for _, rhs_idx in candidates:
candidate_idx = len(backlinks)
ti = bisect.bisect_left(table_rhs_idx, rhs_idx)
# Update the table to record a best chain ending in the current point.
# There always is one, and if any of the previously visited points had
# a higher Y coordinate, then there is always a previously recorded best
# chain that can be improved upon by using the current point.
#
# There is only one case where there is some ambiguity. If the
# pre-existing entry table[ti] has the same Y coordinate / rhs_idx as
# the current point (this can only happen if the same line appeared
# multiple times on the LHS), then we could choose to keep the
# previously recorded best chain instead. That would bias the algorithm
# differently but should have no systematic impact on the quality of the
# result.
if ti < len(table_rhs_idx):
table_rhs_idx[ti] = rhs_idx
table_candidate_idx[ti] = candidate_idx
else:
table_rhs_idx.append(rhs_idx)
table_candidate_idx.append(candidate_idx)
if ti > 0:
backlinks.append(table_candidate_idx[ti - 1])
else:
backlinks.append(None)
# Commit to names in the matching by walking the backlinks. Recursively
# attempt to fill in more matches in-between.
match_idx = table_candidate_idx[-1]
while match_idx is not None:
current = candidates[match_idx]
matches.append(current)
match_idx = backlinks[match_idx]
matches.reverse()
return matches
VARIABLE_TAG = "[[@@]]"
METAVAR_RE = re.compile(r"\[\[([A-Z0-9_]+)(?::[^]]+)?\]\]")
NUMERIC_SUFFIX_RE = re.compile(r"[0-9]*$")
class TestVar:
def __init__(self, nameless_value: NamelessValue, prefix: str, suffix: str):
self._nameless_value = nameless_value
self._prefix = prefix
self._suffix = suffix
def seen(self, nameless_value: NamelessValue, prefix: str, suffix: str):
if prefix != self._prefix:
self._prefix = ""
if suffix != self._suffix:
self._suffix = ""
def get_variable_name(self, text):
return self._nameless_value.get_value_name(
text, self._nameless_value.check_prefix
)
def get_def(self, name, prefix, suffix):
if self._nameless_value.is_number:
return f"{prefix}[[#{name}:]]{suffix}"
if self._prefix:
assert self._prefix == prefix
prefix = ""
if self._suffix:
assert self._suffix == suffix
suffix = ""
return f"{prefix}[[{name}:{self._prefix}{self._nameless_value.get_ir_regex()}{self._suffix}]]{suffix}"
def get_use(self, name, prefix, suffix):
if self._nameless_value.is_number:
return f"{prefix}[[#{name}]]{suffix}"
if self._prefix:
assert self._prefix == prefix
prefix = ""
if self._suffix:
assert self._suffix == suffix
suffix = ""
return f"{prefix}[[{name}]]{suffix}"
class CheckValueInfo:
def __init__(
self,
key,
text,
name: str,
prefix: str,
suffix: str,
):
# Key for the value, e.g. '%'
self.key = key
# Text to be matched by the FileCheck variable (without any prefix or suffix)
self.text = text
# Name of the FileCheck variable
self.name = name
# Prefix and suffix that were captured by the NamelessValue regular expression
self.prefix = prefix
self.suffix = suffix
# Represent a check line in a way that allows us to compare check lines while
# ignoring some or all of the FileCheck variable names.
class CheckLineInfo:
def __init__(self, line, values):
# Line with all FileCheck variable name occurrences replaced by VARIABLE_TAG
self.line: str = line
# Information on each FileCheck variable name occurrences in the line
self.values: List[CheckValueInfo] = values
def __repr__(self):
return f"CheckLineInfo(line={self.line}, self.values={self.values})"
def remap_metavar_names(
old_line_infos: List[CheckLineInfo],
new_line_infos: List[CheckLineInfo],
committed_names: Set[str],
) -> Mapping[str, str]:
"""
Map all FileCheck variable names that appear in new_line_infos to new
FileCheck variable names in an attempt to reduce the diff from old_line_infos
to new_line_infos.
This is done by:
* Matching old check lines and new check lines using a diffing algorithm
applied after replacing names with wildcards.
