~thomir-deactivatedaccount/drizzle/drizzle-fix-bug653747

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
#!/usr/bin/python2.4
#
# cpplint.py is Copyright (C) 2009 Google Inc.
#
# It is free software; you can redistribute it and/or modify it under the
# terms of either:
#
# a) the GNU General Public License as published by the Free Software
# Foundation; either version 1, or (at your option) any later version, or
#
# b) the "Artistic License".

# Modified for Drizzle by Monty Taylor & Robert Collins

# Here are some issues that I've had people identify in my code during reviews,
# that I think are possible to flag automatically in a lint tool.  If these were
# caught by lint, it would save time both for myself and that of my reviewers.
# Most likely, some of these are beyond the scope of the current lint framework,
# but I think it is valuable to retain these wish-list items even if they cannot
# be immediately implemented.
#
#  Suggestions
#  -----------
#  - Check for no 'explicit' for multi-arg ctor
#  - Check for boolean assign RHS in parens
#  - Check for ctor initializer-list colon position and spacing
#  - Check that if there's a ctor, there should be a dtor
#  - Check accessors that return non-pointer member variables are
#    declared const
#  - Check accessors that return non-const pointer member vars are
#    *not* declared const
#  - Check for using public includes for testing
#  - Check for spaces between brackets in one-line inline method
#  - Check for no assert()
#  - Check for spaces surrounding operators
#  - Check for 0 in pointer context (should be NULL)
#  - Check for 0 in char context (should be '\0')
#  - Check for camel-case method name conventions for methods
#    that are not simple inline getters and setters
#  - Check that base classes have virtual destructors
#    put "  // namespace" after } that closes a namespace, with
#    namespace's name after 'namespace' if it is named.
#  - Do not indent namespace contents
#  - Avoid inlining non-trivial constructors in header files
#    include base/basictypes.h if DISALLOW_EVIL_CONSTRUCTORS is used
#  - Check for old-school (void) cast for call-sites of functions
#    ignored return value
#  - Check gUnit usage of anonymous namespace
#  - Check for class declaration order (typedefs, consts, enums,
#    ctor(s?), dtor, friend declarations, methods, member vars)
#

"""Does google-lint on c++ files.

The goal of this script is to identify places in the code that *may*
be in non-compliance with google style.  It does not attempt to fix
up these problems -- the point is to educate.  It does also not
attempt to find all problems, or to ensure that everything it does
find is legitimately a problem.

In particular, we can get very confused by /* and // inside strings!
We do a small hack, which is to ignore //'s with "'s after them on the
same line, but it is far from perfect (in either direction).
"""

import codecs
import getopt
import math  # for log
import os
import re
import sre_compile
import string
import sys
import unicodedata


_USAGE = """
Syntax: cpplint.py [--verbose=#] [--output=vs7] [--deps=path] [--filter=-x,+y,...]
        <file> [file] ...

  The style guidelines this tries to follow are those in
    http://google-styleguide.googlecode.com/svn/trunk/cppguide.xml

  Every problem is given a confidence score from 1-5, with 5 meaning we are
  certain of the problem, and 1 meaning it could be a legitimate construct.
  This will miss some errors, and is not a substitute for a code review.

  To prevent specific lines from being linted, add a '// NOLINT' comment to the
  end of the line.

  The files passed in will be linted; at least one file must be provided.
  Linted extensions are .cc, .cpp, and .h.  Other file types will be ignored.

  Flags:

    output=vs7
      By default, the output is formatted to ease emacs parsing.  Visual Studio
      compatible output (vs7) may also be used.  Other formats are unsupported.

    verbose=#
      Specify a number 0-5 to restrict errors to certain verbosity levels.

    deps=path
      write out a Makefile that can be included listing the files included
      during the lint process as make style dependencies with null-build rules
      (so that deleted headers will not cause failures). This can be useful to
      perform on-demand linting. The top level target will be the name of the
      lint file itself.

    filter=-x,+y,...
      Specify a comma-separated list of category-filters to apply: only
      error messages whose category names pass the filters will be printed.
      (Category names are printed with the message and look like
      "[whitespace/indent]".)  Filters are evaluated left to right.
      "-FOO" and "FOO" means "do not print categories that start with FOO".
      "+FOO" means "do print categories that start with FOO".

      Examples: --filter=-whitespace,+whitespace/braces
                --filter=whitespace,runtime/printf,+runtime/printf_format
                --filter=-,+build/include_what_you_use

      To see a list of all the categories used in cpplint, pass no arg:
         --filter=
"""

# We categorize each error message we print.  Here are the categories.
# We want an explicit list so we can list them all in cpplint --filter=.
# If you add a new error message with a new category, add it to the list
# here!  cpplint_unittest.py should tell you if you forget to do this.
# \ used for clearer layout -- pylint: disable-msg=C6013
_ERROR_CATEGORIES = '''\
  build/class
  build/deprecated
  build/endif_comment
  build/forward_decl
  build/header_guard
  build/include
  build/include_config
  build/include_order
  build/include_what_you_use
  build/namespaces
  build/printf_format
  build/storage_class
  legal/copyright
  readability/braces
  readability/casting
  readability/check
  readability/constructors
  readability/fn_size
  readability/function
  readability/multiline_comment
  readability/multiline_string
  readability/streams
  readability/todo
  readability/utf8
  runtime/arrays
  runtime/casting
  runtime/explicit
  runtime/int
  runtime/init
  runtime/invalid_increment
  runtime/memset
  runtime/printf
  runtime/printf_format
  runtime/references
  runtime/rtti
  runtime/sizeof
  runtime/string
  runtime/threadsafe_fn
  runtime/virtual
  whitespace/blank_line
  whitespace/braces
  whitespace/comma
  whitespace/comments
  whitespace/end_of_line
  whitespace/ending_newline
  whitespace/indent
  whitespace/labels
  whitespace/line_length
  whitespace/newline
  whitespace/operators
  whitespace/parens
  whitespace/semicolon
  whitespace/tab
  whitespace/todo
'''

# The default state of the category filter. This is overrided by the --filter=
# flag. By default all errors are on, so only add here categories that should be
# off by default (i.e., categories that must be enabled by the --filter= flags).
# All entries here should start with a '-' or '+', as in the --filter= flag.
_DEFAULT_FILTERS = []

# We used to check for high-bit characters, but after much discussion we
# decided those were OK, as long as they were in UTF-8 and didn't represent
# hard-coded international strings, which belong in a seperate i18n file.

# Headers that we consider STL headers.
_STL_HEADERS = frozenset([
    'algobase.h', 'algorithm', 'alloc.h', 'bitset', 'deque', 'exception',
    'function.h', 'functional', 'hash_map', 'hash_map.h', 'hash_set',
    'hash_set.h', 'iterator', 'list', 'list.h', 'map', 'memory', 'pair.h',
    'pthread_alloc', 'queue', 'set', 'set.h', 'sstream', 'stack',
    'stl_alloc.h', 'stl_relops.h', 'type_traits.h',
    'utility', 'vector', 'vector.h',
    ])


# Non-STL C++ system headers.
_CPP_HEADERS = frozenset([
    'algo.h', 'builtinbuf.h', 'bvector.h', 'cassert', 'cctype',
    'cerrno', 'cfloat', 'ciso646', 'climits', 'clocale', 'cmath',
    'complex', 'complex.h', 'csetjmp', 'csignal', 'cstdarg', 'cstddef',
    'cstdio', 'cstdlib', 'cstring', 'ctime', 'cwchar', 'cwctype',
    'defalloc.h', 'deque.h', 'editbuf.h', 'exception', 'fstream',
    'fstream.h', 'hashtable.h', 'heap.h', 'indstream.h', 'iomanip',
    'iomanip.h', 'ios', 'iosfwd', 'iostream', 'iostream.h', 'istream.h',
    'iterator.h', 'limits', 'map.h', 'multimap.h', 'multiset.h',
    'numeric', 'ostream.h', 'parsestream.h', 'pfstream.h', 'PlotFile.h',
    'procbuf.h', 'pthread_alloc.h', 'rope', 'rope.h', 'ropeimpl.h',
    'SFile.h', 'slist', 'slist.h', 'stack.h', 'stdexcept',
    'stdiostream.h', 'streambuf.h', 'stream.h', 'strfile.h', 'string',
    'strstream', 'strstream.h', 'tempbuf.h', 'tree.h', 'typeinfo', 'valarray',
    ])


# Assertion macros.  These are defined in base/logging.h and
# testing/base/gunit.h.  Note that the _M versions need to come first
# for substring matching to work.
_CHECK_MACROS = [
    'DCHECK', 'CHECK',
    'EXPECT_TRUE_M', 'EXPECT_TRUE',
    'ASSERT_TRUE_M', 'ASSERT_TRUE',
    'EXPECT_FALSE_M', 'EXPECT_FALSE',
    'ASSERT_FALSE_M', 'ASSERT_FALSE',
    ]

# Replacement macros for CHECK/DCHECK/EXPECT_TRUE/EXPECT_FALSE
_CHECK_REPLACEMENT = dict([(m, {}) for m in _CHECK_MACROS])

for op, replacement in [('==', 'EQ'), ('!=', 'NE'),
                        ('>=', 'GE'), ('>', 'GT'),
                        ('<=', 'LE'), ('<', 'LT')]:
  _CHECK_REPLACEMENT['DCHECK'][op] = 'DCHECK_%s' % replacement
  _CHECK_REPLACEMENT['CHECK'][op] = 'CHECK_%s' % replacement
  _CHECK_REPLACEMENT['EXPECT_TRUE'][op] = 'EXPECT_%s' % replacement
  _CHECK_REPLACEMENT['ASSERT_TRUE'][op] = 'ASSERT_%s' % replacement
  _CHECK_REPLACEMENT['EXPECT_TRUE_M'][op] = 'EXPECT_%s_M' % replacement
  _CHECK_REPLACEMENT['ASSERT_TRUE_M'][op] = 'ASSERT_%s_M' % replacement

for op, inv_replacement in [('==', 'NE'), ('!=', 'EQ'),
                            ('>=', 'LT'), ('>', 'LE'),
                            ('<=', 'GT'), ('<', 'GE')]:
  _CHECK_REPLACEMENT['EXPECT_FALSE'][op] = 'EXPECT_%s' % inv_replacement
  _CHECK_REPLACEMENT['ASSERT_FALSE'][op] = 'ASSERT_%s' % inv_replacement
  _CHECK_REPLACEMENT['EXPECT_FALSE_M'][op] = 'EXPECT_%s_M' % inv_replacement
  _CHECK_REPLACEMENT['ASSERT_FALSE_M'][op] = 'ASSERT_%s_M' % inv_replacement