* Committing to variable names such that the matched lines become equal
(without wildcards) if possible
* This is done recursively to handle cases where many lines are equal
after wildcard replacement
"""
# Initialize uncommitted identity mappings
new_mapping = {}
for line in new_line_infos:
for value in line.values:
new_mapping[value.name] = value.name
# Recursively commit to the identity mapping or find a better one
def recurse(old_begin, old_end, new_begin, new_end):
if old_begin == old_end or new_begin == new_end:
return
# Find a matching of lines where uncommitted names are replaced
# with a placeholder.
def diffify_line(line, mapper):
values = []
for value in line.values:
mapped = mapper(value.name)
values.append(mapped if mapped in committed_names else "?")
return line.line.strip() + " @@@ " + " @ ".join(values)
lhs_lines = [
diffify_line(line, lambda x: x)
for line in old_line_infos[old_begin:old_end]
]
rhs_lines = [
diffify_line(line, lambda x: new_mapping[x])
for line in new_line_infos[new_begin:new_end]
]
candidate_matches = find_diff_matching(lhs_lines, rhs_lines)
candidate_matches = [
(old_begin + lhs_idx, new_begin + rhs_idx)
for lhs_idx, rhs_idx in candidate_matches
]
# Candidate matches may conflict if they require conflicting mappings of
# names. We want to determine a large set of compatible candidates,
# because that leads to a small diff.
#
# We think of the candidates as vertices in a conflict graph. The
# conflict graph has edges between incompatible candidates. We want to
# find a large independent set in this graph.
#
# Greedily selecting candidates and removing incompatible ones has the
# disadvantage that making few bad decisions early on can have huge
# consequences.
#
# Instead, we implicitly compute multiple independent sets by greedily
# assigning a *coloring* to the conflict graph. Then, we select the
# largest color class (which is the largest independent set we found),
# commit to all candidates in it, and recurse.
#
# Note that we don't actually materialize the conflict graph. Instead,
# each color class tracks the information needed to decide implicitly
# whether a vertex conflicts (has an edge to) any of the vertices added
# to the color class so far.
class Color:
def __init__(self):
# (lhs_idx, rhs_idx) of matches in this color
self.matches = []
# rhs_name -> lhs_name mappings required by this color
self.mapping = {}
# lhs_names committed for this color
self.committed = set()
colors = []
for lhs_idx, rhs_idx in candidate_matches:
lhs_line = old_line_infos[lhs_idx]
rhs_line = new_line_infos[rhs_idx]
# We scan through the uncommitted names in the candidate line and
# filter out the color classes to which the candidate could be
# assigned.
#
# Simultaneously, we prepare a new color class in case the candidate
# conflicts with all colors that have been established so far.
compatible_colors = colors[:]
new_color = Color()
new_color.matches.append((lhs_idx, rhs_idx))
for lhs_value, rhs_value in zip(lhs_line.values, rhs_line.values):
if new_mapping[rhs_value.name] in committed_names:
# The new value has already been committed. If it was mapped
# to the same name as the original value, we can consider
# committing other values from this line. Otherwise, we
# should ignore this line.
if new_mapping[rhs_value.name] == lhs_value.name:
continue
else:
break
if rhs_value.name in new_color.mapping:
# Same, but for a possible commit happening on the same line
if new_color.mapping[rhs_value.name] == lhs_value.name:
continue
else:
break
if (
lhs_value.name in committed_names
or lhs_value.name in new_color.committed
):
# We can't map this value because the name we would map it
# to has already been committed for something else. Give up
# on this line.
break
new_color.mapping[rhs_value.name] = lhs_value.name
new_color.committed.add(lhs_value.name)
color_idx = 0
while color_idx < len(compatible_colors):
color = compatible_colors[color_idx]
compatible = True
if rhs_value.name in color.mapping:
compatible = color.mapping[rhs_value.name] == lhs_value.name
else:
compatible = lhs_value.name not in color.committed
if compatible:
color_idx += 1
else:
del compatible_colors[color_idx]
else:
# We never broke out of the loop, which means that at a minimum,
# this line is viable standalone
if compatible_colors:
color = max(compatible_colors, key=lambda color: len(color.matches))
color.mapping.update(new_color.mapping)
color.committed.update(new_color.committed)
color.matches.append((lhs_idx, rhs_idx))
else:
colors.append(new_color)
if colors:
# Pick the largest color class. This gives us a large independent
# (non-conflicting) set of candidate matches. Assign all names
# required by the independent set and recurse.
max_color = max(colors, key=lambda color: len(color.matches))
for rhs_var, lhs_var in max_color.mapping.items():
new_mapping[rhs_var] = lhs_var
committed_names.add(lhs_var)
if (
lhs_var != rhs_var
and lhs_var in new_mapping
and new_mapping[lhs_var] == lhs_var
):
new_mapping[lhs_var] = "conflict_" + lhs_var
matches = (
[(old_begin - 1, new_begin - 1)]
+ max_color.matches
+ [(old_end, new_end)]
)
for (lhs_prev, rhs_prev), (lhs_next, rhs_next) in zip(matches, matches[1:]):
recurse(lhs_prev + 1, lhs_next, rhs_prev + 1, rhs_next)
recurse(0, len(old_line_infos), 0, len(new_line_infos))
# Commit to remaining names and resolve conflicts
for new_name, mapped_name in new_mapping.items():
if mapped_name in committed_names:
continue
if not mapped_name.startswith("conflict_"):
assert mapped_name == new_name
committed_names.add(mapped_name)
for new_name, mapped_name in new_mapping.items():
if mapped_name in committed_names:
continue
assert mapped_name.startswith("conflict_")
m = NUMERIC_SUFFIX_RE.search(new_name)
base_name = new_name[: m.start()]
suffix = int(new_name[m.start() :]) if m.start() != m.end() else 1
while True:
candidate = f"{base_name}{suffix}"
if candidate not in committed_names:
new_mapping[new_name] = candidate
committed_names.add(candidate)
break
suffix += 1
return new_mapping
def generalize_check_lines(
lines,
ginfo: GeneralizerInfo,
vars_seen,
global_vars_seen,
preserve_names=False,
original_check_lines=None,
*,
unstable_globals_only=False,
no_meta_details=False,
):
if unstable_globals_only:
regexp = ginfo.get_unstable_globals_regexp()
else:
regexp = ginfo.get_regexp()
multiple_braces_re = re.compile(r"({{+)|(}}+)")
def escape_braces(match_obj):
return "{{" + re.escape(match_obj.group(0)) + "}}"
if ginfo.is_ir():
for i, line in enumerate(lines):
# An IR variable named '%.' matches the FileCheck regex string.
line = line.replace("%.", "%dot")
for regex in _global_hex_value_regex:
if re.match("^@" + regex + " = ", line):
line = re.sub(
r"\bi([0-9]+) ([0-9]+)",
lambda m: "i"
+ m.group(1)
+ " [[#"
+ hex(int(m.group(2)))
+ "]]",
line,
)
break
# Ignore any comments, since the check lines will too.
scrubbed_line = SCRUB_IR_COMMENT_RE.sub(r"", line)
# Ignore the metadata details if check global is none
if no_meta_details:
scrubbed_line = SCRUB_IR_FUNC_META_RE.sub(r"{{.*}}", scrubbed_line)
lines[i] = scrubbed_line
if not preserve_names:
committed_names = set(
test_var.get_variable_name(name)
for (name, _), test_var in vars_seen.items()
)
defs = set()
# Collect information about new check lines, and generalize global reference
new_line_infos = []
for line in lines:
filtered_line = ""
values = []
while True:
m = regexp.search(line)
if m is None:
filtered_line += line
break
name = ginfo.get_name_from_match(m)
nameless_value = ginfo.get_nameless_value_from_match(m)
prefix, suffix = nameless_value.get_affixes_from_match(m)
if may_clash_with_default_check_prefix_name(
nameless_value.check_prefix, name
):
warn(
"Change IR value name '%s' or use --prefix-filecheck-ir-name to prevent possible conflict"
" with scripted FileCheck name." % (name,)
)
# Record the variable as seen and (for locals) accumulate
# prefixes/suffixes
is_local_def = nameless_value.is_local_def_ir_value()
if is_local_def:
vars_dict = vars_seen
else:
vars_dict = global_vars_seen
key = (name, nameless_value.check_key)
if is_local_def:
test_prefix = prefix
test_suffix = suffix
else:
test_prefix = ""
test_suffix = ""
if key in vars_dict:
vars_dict[key].seen(nameless_value, test_prefix, test_suffix)
else:
vars_dict[key] = TestVar(nameless_value, test_prefix, test_suffix)
defs.add(key)
var = vars_dict[key].get_variable_name(name)
# Replace with a [[@@]] tag, but be sure to keep the spaces and commas.
filtered_line += (
line[: m.start()] + m.group(1) + VARIABLE_TAG + m.group(m.lastindex)
)
line = line[m.end() :]
values.append(
CheckValueInfo(
key=nameless_value.check_key,
text=name,
name=var,
prefix=prefix,
suffix=suffix,
)
)
new_line_infos.append(CheckLineInfo(filtered_line, values))
committed_names.update(
test_var.get_variable_name(name)
for (name, _), test_var in global_vars_seen.items()
)
# Collect information about original check lines, if any.
orig_line_infos = []
for line in original_check_lines or []:
filtered_line = ""
values = []
while True:
m = METAVAR_RE.search(line)
if m is None:
filtered_line += line
break
# Replace with a [[@@]] tag, but be sure to keep the spaces and commas.
filtered_line += line[: m.start()] + VARIABLE_TAG
line = line[m.end() :]
values.append(
CheckValueInfo(
key=None,
text=None,
name=m.group(1),
prefix="",
suffix="",
)
)
orig_line_infos.append(CheckLineInfo(filtered_line, values))
# Compute the variable name mapping
mapping = remap_metavar_names(orig_line_infos, new_line_infos, committed_names)
# Apply the variable name mapping
for i, line_info in enumerate(new_line_infos):
line_template = line_info.line
line = ""
for value in line_info.values:
idx = line_template.find(VARIABLE_TAG)
line += line_template[:idx]
line_template = line_template[idx + len(VARIABLE_TAG) :]
key = (value.text, value.key)
if value.key == "%":
vars_dict = vars_seen
else:
vars_dict = global_vars_seen
if key in defs:
line += vars_dict[key].get_def(
mapping[value.name], value.prefix, value.suffix
)
defs.remove(key)
else:
line += vars_dict[key].get_use(
mapping[value.name], value.prefix, value.suffix
)
line += line_template
lines[i] = line
if ginfo.is_analyze():
for i, _ in enumerate(lines):
# Escape multiple {{ or }} as {{}} denotes a FileCheck regex.
scrubbed_line = multiple_braces_re.sub(escape_braces, lines[i])
lines[i] = scrubbed_line
return lines
def add_checks(
output_lines,
comment_marker,
prefix_list,
func_dict,
func_name,
check_label_format,
ginfo,
global_vars_seen_dict,
is_filtered,
preserve_names=False,
original_check_lines: Mapping[str, List[str]] = {},
):
# prefix_exclusions are prefixes we cannot use to print the function because it doesn't exist in run lines that use these prefixes as well.
prefix_exclusions = set()
printed_prefixes = []
for p in prefix_list:
checkprefixes = p[0]
# If not all checkprefixes of this run line produced the function we cannot check for it as it does not
# exist for this run line. A subset of the check prefixes might know about the function but only because
# other run lines created it.
if any(
map(
lambda checkprefix: func_name not in func_dict[checkprefix],
checkprefixes,
)
):
prefix_exclusions |= set(checkprefixes)
continue
# prefix_exclusions is constructed, we can now emit the output
for p in prefix_list:
global_vars_seen = {}
checkprefixes = p[0]
for checkprefix in checkprefixes:
if checkprefix in global_vars_seen_dict:
global_vars_seen.update(global_vars_seen_dict[checkprefix])
else:
global_vars_seen_dict[checkprefix] = {}
if checkprefix in printed_prefixes:
break
# Check if the prefix is excluded.
if checkprefix in prefix_exclusions:
continue
# If we do not have output for this prefix we skip it.
if not func_dict[checkprefix][func_name]:
continue
# Add some space between different check prefixes, but not after the last
# check line (before the test code).
if ginfo.is_asm():
if len(printed_prefixes) != 0:
output_lines.append(comment_marker)
if checkprefix not in global_vars_seen_dict:
global_vars_seen_dict[checkprefix] = {}
global_vars_seen_before = [key for key in global_vars_seen.keys()]
vars_seen = {}
printed_prefixes.append(checkprefix)
attrs = str(func_dict[checkprefix][func_name].attrs)
attrs = "" if attrs == "None" else attrs
if ginfo.get_version() > 1:
funcdef_attrs_and_ret = func_dict[checkprefix][
func_name
].funcdef_attrs_and_ret
else:
funcdef_attrs_and_ret = ""
if attrs:
output_lines.append(
"%s %s: Function Attrs: %s" % (comment_marker, checkprefix, attrs)
)
args_and_sig = str(func_dict[checkprefix][func_name].args_and_sig)
if args_and_sig:
args_and_sig = generalize_check_lines(
[args_and_sig],
ginfo,
vars_seen,
global_vars_seen,
preserve_names,
original_check_lines=[],
no_meta_details=ginfo.no_meta_details(),
)[0]
func_name_separator = func_dict[checkprefix][func_name].func_name_separator
if "[[" in args_and_sig:
# Captures in label lines are not supported, thus split into a -LABEL
# and a separate -SAME line that contains the arguments with captures.
args_and_sig_prefix = ""
if ginfo.get_version() >= 3 and args_and_sig.startswith("("):