# These constants define types of headers for use with
# _IncludeState.CheckNextIncludeOrder().
_C_SYS_HEADER = 1
_CPP_SYS_HEADER = 2
_LIKELY_MY_HEADER = 3
_POSSIBLE_MY_HEADER = 4
_OTHER_HEADER = 5


_regexp_compile_cache = {}


def Match(pattern, s):
  """Matches the string with the pattern, caching the compiled regexp."""
  # The regexp compilation caching is inlined in both Match and Search for
  # performance reasons; factoring it out into a separate function turns out
  # to be noticeably expensive.
  if not pattern in _regexp_compile_cache:
    _regexp_compile_cache[pattern] = sre_compile.compile(pattern)
  return _regexp_compile_cache[pattern].match(s)


def Search(pattern, s):
  """Searches the string for the pattern, caching the compiled regexp."""
  if not pattern in _regexp_compile_cache:
    _regexp_compile_cache[pattern] = sre_compile.compile(pattern)
  return _regexp_compile_cache[pattern].search(s)


class _IncludeState(dict):
  """Tracks line numbers for includes, and the order in which includes appear.

  As a dict, an _IncludeState object serves as a mapping between include
  filename and line number on which that file was included.

  Call CheckNextIncludeOrder() once for each header in the file, passing
  in the type constants defined above. Calls in an illegal order will
  raise an _IncludeError with an appropriate error message.

  """
  # self._section will move monotonically through this set. If it ever
  # needs to move backwards, CheckNextIncludeOrder will raise an error.
  _INITIAL_SECTION = 0
  _MY_H_SECTION = 1
  _C_SECTION = 2
  _CPP_SECTION = 3
  _OTHER_H_SECTION = 4

  _TYPE_NAMES = {
      _C_SYS_HEADER: 'C system header',
      _CPP_SYS_HEADER: 'C++ system header',
      _LIKELY_MY_HEADER: 'header this file implements',
      _POSSIBLE_MY_HEADER: 'header this file may implement',
      _OTHER_HEADER: 'other header',
      }
  _SECTION_NAMES = {
      _INITIAL_SECTION: "... nothing. (This can't be an error.)",
      _MY_H_SECTION: 'a header this file implements',
      _C_SECTION: 'C system header',
      _CPP_SECTION: 'C++ system header',
      _OTHER_H_SECTION: 'other header',
      }

  def __init__(self):
    dict.__init__(self)
    self._section = self._INITIAL_SECTION

  def CheckNextIncludeOrder(self, header_type):
    """Returns a non-empty error message if the next header is out of order.

    This function also updates the internal state to be ready to check
    the next include.

    Args:
      header_type: One of the _XXX_HEADER constants defined above.

    Returns:
      The empty string if the header is in the right order, or an
      error message describing what's wrong.

    """
    error_message = ('Found %s after %s' %
                     (self._TYPE_NAMES[header_type],
                      self._SECTION_NAMES[self._section]))

    if header_type == _C_SYS_HEADER:
      if self._section <= self._C_SECTION:
        self._section = self._C_SECTION
      else:
        return error_message
    elif header_type == _CPP_SYS_HEADER:
      if self._section <= self._CPP_SECTION:
        self._section = self._CPP_SECTION
      else:
        return error_message
    elif header_type == _LIKELY_MY_HEADER:
      if self._section <= self._MY_H_SECTION:
        self._section = self._MY_H_SECTION
      else:
        self._section = self._OTHER_H_SECTION
    elif header_type == _POSSIBLE_MY_HEADER:
      if self._section <= self._MY_H_SECTION:
        self._section = self._MY_H_SECTION
      else:
        # This will always be the fallback because we're not sure
        # enough that the header is associated with this file.
        self._section = self._OTHER_H_SECTION
    else:
      assert header_type == _OTHER_HEADER
      self._section = self._OTHER_H_SECTION

    return ''


class _CppLintState(object):
  """Maintains module-wide state.."""

  def __init__(self):
    self.verbose_level = 1  # global setting.
    self.error_count = 0    # global count of reported errors
    # filters to apply when emitting error messages
    self.filters = _DEFAULT_FILTERS[:]

    # output format:
    # "emacs" - format that emacs can parse (default)
    # "vs7" - format that Microsoft Visual Studio 7 can parse
    self.output_format = 'emacs'

    # deps
    self.depfilename = None
    self.seen_fnames = set()

  def finished(self):
    """Complete things that wait for the end of the lint operation."""
    if self.depfilename is not None:
      if self.error_count:
          # Don't alter dependency data
          return
      depfile = file(self.depfilename, 'w+')
      # depend on what we read
      depfile.write("%s: " % self.depfilename)
      names = sorted(self.seen_fnames)
      depfile.write(' '.join(names))
      depfile.write('\n')
      # anything we read shouldn't cause an error if its missing - so claim
      # it can be made.
      for name in names:
        depfile.write('%s:\n' % name)
      depfile.close()

  def seen_file(self, fname):
    self.seen_fnames.add(fname)

  def SetOutputFormat(self, output_format):
    """Sets the output format for errors."""
    self.output_format = output_format

  def SetVerboseLevel(self, level):
    """Sets the module's verbosity, and returns the previous setting."""
    last_verbose_level = self.verbose_level
    self.verbose_level = level
    return last_verbose_level

  def SetFilters(self, filters):
    """Sets the error-message filters.

    These filters are applied when deciding whether to emit a given
    error message.

    Args:
      filters: A string of comma-separated filters (eg "+whitespace/indent").
               Each filter should start with + or -; else we die.

    Raises:
      ValueError: The comma-separated filters did not all start with '+' or '-'.
                  E.g. "-,+whitespace,-whitespace/indent,whitespace/badfilter"
    """
    # Default filters always have less priority than the flag ones.
    self.filters = _DEFAULT_FILTERS[:]
    for filt in filters.split(','):
      clean_filt = filt.strip()
      if clean_filt:
        self.filters.append(clean_filt)
    for filt in self.filters:
      if not (filt.startswith('+') or filt.startswith('-')):
        raise ValueError('Every filter in --filters must start with + or -'
                         ' (%s does not)' % filt)

  def ResetErrorCount(self):
    """Sets the module's error statistic back to zero."""
    self.error_count = 0

  def IncrementErrorCount(self):
    """Bumps the module's error statistic."""
    self.error_count += 1


_cpplint_state = _CppLintState()


def _OutputFormat():
  """Gets the module's output format."""
  return _cpplint_state.output_format


def _SetOutputFormat(output_format):
  """Sets the module's output format."""
  _cpplint_state.SetOutputFormat(output_format)


def _VerboseLevel():
  """Returns the module's verbosity setting."""
  return _cpplint_state.verbose_level


def _SetVerboseLevel(level):
  """Sets the module's verbosity, and returns the previous setting."""
  return _cpplint_state.SetVerboseLevel(level)


def _Filters():
  """Returns the module's list of output filters, as a list."""
  return _cpplint_state.filters


def _SetFilters(filters):
  """Sets the module's error-message filters.

  These filters are applied when deciding whether to emit a given
  error message.

  Args:
    filters: A string of comma-separated filters (eg "whitespace/indent").
             Each filter should start with + or -; else we die.
  """
  _cpplint_state.SetFilters(filters)


class _FunctionState(object):
  """Tracks current function name and the number of lines in its body."""

  _NORMAL_TRIGGER = 250  # for --v=0, 500 for --v=1, etc.
  _TEST_TRIGGER = 400    # about 50% more than _NORMAL_TRIGGER.

  def __init__(self):
    self.in_a_function = False
    self.lines_in_function = 0
    self.current_function = ''

  def Begin(self, function_name):
    """Start analyzing function body.

    Args:
      function_name: The name of the function being tracked.
    """
    self.in_a_function = True
    self.lines_in_function = 0
    self.current_function = function_name

  def Count(self):
    """Count line in current function body."""
    if self.in_a_function:
      self.lines_in_function += 1

  def Check(self, error, filename, linenum):
    """Report if too many lines in function body.

    Args:
      error: The function to call with any errors found.
      filename: The name of the current file.
      linenum: The number of the line to check.
    """
    if Match(r'T(EST|est)', self.current_function):
      base_trigger = self._TEST_TRIGGER
    else:
      base_trigger = self._NORMAL_TRIGGER
    trigger = base_trigger * 2**_VerboseLevel()

    if self.lines_in_function > trigger:
      error_level = int(math.log(self.lines_in_function / base_trigger, 2))
      # 50 => 0, 100 => 1, 200 => 2, 400 => 3, 800 => 4, 1600 => 5, ...
      if error_level > 5:
        error_level = 5
      error(filename, linenum, 'readability/fn_size', error_level,
            'Small and focused functions are preferred:'
            ' %s has %d non-comment lines'
            ' (error triggered by exceeding %d lines).'  % (
                self.current_function, self.lines_in_function, trigger))

  def End(self):
    """Stop analizing function body."""
    self.in_a_function = False


class _IncludeError(Exception):
  """Indicates a problem with the include order in a file."""
  pass


class FileInfo:
  """Provides utility functions for filenames.

  FileInfo provides easy access to the components of a file's path
  relative to the project root.
  """

  def __init__(self, filename):
    self._filename = filename

  def FullName(self):
    """Make Windows paths like Unix."""
    return os.path.abspath(self._filename).replace('\\', '/')

  def RepositoryName(self):
    """FullName after removing the local path to the repository.