# Ensure the "(" separating function name and arguments is in the
# label line. This is required in case of function names that are
# prefixes of each other. Otherwise, the label line for "foo" might
# incorrectly match on "foo.specialized".
args_and_sig_prefix = args_and_sig[0]
args_and_sig = args_and_sig[1:]
# Removing args_and_sig from the label match line requires
# func_name_separator to be empty. Otherwise, the match will not work.
assert func_name_separator == ""
output_lines.append(
check_label_format
% (
checkprefix,
funcdef_attrs_and_ret,
func_name,
args_and_sig_prefix,
func_name_separator,
)
)
output_lines.append(
"%s %s-SAME: %s" % (comment_marker, checkprefix, args_and_sig)
)
else:
output_lines.append(
check_label_format
% (
checkprefix,
funcdef_attrs_and_ret,
func_name,
args_and_sig,
func_name_separator,
)
)
func_body = str(func_dict[checkprefix][func_name]).splitlines()
if not func_body:
# We have filtered everything.
continue
# For ASM output, just emit the check lines.
if ginfo.is_asm():
body_start = 1
if is_filtered:
# For filtered output we don't add "-NEXT" so don't add extra spaces
# before the first line.
body_start = 0
else:
output_lines.append(
"%s %s: %s" % (comment_marker, checkprefix, func_body[0])
)
func_lines = generalize_check_lines(
func_body[body_start:], ginfo, vars_seen, global_vars_seen
)
for func_line in func_lines:
if func_line.strip() == "":
output_lines.append(
"%s %s-EMPTY:" % (comment_marker, checkprefix)
)
else:
check_suffix = "-NEXT" if not is_filtered else ""
output_lines.append(
"%s %s%s: %s"
% (comment_marker, checkprefix, check_suffix, func_line)
)
# Remember new global variables we have not seen before
for key in global_vars_seen:
if key not in global_vars_seen_before:
global_vars_seen_dict[checkprefix][key] = global_vars_seen[key]
break
# For analyze output, generalize the output, and emit CHECK-EMPTY lines as well.
elif ginfo.is_analyze():
func_body = generalize_check_lines(
func_body, ginfo, vars_seen, global_vars_seen
)
for func_line in func_body:
if func_line.strip() == "":
output_lines.append(
"{} {}-EMPTY:".format(comment_marker, checkprefix)
)
else:
check_suffix = "-NEXT" if not is_filtered else ""
output_lines.append(
"{} {}{}: {}".format(
comment_marker, checkprefix, check_suffix, func_line
)
)
# Add space between different check prefixes and also before the first
# line of code in the test function.
output_lines.append(comment_marker)
# Remember new global variables we have not seen before
for key in global_vars_seen:
if key not in global_vars_seen_before:
global_vars_seen_dict[checkprefix][key] = global_vars_seen[key]
break
# For IR output, change all defs to FileCheck variables, so we're immune
# to variable naming fashions.
else:
func_body = generalize_check_lines(
func_body,
ginfo,
vars_seen,
global_vars_seen,
preserve_names,
original_check_lines=original_check_lines.get(checkprefix),
)
# This could be selectively enabled with an optional invocation argument.
# Disabled for now: better to check everything. Be safe rather than sorry.
# Handle the first line of the function body as a special case because
# it's often just noise (a useless asm comment or entry label).
# if func_body[0].startswith("#") or func_body[0].startswith("entry:"):
# is_blank_line = True
# else:
# output_lines.append('%s %s: %s' % (comment_marker, checkprefix, func_body[0]))
# is_blank_line = False
is_blank_line = False
for func_line in func_body:
if func_line.strip() == "":
is_blank_line = True
continue
# Do not waste time checking IR comments.
func_line = SCRUB_IR_COMMENT_RE.sub(r"", func_line)
# Skip blank lines instead of checking them.
if is_blank_line:
output_lines.append(
"{} {}: {}".format(
comment_marker, checkprefix, func_line
)
)
else:
check_suffix = "-NEXT" if not is_filtered else ""
output_lines.append(
"{} {}{}: {}".format(
comment_marker, checkprefix, check_suffix, func_line
)
)
is_blank_line = False
# Add space between different check prefixes and also before the first
# line of code in the test function.
output_lines.append(comment_marker)
# Remember new global variables we have not seen before
for key in global_vars_seen:
if key not in global_vars_seen_before:
global_vars_seen_dict[checkprefix][key] = global_vars_seen[key]
break
return printed_prefixes
def add_ir_checks(
output_lines,
comment_marker,
prefix_list,
func_dict,
func_name,
preserve_names,
function_sig,
ginfo: GeneralizerInfo,
global_vars_seen_dict,
is_filtered,
original_check_lines={},
):
assert ginfo.is_ir()
# Label format is based on IR string.
if function_sig and ginfo.get_version() > 1:
function_def_regex = "define %s"
elif function_sig:
function_def_regex = "define {{[^@]+}}%s"
else:
function_def_regex = "%s"
check_label_format = "{} %s-LABEL: {}@%s%s%s".format(
comment_marker, function_def_regex
)
return add_checks(
output_lines,
comment_marker,
prefix_list,
func_dict,
func_name,
check_label_format,
ginfo,
global_vars_seen_dict,
is_filtered,
preserve_names,
original_check_lines=original_check_lines,
)
def add_analyze_checks(
output_lines,
comment_marker,
prefix_list,
func_dict,
func_name,
ginfo: GeneralizerInfo,
is_filtered,
):
assert ginfo.is_analyze()
check_label_format = "{} %s-LABEL: '%s%s%s%s'".format(comment_marker)
global_vars_seen_dict = {}
return add_checks(
output_lines,
comment_marker,
prefix_list,
func_dict,
func_name,
check_label_format,
ginfo,
global_vars_seen_dict,
is_filtered,
)
def build_global_values_dictionary(glob_val_dict, raw_tool_output, prefixes, ginfo):
for nameless_value in ginfo.get_nameless_values():
if nameless_value.global_ir_rhs_regexp is None:
continue
lhs_re_str = nameless_value.ir_prefix + nameless_value.ir_regexp
rhs_re_str = nameless_value.global_ir_rhs_regexp
global_ir_value_re_str = r"^" + lhs_re_str + r"\s=\s" + rhs_re_str + r"$"
global_ir_value_re = re.compile(global_ir_value_re_str, flags=(re.M))
lines = []
for m in global_ir_value_re.finditer(raw_tool_output):
# Attach the substring's start index so that CHECK lines
# can be sorted properly even if they are matched by different nameless values.
# This is relevant for GLOB and GLOBNAMED since they may appear interlaced.
lines.append((m.start(), m.group(0)))
for prefix in prefixes:
if glob_val_dict[prefix] is None:
continue
if nameless_value.check_prefix in glob_val_dict[prefix]:
if lines == glob_val_dict[prefix][nameless_value.check_prefix]:
continue
if prefix == prefixes[-1]:
warn("Found conflicting asm under the same prefix: %r!" % (prefix,))
else:
glob_val_dict[prefix][nameless_value.check_prefix] = None
continue
glob_val_dict[prefix][nameless_value.check_prefix] = lines
def filter_globals_according_to_preference(
global_val_lines_w_index, global_vars_seen, nameless_value, global_check_setting
):
if global_check_setting == "none":
return []
if global_check_setting == "all":
return global_val_lines_w_index
assert global_check_setting == "smart"
if nameless_value.check_key == "#":
# attribute sets are usually better checked by --check-attributes
return []
def extract(line, nv):
p = (
"^"
+ nv.ir_prefix
+ "("
+ nv.ir_regexp
+ ") = ("
+ nv.global_ir_rhs_regexp
+ ")"
)
match = re.match(p, line)
return (match.group(1), re.findall(nv.ir_regexp, match.group(2)))
transitively_visible = set()
contains_refs_to = {}
def add(var):
nonlocal transitively_visible
nonlocal contains_refs_to
if var in transitively_visible:
return
transitively_visible.add(var)
if not var in contains_refs_to:
return
for x in contains_refs_to[var]:
add(x)
for i, line in global_val_lines_w_index:
(var, refs) = extract(line, nameless_value)
contains_refs_to[var] = refs
for var, check_key in global_vars_seen:
if check_key != nameless_value.check_key:
continue
add(var)
return [
(i, line)
for i, line in global_val_lines_w_index
if extract(line, nameless_value)[0] in transitively_visible
]
METADATA_FILTERS = [
(
r"(?<=\")(.+ )?(\w+ version )[\d.]+(?:[^\" ]*)(?: \([^)]+\))?",
r"{{.*}}\2{{.*}}",
), # preface with glob also, to capture optional CLANG_VENDOR
(r'(!DIFile\(filename: ")(.+/)?([^/]+", directory: )".+"', r"\1{{.*}}\3{{.*}}"),
]
METADATA_FILTERS_RE = [(re.compile(f), r) for (f, r) in METADATA_FILTERS]
def filter_unstable_metadata(line):
for f, replacement in METADATA_FILTERS_RE:
line = f.sub(replacement, line)
return line
def flush_current_checks(output_lines, new_lines_w_index, comment_marker):