    If we have a real absolute path name here we can try to do something smart:
    detecting the root of the checkout and truncating /path/to/checkout from
    the name so that we get header guards that don't include things like
    "C:\Documents and Settings\..." or "/home/username/..." in them and thus
    people on different computers who have checked the source out to different
    locations won't see bogus errors.
    """
    fullname = self.FullName()

    if os.path.exists(fullname):
      project_dir = os.path.dirname(fullname)

      root_dir = os.path.dirname(fullname)
      while (root_dir != os.path.dirname(root_dir) and
             not (os.path.exists(os.path.join(root_dir, ".bzr"))
                  or
                  os.path.exists(os.path.join(root_dir, "_build")))):
        root_dir = os.path.dirname(root_dir)
        if (os.path.exists(os.path.join(root_dir, ".bzr")) or
            os.path.exists(os.path.join(root_dir, "_build"))):
          prefix = os.path.commonprefix([root_dir, project_dir])
          return fullname[len(prefix) + 1:]

    # Don't know what to do; header guard warnings may be wrong...
    return fullname

  def Split(self):
    """Splits the file into the directory, basename, and extension.

    For 'chrome/browser/browser.cc', Split() would
    return ('chrome/browser', 'browser', '.cc')

    Returns:
      A tuple of (directory, basename, extension).
    """

    googlename = self.RepositoryName()
    project, rest = os.path.split(googlename)
    return (project,) + os.path.splitext(rest)

  def BaseName(self):
    """File base name - text after the final slash, before the final period."""
    return self.Split()[1]

  def Extension(self):
    """File extension - text following the final period."""
    return self.Split()[2]

  def NoExtension(self):
    """File has no source file extension."""
    return '/'.join(self.Split()[0:2])

  def IsSource(self):
    """File has a source file extension."""
    return self.Extension()[1:] in ('c', 'cc', 'cpp', 'cxx')


def _ShouldPrintError(category, confidence):
  """Returns true iff confidence >= verbose, and category passes filter."""
  # There are two ways we might decide not to print an error message:
  # the verbosity level isn't high enough, or the filters filter it out.
  if confidence < _cpplint_state.verbose_level:
    return False

  is_filtered = False
  for one_filter in _Filters():
    if one_filter.startswith('-'):
      if category.startswith(one_filter[1:]):
        is_filtered = True
    elif one_filter.startswith('+'):
      if category.startswith(one_filter[1:]):
        is_filtered = False
    else:
      assert False  # should have been checked for in SetFilter.
  if is_filtered:
    return False

  return True


def Error(filename, linenum, category, confidence, message):
  """Logs the fact we've found a lint error.

  We log where the error was found, and also our confidence in the error,
  that is, how certain we are this is a legitimate style regression, and
  not a misidentification or a use that's sometimes justified.

  Args:
    filename: The name of the file containing the error.
    linenum: The number of the line containing the error.
    category: A string used to describe the "category" this bug
      falls under: "whitespace", say, or "runtime".  Categories
      may have a hierarchy separated by slashes: "whitespace/indent".
    confidence: A number from 1-5 representing a confidence score for
      the error, with 5 meaning that we are certain of the problem,
      and 1 meaning that it could be a legitimate construct.
    message: The error message.
  """
  # There are two ways we might decide not to print an error message:
  # the verbosity level isn't high enough, or the filters filter it out.
  if _ShouldPrintError(category, confidence):
    _cpplint_state.IncrementErrorCount()
    if _cpplint_state.output_format == 'vs7':
      sys.stderr.write('%s(%s):  %s  [%s] [%d]\n' % (
          filename, linenum, message, category, confidence))
    else:
      sys.stderr.write('%s:%s:  %s  [%s] [%d]\n' % (
          filename, linenum, message, category, confidence))


# Matches standard C++ escape esequences per 2.13.2.3 of the C++ standard.
_RE_PATTERN_CLEANSE_LINE_ESCAPES = re.compile(
    r'\\([abfnrtv?"\\\']|\d+|x[0-9a-fA-F]+)')
# Matches strings.  Escape codes should already be removed by ESCAPES.
_RE_PATTERN_CLEANSE_LINE_DOUBLE_QUOTES = re.compile(r'"[^"]*"')
# Matches characters.  Escape codes should already be removed by ESCAPES.
_RE_PATTERN_CLEANSE_LINE_SINGLE_QUOTES = re.compile(r"'.'")
# Matches multi-line C++ comments.
# This RE is a little bit more complicated than one might expect, because we
# have to take care of space removals tools so we can handle comments inside
# statements better.
# The current rule is: We only clear spaces from both sides when we're at the
# end of the line. Otherwise, we try to remove spaces from the right side,
# if this doesn't work we try on left side but only if there's a non-character
# on the right.
_RE_PATTERN_CLEANSE_LINE_C_COMMENTS = re.compile(
    r"""(\s*/\*.*\*/\s*$|
            /\*.*\*/\s+|
         \s+/\*.*\*/(?=\W)|
            /\*.*\*/)""", re.VERBOSE)


def IsCppString(line):
  """Does line terminate so, that the next symbol is in string constant.

  This function does not consider single-line nor multi-line comments.

  Args:
    line: is a partial line of code starting from the 0..n.

  Returns:
    True, if next character appended to 'line' is inside a
    string constant.
  """

  line = line.replace(r'\\', 'XX')  # after this, \\" does not match to \"
  return ((line.count('"') - line.count(r'\"') - line.count("'\"'")) & 1) == 1


def FindNextMultiLineCommentStart(lines, lineix):
  """Find the beginning marker for a multiline comment."""
  while lineix < len(lines):
    if lines[lineix].strip().startswith('/*'):
      # Only return this marker if the comment goes beyond this line
      if lines[lineix].strip().find('*/', 2) < 0:
        return lineix
    lineix += 1
  return len(lines)


def FindNextMultiLineCommentEnd(lines, lineix):
  """We are inside a comment, find the end marker."""
  while lineix < len(lines):
    if lines[lineix].strip().endswith('*/'):
      return lineix
    lineix += 1
  return len(lines)


def RemoveMultiLineCommentsFromRange(lines, begin, end):
  """Clears a range of lines for multi-line comments."""
  # Having // dummy comments makes the lines non-empty, so we will not get
  # unnecessary blank line warnings later in the code.
  for i in range(begin, end):
    lines[i] = '// dummy'


def RemoveMultiLineComments(filename, lines, error):
  """Removes multiline (c-style) comments from lines."""
  lineix = 0
  while lineix < len(lines):
    lineix_begin = FindNextMultiLineCommentStart(lines, lineix)
    if lineix_begin >= len(lines):
      return
    lineix_end = FindNextMultiLineCommentEnd(lines, lineix_begin)
    if lineix_end >= len(lines):
      error(filename, lineix_begin + 1, 'readability/multiline_comment', 5,
            'Could not find end of multi-line comment')
      return
    RemoveMultiLineCommentsFromRange(lines, lineix_begin, lineix_end + 1)
    lineix = lineix_end + 1


def CleanseComments(line):
  """Removes //-comments and single-line C-style /* */ comments.

  Args:
    line: A line of C++ source.

  Returns:
    The line with single-line comments removed.
  """
  commentpos = line.find('//')
  if commentpos != -1 and not IsCppString(line[:commentpos]):
    line = line[:commentpos]
  # get rid of /* ... */
  return _RE_PATTERN_CLEANSE_LINE_C_COMMENTS.sub('', line)


class CleansedLines(object):
  """Holds 3 copies of all lines with different preprocessing applied to them.

  1) elided member contains lines without strings and comments,
  2) lines member contains lines without comments, and
  3) raw member contains all the lines without processing.
  All these three members are of <type 'list'>, and of the same length.
  """

  def __init__(self, lines):
    self.elided = []
    self.lines = []
    self.raw_lines = lines
    self.num_lines = len(lines)
    for linenum in range(len(lines)):
      self.lines.append(CleanseComments(lines[linenum]))
      elided = self._CollapseStrings(lines[linenum])
      self.elided.append(CleanseComments(elided))

  def NumLines(self):
    """Returns the number of lines represented."""
    return self.num_lines

  @staticmethod
  def _CollapseStrings(elided):
    """Collapses strings and chars on a line to simple "" or '' blocks.

    We nix strings first so we're not fooled by text like '"http://"'

    Args:
      elided: The line being processed.

    Returns:
      The line with collapsed strings.
    """
    if not _RE_PATTERN_INCLUDE.match(elided):
      # Remove escaped characters first to make quote/single quote collapsing
      # basic.  Things that look like escaped characters shouldn't occur
      # outside of strings and chars.
      elided = _RE_PATTERN_CLEANSE_LINE_ESCAPES.sub('', elided)
      elided = _RE_PATTERN_CLEANSE_LINE_SINGLE_QUOTES.sub("''", elided)
      elided = _RE_PATTERN_CLEANSE_LINE_DOUBLE_QUOTES.sub('""', elided)
    return elided


def CloseExpression(clean_lines, linenum, pos):
  """If input points to ( or { or [, finds the position that closes it.

  If lines[linenum][pos] points to a '(' or '{' or '[', finds the the
  linenum/pos that correspond to the closing of the expression.

  Args:
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    pos: A position on the line.

  Returns:
    A tuple (line, linenum, pos) pointer *past* the closing brace, or
    (line, len(lines), -1) if we never find a close.  Note we ignore
    strings and comments when matching; and the line we return is the
    'cleansed' line at linenum.
  """

  line = clean_lines.elided[linenum]
  startchar = line[pos]
  if startchar not in '({[':
    return (line, clean_lines.NumLines(), -1)
  if startchar == '(': endchar = ')'
  if startchar == '[': endchar = ']'
  if startchar == '{': endchar = '}'

  num_open = line.count(startchar) - line.count(endchar)
  while linenum < clean_lines.NumLines() and num_open > 0:
    linenum += 1
    line = clean_lines.elided[linenum]
    num_open += line.count(startchar) - line.count(endchar)
  # OK, now find the endchar that actually got us back to even
  endpos = len(line)
  while num_open >= 0:
    endpos = line.rfind(')', 0, endpos)
    num_open -= 1                 # chopped off another )
  return (line, linenum, endpos + 1)


def CheckForCopyright(filename, lines, error):
  """Logs an error if no Copyright message appears at the top of the file."""

  # We'll say it should occur by line 10. Don't forget there's a
  # dummy line at the front.
  for line in xrange(1, min(len(lines), 11)):
    if re.search(r'Copyright', lines[line], re.I): break
  else:                       # means no copyright line was found
    error(filename, 0, 'legal/copyright', 5,
          'No copyright message found.  '
          'You should have a line: "Copyright [year] <Copyright Owner>"')


def GetHeaderGuardCPPVariable(filename):
  """Returns the CPP variable that should be used as a header guard.

  Args:
    filename: The name of a C++ header file.

  Returns:
    The CPP variable that should be used as a header guard in the
    named file.

  """

  fileinfo = FileInfo(filename)
  return re.sub(r'[-./\s]', '_', fileinfo.RepositoryName()).upper()


def CheckForHeaderGuard(filename, lines, error):
  """Checks that the file contains a header guard.

  Logs an error if no #ifndef header guard is present.  For other
  headers, checks that the full pathname is used.

  Args:
    filename: The name of the C++ header file.
    lines: An array of strings, each representing a line of the file.
    error: The function to call with any errors found.
  """

  cppvar = GetHeaderGuardCPPVariable(filename)

  ifndef = None
  ifndef_linenum = 0
  define = None
  endif = None
  endif_linenum = 0
  for linenum, line in enumerate(lines):
    linesplit = line.split()
    if len(linesplit) >= 2:
      # find the first occurrence of #ifndef and #define, save arg
      if not ifndef and linesplit[0] == '#ifndef':
        # set ifndef to the header guard presented on the #ifndef line.
        ifndef = linesplit[1]
        ifndef_linenum = linenum
      if not define and linesplit[0] == '#define':
        define = linesplit[1]
    # find the last occurrence of #endif, save entire line
    if line.startswith('#endif'):
      endif = line
      endif_linenum = linenum

  if not ifndef or not define or ifndef != define:
    error(filename, 0, 'build/header_guard', 5,
          'No #ifndef header guard found, suggested CPP variable is: %s' %
          cppvar)
    return

  # The guard should be PATH_FILE_H_, but we also allow PATH_FILE_H__
  # for backward compatibility.
  if ifndef != cppvar:
    error_level = 0
    if ifndef != cppvar + '_':
      error_level = 5

    error(filename, ifndef_linenum, 'build/header_guard', error_level,
          '#ifndef header guard has wrong style, please use: %s' % cppvar)

  if endif != ('#endif /* %s */' % cppvar):
    error_level = 0
    if endif != ('#endif /* %s */' % (cppvar + '_')):
      error_level = 5

    error(filename, endif_linenum, 'build/header_guard', error_level,
          '#endif line should be "#endif /* %s */"' % cppvar)


def CheckForUnicodeReplacementCharacters(filename, lines, error):
  """Logs an error for each line containing Unicode replacement characters.

  These indicate that either the file contained invalid UTF-8 (likely)
  or Unicode replacement characters (which it shouldn't).  Note that
  it's possible for this to throw off line numbering if the invalid
  UTF-8 occurred adjacent to a newline.

  Args:
    filename: The name of the current file.
    lines: An array of strings, each representing a line of the file.
    error: The function to call with any errors found.
  """
  for linenum, line in enumerate(lines):
    if u'\ufffd' in line:
      error(filename, linenum, 'readability/utf8', 5,
            'Line contains invalid UTF-8 (or Unicode replacement character).')


def CheckForNewlineAtEOF(filename, lines, error):
  """Logs an error if there is no newline char at the end of the file.

  Args:
    filename: The name of the current file.
    lines: An array of strings, each representing a line of the file.
    error: The function to call with any errors found.
  """

  # The array lines() was created by adding two newlines to the
  # original file (go figure), then splitting on \n.
  # To verify that the file ends in \n, we just have to make sure the
  # last-but-two element of lines() exists and is empty.
  if len(lines) < 3 or lines[-2]:
    error(filename, len(lines) - 2, 'whitespace/ending_newline', 5,
          'Could not find a newline character at the end of the file.')


def CheckForMultilineCommentsAndStrings(filename, clean_lines, linenum, error):
  """Logs an error if we see /* ... */ or "..." that extend past one line.

  /* ... */ comments are legit inside macros, for one line.
  Otherwise, we prefer // comments, so it's ok to warn about the
  other.  Likewise, it's ok for strings to extend across multiple
  lines, as long as a line continuation character (backslash)
  terminates each line. Although not currently prohibited by the C++
  style guide, it's ugly and unnecessary. We don't do well with either
  in this lint program, so we warn about both.

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    error: The function to call with any errors found.
  """
  line = clean_lines.elided[linenum]

  # Remove all \\ (escaped backslashes) from the line. They are OK, and the
  # second (escaped) slash may trigger later \" detection erroneously.
  line = line.replace('\\\\', '')

  if line.count('/*') > line.count('*/'):
    error(filename, linenum, 'readability/multiline_comment', 5,
          'Complex multi-line /*...*/-style comment found. '
          'Lint may give bogus warnings.  '
          'Consider replacing these with //-style comments, '
          'with #if 0...#endif, '
          'or with more clearly structured multi-line comments.')

  if (line.count('"') - line.count('\\"')) % 2:
    error(filename, linenum, 'readability/multiline_string', 5,
          'Multi-line string ("...") found.  This lint script doesn\'t '
          'do well with such strings, and may give bogus warnings.  They\'re '
          'ugly and unnecessary, and you should use concatenation instead".')


threading_list = (
    ('asctime(', 'asctime_r('),
    ('ctime(', 'ctime_r('),
    ('getgrgid(', 'getgrgid_r('),
    ('getgrnam(', 'getgrnam_r('),
    ('getlogin(', 'getlogin_r('),
    ('getpwnam(', 'getpwnam_r('),
    ('getpwuid(', 'getpwuid_r('),
    ('gmtime(', 'gmtime_r('),
    ('localtime(', 'localtime_r('),
    ('rand(', 'rand_r('),
    ('readdir(', 'readdir_r('),
    ('strtok(', 'strtok_r('),
    ('ttyname(', 'ttyname_r('),
    )


def CheckPosixThreading(filename, clean_lines, linenum, error):
  """Checks for calls to thread-unsafe functions.

  Much code has been originally written without consideration of
  multi-threading. Also, engineers are relying on their old experience;
  they have learned posix before threading extensions were added. These
  tests guide the engineers to use thread-safe functions (when using
  posix directly).

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    error: The function to call with any errors found.
  """
  line = clean_lines.elided[linenum]
  for single_thread_function, multithread_safe_function in threading_list:
    ix = line.find(single_thread_function)
    # Comparisons made explicit for clarity -- pylint: disable-msg=C6403
    if ix >= 0 and (ix == 0 or (not line[ix - 1].isalnum() and
                                line[ix - 1] not in ('_', '.', '>'))):
      error(filename, linenum, 'runtime/threadsafe_fn', 2,
            'Consider using ' + multithread_safe_function +
            '...) instead of ' + single_thread_function +
            '...) for improved thread safety.')


# Matches invalid increment: *count++, which moves pointer insead of
# incrementing a value.
_RE_PATTERN_IVALID_INCREMENT = re.compile(
    r'^\s*\*\w+(\+\+|--);')


def CheckInvalidIncrement(filename, clean_lines, linenum, error):
  """Checks for invalud increment *count++.

  For example following function:
  void increment_counter(int* count) {
    *count++;
  }
  is invalid, because it effectively does count++, moving pointer, and should
  be replaced with ++*count, (*count)++ or *count += 1.

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    error: The function to call with any errors found.
  """
  line = clean_lines.elided[linenum]
  if _RE_PATTERN_IVALID_INCREMENT.match(line):
    error(filename, linenum, 'runtime/invalid_increment', 5,
          'Changing pointer instead of value (or unused value of operator*).')


class _ClassInfo(object):
  """Stores information about a class."""

  def __init__(self, name, linenum):
    self.name = name
    self.linenum = linenum
    self.seen_open_brace = False
    self.is_derived = False
    self.virtual_method_linenumber = None
    self.has_virtual_destructor = False
    self.brace_depth = 0


class _ClassState(object):
  """Holds the current state of the parse relating to class declarations.

  It maintains a stack of _ClassInfos representing the parser's guess
  as to the current nesting of class declarations. The innermost class
  is at the top (back) of the stack. Typically, the stack will either
  be empty or have exactly one entry.
  """

  def __init__(self):
    self.classinfo_stack = []

  def CheckFinished(self, filename, error):
    """Checks that all classes have been completely parsed.

    Call this when all lines in a file have been processed.
    Args:
      filename: The name of the current file.
      error: The function to call with any errors found.
    """
    if self.classinfo_stack:
      # Note: This test can result in false positives if #ifdef constructs
      # get in the way of brace matching. See the testBuildClass test in
      # cpplint_unittest.py for an example of this.
      error(filename, self.classinfo_stack[0].linenum, 'build/class', 5,
            'Failed to find complete declaration of class %s' %
            self.classinfo_stack[0].name)


def CheckForNonStandardConstructs(filename, clean_lines, linenum,
                                  class_state, error):
  """Logs an error if we see certain non-ANSI constructs ignored by gcc-2.

  Complain about several constructs which gcc-2 accepts, but which are
  not standard C++.  Warning about these in lint is one way to ease the
  transition to new compilers.
  - put storage class first (e.g. "static const" instead of "const static").
  - "%lld" instead of %qd" in printf-type functions.
  - "%1$d" is non-standard in printf-type functions.
  - "\%" is an undefined character escape sequence.
  - text after #endif is not allowed.
  - invalid inner-style forward declaration.
  - >? and <? operators, and their >?= and <?= cousins.
  - classes with virtual methods need virtual destructors (compiler warning
    available, but not turned on yet.)

  Additionally, check for constructor/destructor style violations as it
  is very convenient to do so while checking for gcc-2 compliance.

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    class_state: A _ClassState instance which maintains information about
                 the current stack of nested class declarations being parsed.
    error: A callable to which errors are reported, which takes 4 arguments:
           filename, line number, error level, and message
  """

  # Remove comments from the line, but leave in strings for now.
  line = clean_lines.lines[linenum]

  if Search(r'printf\s*\(.*".*%[-+ ]?\d*q', line):
    error(filename, linenum, 'runtime/printf_format', 3,
          '%q in format strings is deprecated.  Use %ll instead.')

  if Search(r'printf\s*\(.*".*%\d+\$', line):
    error(filename, linenum, 'runtime/printf_format', 2,
          '%N$ formats are unconventional.  Try rewriting to avoid them.')