if not new_lines_w_index:
return
output_lines.append(comment_marker + SEPARATOR)
new_lines_w_index.sort()
for _, line in new_lines_w_index:
output_lines.append(line)
new_lines_w_index.clear()
def add_global_checks(
glob_val_dict,
comment_marker,
prefix_list,
output_lines,
ginfo: GeneralizerInfo,
global_vars_seen_dict,
preserve_names,
is_before_functions,
global_check_setting,
):
printed_prefixes = set()
output_lines_loc = {} # Allows GLOB and GLOBNAMED to be sorted correctly
for nameless_value in ginfo.get_nameless_values():
if nameless_value.global_ir_rhs_regexp is None:
continue
if nameless_value.is_before_functions != is_before_functions:
continue
for p in prefix_list:
global_vars_seen = {}
checkprefixes = p[0]
if checkprefixes is None:
continue
for checkprefix in checkprefixes:
if checkprefix in global_vars_seen_dict:
global_vars_seen.update(global_vars_seen_dict[checkprefix])
else:
global_vars_seen_dict[checkprefix] = {}
if (checkprefix, nameless_value.check_prefix) in printed_prefixes:
break
if not glob_val_dict[checkprefix]:
continue
if nameless_value.check_prefix not in glob_val_dict[checkprefix]:
continue
if not glob_val_dict[checkprefix][nameless_value.check_prefix]:
continue
check_lines = []
global_vars_seen_before = [key for key in global_vars_seen.keys()]
lines_w_index = glob_val_dict[checkprefix][nameless_value.check_prefix]
lines_w_index = filter_globals_according_to_preference(
lines_w_index,
global_vars_seen_before,
nameless_value,
global_check_setting,
)
for i, line in lines_w_index:
if _global_value_regex:
matched = False
for regex in _global_value_regex:
if re.match("^@" + regex + " = ", line) or re.match(
"^!" + regex + " = ", line
):
matched = True
break
if not matched:
continue
[new_line] = generalize_check_lines(
[line],
ginfo,
{},
global_vars_seen,
preserve_names,
unstable_globals_only=True,
)
new_line = filter_unstable_metadata(new_line)
check_line = "%s %s: %s" % (comment_marker, checkprefix, new_line)
check_lines.append((i, check_line))
if not check_lines:
continue
if not checkprefix in output_lines_loc:
output_lines_loc[checkprefix] = []
if not nameless_value.interlaced_with_previous:
flush_current_checks(
output_lines, output_lines_loc[checkprefix], comment_marker
)
for check_line in check_lines:
output_lines_loc[checkprefix].append(check_line)
printed_prefixes.add((checkprefix, nameless_value.check_prefix))
# Remembe new global variables we have not seen before
for key in global_vars_seen:
if key not in global_vars_seen_before:
global_vars_seen_dict[checkprefix][key] = global_vars_seen[key]
break
if printed_prefixes:
for p in prefix_list:
if p[0] is None:
continue
for checkprefix in p[0]:
if checkprefix not in output_lines_loc:
continue
flush_current_checks(
output_lines, output_lines_loc[checkprefix], comment_marker
)
break
output_lines.append(comment_marker + SEPARATOR)
return printed_prefixes
def check_prefix(prefix):
if not PREFIX_RE.match(prefix):
hint = ""
if "," in prefix:
hint = " Did you mean '--check-prefixes=" + prefix + "'?"
warn(
(
"Supplied prefix '%s' is invalid. Prefix must contain only alphanumeric characters, hyphens and underscores."
+ hint
)
% (prefix)
)
def get_check_prefixes(filecheck_cmd):
check_prefixes = [
item
for m in CHECK_PREFIX_RE.finditer(filecheck_cmd)
for item in m.group(1).split(",")
]
if not check_prefixes:
check_prefixes = ["CHECK"]
return check_prefixes
def verify_filecheck_prefixes(fc_cmd):
fc_cmd_parts = fc_cmd.split()
for part in fc_cmd_parts:
if "check-prefix=" in part:
prefix = part.split("=", 1)[1]
check_prefix(prefix)
elif "check-prefixes=" in part:
prefixes = part.split("=", 1)[1].split(",")
for prefix in prefixes:
check_prefix(prefix)
if prefixes.count(prefix) > 1:
warn(
"Supplied prefix '%s' is not unique in the prefix list."