  # Remove escaped backslashes before looking for undefined escapes.
  line = line.replace('\\\\', '')

  if Search(r'("|\').*\\(%|\[|\(|{)', line):
    error(filename, linenum, 'build/printf_format', 3,
          '%, [, (, and { are undefined character escapes.  Unescape them.')

  # For the rest, work with both comments and strings removed.
  line = clean_lines.elided[linenum]

  if Search(r'\b(const|volatile|void|char|short|int|long'
            r'|float|double|signed|unsigned'
            r'|schar|u?int8|u?int16|u?int32|u?int64)'
            r'\s+(auto|register|static|extern|typedef)\b',
            line):
    error(filename, linenum, 'build/storage_class', 5,
          'Storage class (static, extern, typedef, etc) should be first.')

  if Match(r'\s*#\s*endif\s*[^/\s]+', line):
    error(filename, linenum, 'build/endif_comment', 5,
          'Uncommented text after #endif is non-standard.  Use a comment.')

  if Match(r'\s*class\s+(\w+\s*::\s*)+\w+\s*;', line):
    error(filename, linenum, 'build/forward_decl', 5,
          'Inner-style forward declarations are invalid.  Remove this line.')

  if Search(r'(\w+|[+-]?\d+(\.\d*)?)\s*(<|>)\?=?\s*(\w+|[+-]?\d+)(\.\d*)?',
            line):
    error(filename, linenum, 'build/deprecated', 3,
          '>? and <? (max and min) operators are non-standard and deprecated.')

  # Track class entry and exit, and attempt to find cases within the
  # class declaration that don't meet the C++ style
  # guidelines. Tracking is very dependent on the code matching Google
  # style guidelines, but it seems to perform well enough in testing
  # to be a worthwhile addition to the checks.
  classinfo_stack = class_state.classinfo_stack
  # Look for a class declaration
  class_decl_match = Match(
      r'\s*(template\s*<[\w\s<>,:]*>\s*)?(class|struct)\s+(\w+(::\w+)*)', line)
  if class_decl_match:
    classinfo_stack.append(_ClassInfo(class_decl_match.group(3), linenum))

  # Everything else in this function uses the top of the stack if it's
  # not empty.
  if not classinfo_stack:
    return

  classinfo = classinfo_stack[-1]

  # If the opening brace hasn't been seen look for it and also
  # parent class declarations.
  if not classinfo.seen_open_brace:
    # If the line has a ';' in it, assume it's a forward declaration or
    # a single-line class declaration, which we won't process.
    if line.find(';') != -1:
      classinfo_stack.pop()
      return
    classinfo.seen_open_brace = (line.find('{') != -1)
    # Look for a bare ':'
    if Search('(^|[^:]):($|[^:])', line):
      classinfo.is_derived = True
    if not classinfo.seen_open_brace:
      return  # Everything else in this function is for after open brace

  # The class may have been declared with namespace or classname qualifiers.
  # The constructor and destructor will not have those qualifiers.
  base_classname = classinfo.name.split('::')[-1]

  # Look for single-argument constructors that aren't marked explicit.
  # Technically a valid construct, but against style.
  args = Match(r'(?<!explicit)\s+%s\s*\(([^,()]+)\)'
               % re.escape(base_classname),
               line)
  if (args and
      args.group(1) != 'void' and
      not Match(r'(const\s+)?%s\s*&' % re.escape(base_classname),
                args.group(1).strip())):
    error(filename, linenum, 'runtime/explicit', 5,
          'Single-argument constructors should be marked explicit.')

  # Look for methods declared virtual.
  if Search(r'\bvirtual\b', line):
    classinfo.virtual_method_linenumber = linenum
    # Only look for a destructor declaration on the same line. It would
    # be extremely unlikely for the destructor declaration to occupy
    # more than one line.
    if Search(r'~%s\s*\(' % base_classname, line):
      classinfo.has_virtual_destructor = True

  # Look for class end.
  brace_depth = classinfo.brace_depth
  brace_depth = brace_depth + line.count('{') - line.count('}')
  if brace_depth <= 0:
    classinfo = classinfo_stack.pop()
    # Try to detect missing virtual destructor declarations.
    # For now, only warn if a non-derived class with virtual methods lacks
    # a virtual destructor. This is to make it less likely that people will
    # declare derived virtual destructors without declaring the base
    # destructor virtual.
    if ((classinfo.virtual_method_linenumber is not None) and
        (not classinfo.has_virtual_destructor) and
        (not classinfo.is_derived)):  # Only warn for base classes
      error(filename, classinfo.linenum, 'runtime/virtual', 4,
            'The class %s probably needs a virtual destructor due to '
            'having virtual method(s), one declared at line %d.'
            % (classinfo.name, classinfo.virtual_method_linenumber))
  else:
    classinfo.brace_depth = brace_depth


def CheckSpacingForFunctionCall(filename, line, linenum, error):
  """Checks for the correctness of various spacing around function calls.

  Args:
    filename: The name of the current file.
    line: The text of the line to check.
    linenum: The number of the line to check.
    error: The function to call with any errors found.
  """

  # Since function calls often occur inside if/for/while/switch
  # expressions - which have their own, more liberal conventions - we
  # first see if we should be looking inside such an expression for a
  # function call, to which we can apply more strict standards.
  fncall = line    # if there's no control flow construct, look at whole line
  for pattern in (r'\bif\s*\((.*)\)\s*{',
                  r'\bfor\s*\((.*)\)\s*{',
                  r'\bwhile\s*\((.*)\)\s*[{;]',
                  r'\bswitch\s*\((.*)\)\s*{'):
    match = Search(pattern, line)
    if match:
      fncall = match.group(1)    # look inside the parens for function calls
      break

  # Except in if/for/while/switch, there should never be space
  # immediately inside parens (eg "f( 3, 4 )").  We make an exception
  # for nested parens ( (a+b) + c ).  Likewise, there should never be
  # a space before a ( when it's a function argument.  I assume it's a
  # function argument when the char before the whitespace is legal in
  # a function name (alnum + _) and we're not starting a macro. Also ignore
  # pointers and references to arrays and functions coz they're too tricky:
  # we use a very simple way to recognize these:
  # " (something)(maybe-something)" or
  # " (something)(maybe-something," or
  # " (something)[something]"
  # Note that we assume the contents of [] to be short enough that
  # they'll never need to wrap.
  if (  # Ignore control structures.
      not Search(r'\b(if|for|while|switch|return|delete)\b', fncall) and
      # Ignore pointers/references to functions.
      not Search(r' \([^)]+\)\([^)]*(\)|,$)', fncall) and
      # Ignore pointers/references to arrays.
      not Search(r' \([^)]+\)\[[^\]]+\]', fncall)):
    if Search(r'\w\s*\(\s(?!\s*\\$)', fncall):      # a ( used for a fn call
      error(filename, linenum, 'whitespace/parens', 4,
            'Extra space after ( in function call')
    elif Search(r'\(\s+(?!(\s*\\)|\()', fncall):
      error(filename, linenum, 'whitespace/parens', 2,
            'Extra space after (')
    if (Search(r'\w\s+\(', fncall) and
        not Search(r'#\s*define|typedef', fncall)):
      error(filename, linenum, 'whitespace/parens', 4,
            'Extra space before ( in function call')
    # If the ) is followed only by a newline or a { + newline, assume it's
    # part of a control statement (if/while/etc), and don't complain
    if Search(r'[^)]\s+\)\s*[^{\s]', fncall):
      error(filename, linenum, 'whitespace/parens', 2,
            'Extra space before )')


def IsBlankLine(line):
  """Returns true if the given line is blank.

  We consider a line to be blank if the line is empty or consists of
  only white spaces.

  Args:
    line: A line of a string.

  Returns:
    True, if the given line is blank.
  """
  return not line or line.isspace()


def CheckForFunctionLengths(filename, clean_lines, linenum,
                            function_state, error):
  """Reports for long function bodies.

  For an overview why this is done, see:
  http://google-styleguide.googlecode.com/svn/trunk/cppguide.xml#Write_Short_Functions

  Uses a simplistic algorithm assuming other style guidelines
  (especially spacing) are followed.
  Only checks unindented functions, so class members are unchecked.
  Trivial bodies are unchecked, so constructors with huge initializer lists
  may be missed.
  Blank/comment lines are not counted so as to avoid encouraging the removal
  of vertical space and commments just to get through a lint check.
  NOLINT *on the last line of a function* disables this check.

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    function_state: Current function name and lines in body so far.
    error: The function to call with any errors found.
  """
  lines = clean_lines.lines
  line = lines[linenum]
  raw = clean_lines.raw_lines
  raw_line = raw[linenum]
  joined_line = ''

  starting_func = False
  regexp = r'(\w(\w|::|\*|\&|\s)*)\('  # decls * & space::name( ...
  match_result = Match(regexp, line)
  if match_result:
    # If the name is all caps and underscores, figure it's a macro and
    # ignore it, unless it's TEST or TEST_F.
    function_name = match_result.group(1).split()[-1]
    if function_name == 'TEST' or function_name == 'TEST_F' or (
        not Match(r'[A-Z_]+$', function_name)):
      starting_func = True

  if starting_func:
    body_found = False
    for start_linenum in xrange(linenum, clean_lines.NumLines()):
      start_line = lines[start_linenum]
      joined_line += ' ' + start_line.lstrip()
      if Search(r'(;|})', start_line):  # Declarations and trivial functions
        body_found = True
        break                              # ... ignore
      elif Search(r'{', start_line):
        body_found = True
        function = Search(r'((\w|:)*)\(', line).group(1)
        if Match(r'TEST', function):    # Handle TEST... macros
          parameter_regexp = Search(r'(\(.*\))', joined_line)
          if parameter_regexp:             # Ignore bad syntax
            function += parameter_regexp.group(1)
        else:
          function += '()'
        function_state.Begin(function)
        break
    if not body_found:
      # No body for the function (or evidence of a non-function) was found.
      error(filename, linenum, 'readability/fn_size', 5,
            'Lint failed to find start of function body.')
  elif Match(r'^\}\s*$', line):  # function end
    if not Search(r'\bNOLINT\b', raw_line):
      function_state.Check(error, filename, linenum)
    function_state.End()
  elif not Match(r'^\s*$', line):
    function_state.Count()  # Count non-blank/non-comment lines.


_RE_PATTERN_TODO = re.compile(r'^//(\s*)TODO(\(.+?\))?:?(\s|$)?')


def CheckComment(comment, filename, linenum, error):
  """Checks for common mistakes in TODO comments.

  Args:
    comment: The text of the comment from the line in question.
    filename: The name of the current file.
    linenum: The number of the line to check.
    error: The function to call with any errors found.
  """
  match = _RE_PATTERN_TODO.match(comment)
  if match:
    # One whitespace is correct; zero whitespace is handled elsewhere.
    leading_whitespace = match.group(1)
    if len(leading_whitespace) > 1:
      error(filename, linenum, 'whitespace/todo', 2,
            'Too many spaces before TODO')

    username = match.group(2)
    if not username:
      error(filename, linenum, 'readability/todo', 2,
            'Missing username in TODO; it should look like '
            '"// TODO(my_username): Stuff."')

    middle_whitespace = match.group(3)
    # Comparisons made explicit for correctness -- pylint: disable-msg=C6403
    if middle_whitespace != ' ' and middle_whitespace != '':
      error(filename, linenum, 'whitespace/todo', 2,
            'TODO(my_username) should be followed by a space')


def CheckSpacing(filename, clean_lines, linenum, error):
  """Checks for the correctness of various spacing issues in the code.

  Things we check for: spaces around operators, spaces after
  if/for/while/switch, no spaces around parens in function calls, two
  spaces between code and comment, don't start a block with a blank
  line, don't end a function with a blank line, don't have too many
  blank lines in a row.

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    error: The function to call with any errors found.
  """

  raw = clean_lines.raw_lines
  line = raw[linenum]

  # Before nixing comments, check if the line is blank for no good
  # reason.  This includes the first line after a block is opened, and
  # blank lines at the end of a function (ie, right before a line like '}'
  if IsBlankLine(line):
    elided = clean_lines.elided
    prev_line = elided[linenum - 1]
    prevbrace = prev_line.rfind('{')
    # TODO(unknown): Don't complain if line before blank line, and line after,
    #                both start with alnums and are indented the same amount.
    #                This ignores whitespace at the start of a namespace block
    #                because those are not usually indented.
    if (prevbrace != -1 and prev_line[prevbrace:].find('}') == -1
        and prev_line[:prevbrace].find('namespace') == -1):
      # OK, we have a blank line at the start of a code block.  Before we
      # complain, we check if it is an exception to the rule: The previous
      # non-empty line has the paramters of a function header that are indented
      # 4 spaces (because they did not fit in a 80 column line when placed on
      # the same line as the function name).  We also check for the case where
      # the previous line is indented 6 spaces, which may happen when the
      # initializers of a constructor do not fit into a 80 column line.
      exception = False
      if Match(r' {6}\w', prev_line):  # Initializer list?
        # We are looking for the opening column of initializer list, which
        # should be indented 4 spaces to cause 6 space indentation afterwards.
        search_position = linenum-2
        while (search_position >= 0
               and Match(r' {6}\w', elided[search_position])):
          search_position -= 1
        exception = (search_position >= 0
                     and elided[search_position][:5] == '    :')
      else:
        # Search for the function arguments or an initializer list.  We use a
        # simple heuristic here: If the line is indented 4 spaces; and we have a
        # closing paren, without the opening paren, followed by an opening brace
        # or colon (for initializer lists) we assume that it is the last line of
        # a function header.  If we have a colon indented 4 spaces, it is an
        # initializer list.
        exception = (Match(r' {4}\w[^\(]*\)\s*(const\s*)?(\{\s*$|:)',
                           prev_line)
                     or Match(r' {4}:', prev_line))

      if not exception:
        error(filename, linenum, 'whitespace/blank_line', 2,
              'Blank line at the start of a code block.  Is this needed?')
    # This doesn't ignore whitespace at the end of a namespace block
    # because that is too hard without pairing open/close braces;
    # however, a special exception is made for namespace closing
    # brackets which have a comment containing "namespace".
    #
    # Also, ignore blank lines at the end of a block in a long if-else
    # chain, like this:
    #   if (condition1) {
    #     // Something followed by a blank line
    #
    #   } else if (condition2) {
    #     // Something else
    #   }
    if linenum + 1 < clean_lines.NumLines():
      next_line = raw[linenum + 1]
      if (next_line
          and Match(r'\s*}', next_line)
          and next_line.find('namespace') == -1
          and next_line.find('} else ') == -1):
        error(filename, linenum, 'whitespace/blank_line', 3,
              'Blank line at the end of a code block.  Is this needed?')

  # Next, we complain if there's a comment too near the text
  commentpos = line.find('//')
  if commentpos != -1:
    # Check if the // may be in quotes.  If so, ignore it
    # Comparisons made explicit for clarity -- pylint: disable-msg=C6403
    if (line.count('"', 0, commentpos) -
        line.count('\\"', 0, commentpos)) % 2 == 0:   # not in quotes
      # Allow one space for new scopes, two spaces otherwise:
      if (not Match(r'^\s*{ //', line) and
          ((commentpos >= 1 and
            line[commentpos-1] not in string.whitespace) or
           (commentpos >= 2 and
            line[commentpos-2] not in string.whitespace))):
        error(filename, linenum, 'whitespace/comments', 2,
              'At least two spaces is best between code and comments')
      # There should always be a space between the // and the comment
      commentend = commentpos + 2
      if commentend < len(line) and not line[commentend] == ' ':
        # but some lines are exceptions -- e.g. if they're big
        # comment delimiters like:
        # //----------------------------------------------------------
        # or they begin with multiple slashes followed by a space:
        # //////// Header comment
        match = (Search(r'[=/-]{4,}\s*$', line[commentend:]) or
                 Search(r'^/+ ', line[commentend:]))
        if not match:
          error(filename, linenum, 'whitespace/comments', 4,
                'Should have a space between // and comment')
      CheckComment(line[commentpos:], filename, linenum, error)

  line = clean_lines.elided[linenum]  # get rid of comments and strings

  # Don't try to do spacing checks for operator methods
  line = re.sub(r'operator(==|!=|<|<<|<=|>=|>>|>)\(', 'operator\(', line)

  # = should have no space before and should always have a space after.
  if Search(r'[\s.]=[^=]', line):
    error(filename, linenum, 'whitespace/operators', 4,
          'Space found before =')
  if Search(r'=[\w.]', line):
    error(filename, linenum, 'whitespace/operators', 4,
          'Missing space after =')

  # It's ok not to have spaces around binary operators like + - * /, but if
  # there's too little whitespace, we get concerned.  It's hard to tell,
  # though, so we punt on this one for now.  TODO.

  # You should always have whitespace around binary operators.
  # Alas, we can't test < or > because they're legitimately used sans spaces
  # (a->b, vector<int> a).  The only time we can tell is a < with no >, and
  # only if it's not template params list spilling into the next line.
  match = Search(r'[^<>=!\s](==|!=|<=|>=)[^<>=!\s]', line)
  if not match:
    # Note that while it seems that the '<[^<]*' term in the following
    # regexp could be simplified to '<.*', which would indeed match
    # the same class of strings, the [^<] means that searching for the
    # regexp takes linear rather than quadratic time.
    if not Search(r'<[^<]*,\s*$', line):  # template params spill
      match = Search(r'[^<>=!\s](<)[^<>=!\s]([^>]|->)*$', line)
  if match:
    error(filename, linenum, 'whitespace/operators', 3,
          'Missing spaces around %s' % match.group(1))
  # We allow no-spaces around << and >> when used like this: 10<<20, but
  # not otherwise (particularly, not when used as streams)
  match = Search(r'[^0-9\s](<<|>>)[^0-9\s]', line)
  if match:
    error(filename, linenum, 'whitespace/operators', 3,
          'Missing spaces around %s' % match.group(1))

  # There shouldn't be space around unary operators
  match = Search(r'(!\s|~\s|[\s]--[\s;]|[\s]\+\+[\s;])', line)
  if match:
    error(filename, linenum, 'whitespace/operators', 4,
          'Extra space for operator %s' % match.group(1))

  # A pet peeve of mine: no spaces after an if, while, switch, or for
  match = Search(r' (if\(|for\(|while\(|switch\()', line)
  if match:
    error(filename, linenum, 'whitespace/parens', 5,
          'Missing space before ( in %s' % match.group(1))

  # For if/for/while/switch, the left and right parens should be
  # consistent about how many spaces are inside the parens, and
  # there should either be zero or one spaces inside the parens.
  # We don't want: "if ( foo)" or "if ( foo   )".
  # Exception: "for ( ; foo; bar)" and "for (foo; bar; )" are allowed.
  match = Search(r'\b(if|for|while|switch)\s*'
                 r'\(([ ]*)(.).*[^ ]+([ ]*)\)\s*{\s*$',
                 line)
  if match:
    if len(match.group(2)) != len(match.group(4)):
      if not (match.group(3) == ';' and
              len(match.group(2)) == 1 + len(match.group(4)) or
              not match.group(2) and Search(r'\bfor\s*\(.*; \)', line)):
        error(filename, linenum, 'whitespace/parens', 5,
              'Mismatching spaces inside () in %s' % match.group(1))
    if not len(match.group(2)) in [0, 1]:
      error(filename, linenum, 'whitespace/parens', 5,
            'Should have zero or one spaces inside ( and ) in %s' %
            match.group(1))

  # You should always have a space after a comma (either as fn arg or operator)
  if Search(r',[^\s]', line):
    error(filename, linenum, 'whitespace/comma', 3,
          'Missing space after ,')