% (prefix,)
)
def get_autogennote_suffix(parser, args):
autogenerated_note_args = ""
for action in parser._actions:
if not hasattr(args, action.dest):
continue # Ignore options such as --help that aren't included in args
# Ignore parameters such as paths to the binary or the list of tests
if action.dest in (
"tests",
"update_only",
"tool_binary",
"opt_binary",
"llc_binary",
"clang",
"opt",
"llvm_bin",
"verbose",
"force_update",
"reset_variable_names",
"llvm_mc_binary",
):
continue
value = getattr(args, action.dest)
if action.dest == "check_globals":
default_value = "none" if args.version < 4 else "smart"
if value == default_value:
continue
autogenerated_note_args += action.option_strings[0] + " "
if args.version < 4 and value == "all":
continue
autogenerated_note_args += "%s " % value
continue
if action.const is not None: # action stores a constant (usually True/False)
# Skip actions with different constant values (this happens with boolean
# --foo/--no-foo options)
if value != action.const:
continue
if parser.get_default(action.dest) == value:
continue # Don't add default values
if action.dest == "function_signature" and args.version >= 2:
continue # Enabled by default in version 2
if action.dest == "filters":
# Create a separate option for each filter element. The value is a list
# of Filter objects.
for elem in value:
if elem.is_filter_out:
opt_name = "filter-out"
elif elem.is_filter_out_after:
opt_name = "filter-out-after"
else:
opt_name = "filter"
opt_value = elem.pattern()
new_arg = '--%s "%s" ' % (opt_name, opt_value.strip('"'))
if new_arg not in autogenerated_note_args:
autogenerated_note_args += new_arg
else:
autogenerated_note_args += action.option_strings[0] + " "
if action.const is None: # action takes a parameter
if action.nargs == "+":
value = " ".join(map(lambda v: '"' + v.strip('"') + '"', value))
autogenerated_note_args += "%s " % value
if autogenerated_note_args:
autogenerated_note_args = " %s %s" % (
UTC_ARGS_KEY,
autogenerated_note_args[:-1],
)
return autogenerated_note_args
def check_for_command(line, parser, args, argv, argparse_callback):
cmd_m = UTC_ARGS_CMD.match(line)
if cmd_m:
for option in shlex.split(cmd_m.group("cmd").strip()):
if option:
argv.append(option)
args = parse_args(parser, filter(lambda arg: arg not in args.tests, argv))
if argparse_callback is not None:
argparse_callback(args)
return args, argv
def find_arg_in_test(test_info, get_arg_to_check, arg_string, is_global):
result = get_arg_to_check(test_info.args)
if not result and is_global:
# See if this has been specified via UTC_ARGS. This is a "global" option
# that affects the entire generation of test checks. If it exists anywhere
# in the test, apply it to everything.
saw_line = False
for line_info in test_info.ro_iterlines():
line = line_info.line
if not line.startswith(";") and line.strip() != "":
saw_line = True
result = get_arg_to_check(line_info.args)
if result:
if warn and saw_line:
# We saw the option after already reading some test input lines.
# Warn about it.
print(
"WARNING: Found {} in line following test start: ".format(
arg_string
)
+ line,
file=sys.stderr,
)
print(
"WARNING: Consider moving {} to top of file".format(arg_string),
file=sys.stderr,
)
break
return result
def dump_input_lines(output_lines, test_info, prefix_set, comment_string):
for input_line_info in test_info.iterlines(output_lines):
line = input_line_info.line
args = input_line_info.args
if line.strip() == comment_string:
continue
if line.strip() == comment_string + SEPARATOR:
continue
if line.lstrip().startswith(comment_string):
m = CHECK_RE.match(line)
if m and m.group(1) in prefix_set:
continue
output_lines.append(line.rstrip("\n"))
def add_checks_at_end(
output_lines, prefix_list, func_order, comment_string, check_generator
):
added = set()
generated_prefixes = set()
for prefix in prefix_list:
prefixes = prefix[0]
tool_args = prefix[1]
for prefix in prefixes:
for func in func_order[prefix]:
# The func order can contain the same functions multiple times.
# If we see one again we are done.
if (func, prefix) in added:
continue
if added:
output_lines.append(comment_string)
# The add_*_checks routines expect a run list whose items are
# tuples that have a list of prefixes as their first element and
# tool command args string as their second element. They output
# checks for each prefix in the list of prefixes. By doing so, it
# implicitly assumes that for each function every run line will
# generate something for that function. That is not the case for
# generated functions as some run lines might not generate them
# (e.g. -fopenmp vs. no -fopenmp).
#
# Therefore, pass just the prefix we're interested in. This has
# the effect of generating all of the checks for functions of a
# single prefix before moving on to the next prefix. So checks
# are ordered by prefix instead of by function as in "normal"
# mode.
for generated_prefix in check_generator(
output_lines, [([prefix], tool_args)], func
):
added.add((func, generated_prefix))
generated_prefixes.add(generated_prefix)
return generated_prefixes
|