  # Next we will look for issues with function calls.
  CheckSpacingForFunctionCall(filename, line, linenum, error)

  # Except after an opening paren, you should have spaces before your braces.
  # And since you should never have braces at the beginning of a line, this is
  # an easy test.
  if Search(r'[^ (]{', line):
    error(filename, linenum, 'whitespace/braces', 5,
          'Missing space before {')

  # Make sure '} else {' has spaces.
  if Search(r'}else', line):
    error(filename, linenum, 'whitespace/braces', 5,
          'Missing space before else')

  # You shouldn't have spaces before your brackets, except maybe after
  # 'delete []' or 'new char * []'.
  if Search(r'\w\s+\[', line) and not Search(r'delete\s+\[', line):
    error(filename, linenum, 'whitespace/braces', 5,
          'Extra space before [')

  # You shouldn't have a space before a semicolon at the end of the line.
  # There's a special case for "for" since the style guide allows space before
  # the semicolon there.
  if Search(r':\s*;\s*$', line):
    error(filename, linenum, 'whitespace/semicolon', 5,
          'Semicolon defining empty statement. Use { } instead.')
  elif Search(r'^\s*;\s*$', line):
    error(filename, linenum, 'whitespace/semicolon', 5,
          'Line contains only semicolon. If this should be an empty statement, '
          'use { } instead.')
  elif (Search(r'\s+;\s*$', line) and
        not Search(r'\bfor\b', line)):
    error(filename, linenum, 'whitespace/semicolon', 5,
          'Extra space before last semicolon. If this should be an empty '
          'statement, use { } instead.')


def GetPreviousNonBlankLine(clean_lines, linenum):
  """Return the most recent non-blank line and its line number.

  Args:
    clean_lines: A CleansedLines instance containing the file contents.
    linenum: The number of the line to check.

  Returns:
    A tuple with two elements.  The first element is the contents of the last
    non-blank line before the current line, or the empty string if this is the
    first non-blank line.  The second is the line number of that line, or -1
    if this is the first non-blank line.
  """

  prevlinenum = linenum - 1
  while prevlinenum >= 0:
    prevline = clean_lines.elided[prevlinenum]
    if not IsBlankLine(prevline):     # if not a blank line...
      return (prevline, prevlinenum)
    prevlinenum -= 1
  return ('', -1)


def CheckBraces(filename, clean_lines, linenum, error):
  """Looks for misplaced braces (e.g. at the end of line).

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    error: The function to call with any errors found.
  """

  line = clean_lines.elided[linenum]        # get rid of comments and strings

  if Match(r'\s*{\s*$', line):
    # We allow an open brace to start a line in the case where someone
    # is using braces in a block to explicitly create a new scope,
    # which is commonly used to control the lifetime of
    # stack-allocated variables.  We don't detect this perfectly: we
    # just don't complain if the last non-whitespace character on the
    # previous non-blank line is ';', ':', '{', or '}'.
    prevline = GetPreviousNonBlankLine(clean_lines, linenum)[0]
    if not Search(r'[;:}{]\s*$', prevline):
      error(filename, linenum, 'whitespace/braces', 4,
            '{ should almost always be at the end of the previous line')

  # An else clause should be on the same line as the preceding closing brace.
  if Match(r'\s*else\s*', line):
    prevline = GetPreviousNonBlankLine(clean_lines, linenum)[0]
    if Match(r'\s*}\s*$', prevline):
      error(filename, linenum, 'whitespace/newline', 4,
            'An else should appear on the same line as the preceding }')

  # If braces come on one side of an else, they should be on both.
  # However, we have to worry about "else if" that spans multiple lines!
  if Search(r'}\s*else[^{]*$', line) or Match(r'[^}]*else\s*{', line):
    if Search(r'}\s*else if([^{]*)$', line):       # could be multi-line if
      # find the ( after the if
      pos = line.find('else if')
      pos = line.find('(', pos)
      if pos > 0:
        (endline, _, endpos) = CloseExpression(clean_lines, linenum, pos)
        if endline[endpos:].find('{') == -1:    # must be brace after if
          error(filename, linenum, 'readability/braces', 5,
                'If an else has a brace on one side, it should have it on both')
    else:            # common case: else not followed by a multi-line if
      error(filename, linenum, 'readability/braces', 5,
            'If an else has a brace on one side, it should have it on both')

  # Likewise, an else should never have the else clause on the same line
  if Search(r'\belse [^\s{]', line) and not Search(r'\belse if\b', line):
    error(filename, linenum, 'whitespace/newline', 4,
          'Else clause should never be on same line as else (use 2 lines)')

  # In the same way, a do/while should never be on one line
  if Match(r'\s*do [^\s{]', line):
    error(filename, linenum, 'whitespace/newline', 4,
          'do/while clauses should not be on a single line')

  # Braces shouldn't be followed by a ; unless they're defining a struct
  # or initializing an array.
  # We can't tell in general, but we can for some common cases.
  prevlinenum = linenum
  while True:
    (prevline, prevlinenum) = GetPreviousNonBlankLine(clean_lines, prevlinenum)
    if Match(r'\s+{.*}\s*;', line) and not prevline.count(';'):
      line = prevline + line
    else:
      break
  if (Search(r'{.*}\s*;', line) and
      line.count('{') == line.count('}') and
      not Search(r'struct|class|enum|\s*=\s*{', line)):
    error(filename, linenum, 'readability/braces', 4,
          "You don't need a ; after a }")


def ReplaceableCheck(operator, macro, line):
  """Determine whether a basic CHECK can be replaced with a more specific one.

  For example suggest using CHECK_EQ instead of CHECK(a == b) and
  similarly for CHECK_GE, CHECK_GT, CHECK_LE, CHECK_LT, CHECK_NE.

  Args:
    operator: The C++ operator used in the CHECK.
    macro: The CHECK or EXPECT macro being called.
    line: The current source line.

  Returns:
    True if the CHECK can be replaced with a more specific one.
  """

  # This matches decimal and hex integers, strings, and chars (in that order).
  match_constant = r'([-+]?(\d+|0[xX][0-9a-fA-F]+)[lLuU]{0,3}|".*"|\'.*\')'

  # Expression to match two sides of the operator with something that
  # looks like a literal, since CHECK(x == iterator) won't compile.
  # This means we can't catch all the cases where a more specific
  # CHECK is possible, but it's less annoying than dealing with
  # extraneous warnings.
  match_this = (r'\s*' + macro + r'\((\s*' +
                match_constant + r'\s*' + operator + r'[^<>].*|'
                r'.*[^<>]' + operator + r'\s*' + match_constant +
                r'\s*\))')

  # Don't complain about CHECK(x == NULL) or similar because
  # CHECK_EQ(x, NULL) won't compile (requires a cast).
  # Also, don't complain about more complex boolean expressions
  # involving && or || such as CHECK(a == b || c == d).
  return Match(match_this, line) and not Search(r'NULL|&&|\|\|', line)


def CheckCheck(filename, clean_lines, linenum, error):
  """Checks the use of CHECK and EXPECT macros.

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    error: The function to call with any errors found.
  """

  # Decide the set of replacement macros that should be suggested
  raw_lines = clean_lines.raw_lines
  current_macro = ''
  for macro in _CHECK_MACROS:
    if raw_lines[linenum].find(macro) >= 0:
      current_macro = macro
      break
  if not current_macro:
    # Don't waste time here if line doesn't contain 'CHECK' or 'EXPECT'
    return

  line = clean_lines.elided[linenum]        # get rid of comments and strings

  # Encourage replacing plain CHECKs with CHECK_EQ/CHECK_NE/etc.
  for operator in ['==', '!=', '>=', '>', '<=', '<']:
    if ReplaceableCheck(operator, current_macro, line):
      error(filename, linenum, 'readability/check', 2,
            'Consider using %s instead of %s(a %s b)' % (
                _CHECK_REPLACEMENT[current_macro][operator],
                current_macro, operator))
      break


def GetLineWidth(line):
  """Determines the width of the line in column positions.

  Args:
    line: A string, which may be a Unicode string.

  Returns:
    The width of the line in column positions, accounting for Unicode
    combining characters and wide characters.
  """
  if isinstance(line, unicode):
    width = 0
    for c in unicodedata.normalize('NFC', line):
      if unicodedata.east_asian_width(c) in ('W', 'F'):
        width += 2
      elif not unicodedata.combining(c):
        width += 1
    return width
  else:
    return len(line)


def CheckStyle(filename, clean_lines, linenum, file_extension, error):
  """Checks rules from the 'C++ style rules' section of cppguide.html.

  Most of these rules are hard to test (naming, comment style), but we
  do what we can.  In particular we check for 2-space indents, line lengths,
  tab usage, spaces inside code, etc.

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    file_extension: The extension (without the dot) of the filename.
    error: The function to call with any errors found.
  """

  raw_lines = clean_lines.raw_lines
  line = raw_lines[linenum]

  if line.find('\t') != -1:
    error(filename, linenum, 'whitespace/tab', 1,
          'Tab found; better to use spaces')

  # One or three blank spaces at the beginning of the line is weird; it's
  # hard to reconcile that with 2-space indents.
  # NOTE: here are the conditions rob pike used for his tests.  Mine aren't
  # as sophisticated, but it may be worth becoming so:  RLENGTH==initial_spaces
  # if(RLENGTH > 20) complain = 0;
  # if(match($0, " +(error|private|public|protected):")) complain = 0;
  # if(match(prev, "&& *$")) complain = 0;
  # if(match(prev, "\\|\\| *$")) complain = 0;
  # if(match(prev, "[\",=><] *$")) complain = 0;
  # if(match($0, " <<")) complain = 0;
  # if(match(prev, " +for \\(")) complain = 0;
  # if(prevodd && match(prevprev, " +for \\(")) complain = 0;
  initial_spaces = 0
  cleansed_line = clean_lines.elided[linenum]
  while initial_spaces < len(line) and line[initial_spaces] == ' ':
    initial_spaces += 1
  if line and line[-1].isspace():
    error(filename, linenum, 'whitespace/end_of_line', 4,
          'Line ends in whitespace.  Consider deleting these extra spaces.')
  # There are certain situations we allow one space, notably for labels
  elif ((initial_spaces == 1 or initial_spaces == 3) and
        not Match(r'\s*\w+\s*:\s*$', cleansed_line)):
    error(filename, linenum, 'whitespace/indent', 3,
          'Weird number of spaces at line-start.  '
          'Are you using a 2-space indent?')
  # Labels should always be indented at least one space.
  elif not initial_spaces and line[:2] != '//' and Search(r'[^:]:\s*$',
                                                          line):
    error(filename, linenum, 'whitespace/labels', 4,
          'Labels should always be indented at least one space.  '
          'If this is a member-initializer list in a constructor, '
          'the colon should be on the line after the definition header.')

  # Check if the line is a header guard.
  is_header_guard = False
  if file_extension == 'h':
    cppvar = GetHeaderGuardCPPVariable(filename)
    if (line.startswith('#ifndef %s' % cppvar) or
        line.startswith('#define %s' % cppvar) or
        line.startswith('#endif  // %s' % cppvar)):
      is_header_guard = True
  # #include lines and header guards can be long, since there's no clean way to
  # split them.
  #
  # URLs can be long too.  It's possible to split these, but it makes them
  # harder to cut&paste.
  if (not line.startswith('#include') and not is_header_guard and
      not Match(r'^\s*//.*http(s?)://\S*$', line)):
    line_width = GetLineWidth(line)
    if line_width > 100:
      error(filename, linenum, 'whitespace/line_length', 4,
            'Lines should very rarely be longer than 100 characters')
    elif line_width > 80:
      error(filename, linenum, 'whitespace/line_length', 2,
            'Lines should be <= 80 characters long')

  if (cleansed_line.count(';') > 1 and
      # for loops are allowed two ;'s (and may run over two lines).
      cleansed_line.find('for') == -1 and
      (GetPreviousNonBlankLine(clean_lines, linenum)[0].find('for') == -1 or
       GetPreviousNonBlankLine(clean_lines, linenum)[0].find(';') != -1) and
      # It's ok to have many commands in a switch case that fits in 1 line
      not ((cleansed_line.find('case ') != -1 or
            cleansed_line.find('default:') != -1) and
           cleansed_line.find('break;') != -1)):
    error(filename, linenum, 'whitespace/newline', 4,
          'More than one command on the same line')

  # Some more style checks
  CheckBraces(filename, clean_lines, linenum, error)
  CheckSpacing(filename, clean_lines, linenum, error)
  CheckCheck(filename, clean_lines, linenum, error)


_RE_PATTERN_INCLUDE_NEW_STYLE = re.compile(r'#include +"[^/]+\.h"')
_RE_PATTERN_INCLUDE = re.compile(r'^\s*#\s*include\s*([<"])([^>"]*)[>"].*$')
# Matches the first component of a filename delimited by -s and _s. That is:
#  _RE_FIRST_COMPONENT.match('foo').group(0) == 'foo'
#  _RE_FIRST_COMPONENT.match('foo.cc').group(0) == 'foo'
#  _RE_FIRST_COMPONENT.match('foo-bar_baz.cc').group(0) == 'foo'
#  _RE_FIRST_COMPONENT.match('foo_bar-baz.cc').group(0) == 'foo'
_RE_FIRST_COMPONENT = re.compile(r'^[^-_.]+')


def _DropCommonSuffixes(filename):
  """Drops common suffixes like _test.cc or -inl.h from filename.

  For example:
    >>> _DropCommonSuffixes('foo/foo-inl.h')
    'foo/foo'
    >>> _DropCommonSuffixes('foo/bar/foo.cc')
    'foo/bar/foo'
    >>> _DropCommonSuffixes('foo/foo_internal.h')
    'foo/foo'
    >>> _DropCommonSuffixes('foo/foo_unusualinternal.h')
    'foo/foo_unusualinternal'

  Args:
    filename: The input filename.

  Returns:
    The filename with the common suffix removed.
  """
  for suffix in ('test.cc', 'regtest.cc', 'unittest.cc',
                 'inl.h', 'impl.h', 'internal.h'):
    if (filename.endswith(suffix) and len(filename) > len(suffix) and
        filename[-len(suffix) - 1] in ('-', '_')):
      return filename[:-len(suffix) - 1]
  return os.path.splitext(filename)[0]


def _IsTestFilename(filename):
  """Determines if the given filename has a suffix that identifies it as a test.

  Args:
    filename: The input filename.

  Returns:
    True if 'filename' looks like a test, False otherwise.
  """
  if (filename.endswith('_test.cc') or
      filename.endswith('_unittest.cc') or
      filename.endswith('_regtest.cc')):
    return True
  else:
    return False


def _ClassifyInclude(fileinfo, include, is_system):
  """Figures out what kind of header 'include' is.

  Args:
    fileinfo: The current file cpplint is running over. A FileInfo instance.
    include: The path to a #included file.
    is_system: True if the #include used <> rather than "".

  Returns:
    One of the _XXX_HEADER constants.

  For example:
    >>> _ClassifyInclude(FileInfo('foo/foo.cc'), 'stdio.h', True)
    _C_SYS_HEADER
    >>> _ClassifyInclude(FileInfo('foo/foo.cc'), 'string', True)
    _CPP_SYS_HEADER
    >>> _ClassifyInclude(FileInfo('foo/foo.cc'), 'foo/foo.h', False)
    _LIKELY_MY_HEADER
    >>> _ClassifyInclude(FileInfo('foo/foo_unknown_extension.cc'),
    ...                  'bar/foo_other_ext.h', False)
    _POSSIBLE_MY_HEADER
    >>> _ClassifyInclude(FileInfo('foo/foo.cc'), 'foo/bar.h', False)
    _OTHER_HEADER
  """
  # This is a list of all standard c++ header files, except
  # those already checked for above.
  is_stl_h = include in _STL_HEADERS
  is_cpp_h = is_stl_h or include in _CPP_HEADERS

  if is_system:
    if is_cpp_h:
      return _CPP_SYS_HEADER
    else:
      return _C_SYS_HEADER

  # If the target file and the include we're checking share a
  # basename when we drop common extensions, and the include
  # lives in . , then it's likely to be owned by the target file.
  target_dir, target_base = (
      os.path.split(_DropCommonSuffixes(fileinfo.RepositoryName())))
  include_dir, include_base = os.path.split(_DropCommonSuffixes(include))
  if target_base == include_base and (
      include_dir == target_dir or
      include_dir == os.path.normpath(target_dir + '/../public')):
    return _LIKELY_MY_HEADER

  # If the target and include share some initial basename
  # component, it's possible the target is implementing the
  # include, so it's allowed to be first, but we'll never
  # complain if it's not there.
  target_first_component = _RE_FIRST_COMPONENT.match(target_base)
  include_first_component = _RE_FIRST_COMPONENT.match(include_base)
  if (target_first_component and include_first_component and
      target_first_component.group(0) ==
      include_first_component.group(0)):
    return _POSSIBLE_MY_HEADER

  return _OTHER_HEADER



def CheckGlobalInclude(filename, clean_lines, linenum, include_state, error):
  """Check rules that are applicable to #include lines.

  config.h should NEVER be included in headers
  unless those headers end in _priv and therefore are private headers.

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    include_state: An _IncludeState instance in which the headers are inserted.
    error: The function to call with any errors found.
  """
  if filename.endswith("config.h") or filename.endswith("_priv.h") or not filename.endswith(".h"):
    return

  fileinfo = FileInfo(filename)

  line = clean_lines.lines[linenum]

  match = _RE_PATTERN_INCLUDE.search(line)
  if match:
    include = match.group(2)
    if Match(r'(config|global|server_includes|_priv)\.h$', include):
      error(filename, linenum, 'build/include_config', 4,
            'Do not include config.h or files that include config.h in .h files')
      
def CheckIncludeLine(filename, clean_lines, linenum, include_state, error):
  """Check rules that are applicable to #include lines.

  Strings on #include lines are NOT removed from elided line, to make
  certain tasks easier. However, to prevent false positives, checks
  applicable to #include lines in CheckLanguage must be put here.

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    include_state: An _IncludeState instance in which the headers are inserted.
    error: The function to call with any errors found.
  """
  fileinfo = FileInfo(filename)

  line = clean_lines.lines[linenum]

  # "include" should use the new style "foo/bar.h" instead of just "bar.h"
  if _RE_PATTERN_INCLUDE_NEW_STYLE.search(line):
    error(filename, linenum, 'build/include', 4,
          'Include the directory when naming .h files')

  # we shouldn't include a file more than once. actually, there are a
  # handful of instances where doing so is okay, but in general it's
  # not.
  match = _RE_PATTERN_INCLUDE.search(line)
  if match:
    include = match.group(2)
    is_system = (match.group(1) == '<')
    if include in include_state:
      error(filename, linenum, 'build/include', 4,
            '"%s" already included at %s:%s' %
            (include, filename, include_state[include]))
    else:
      include_state[include] = linenum

      # We want to ensure that headers appear in the right order:
      # 1) for foo.cc, foo.h  (preferred location)
      # 2) c system files
      # 3) cpp system files
      # 4) for foo.cc, foo.h  (deprecated location)
      # 5) other google headers
      #
      # We classify each include statement as one of those 5 types
      # using a number of techniques. The include_state object keeps
      # track of the highest type seen, and complains if we see a
      # lower type after that.
      error_message = include_state.CheckNextIncludeOrder(
          _ClassifyInclude(fileinfo, include, is_system))
      if error_message:
        error(filename, linenum, 'build/include_order', 4,
              '%s. Should be: %s.h, c system, c++ system, other.' %
              (error_message, fileinfo.BaseName()))

  # Look for any of the stream classes that are part of standard C++.
  match = _RE_PATTERN_INCLUDE.match(line)
  if match:
    include = match.group(2)
    if Match(r'(f|ind|io|i|o|parse|pf|stdio|str|)?stream$', include):
      # Many unit tests use cout, so we exempt them.
      if not _IsTestFilename(filename):
        error(filename, linenum, 'readability/streams', 3,
              'Streams are highly discouraged.')

def CheckLanguage(filename, clean_lines, linenum, file_extension, include_state,
                  error):
  """Checks rules from the 'C++ language rules' section of cppguide.html.

  Some of these rules are hard to test (function overloading, using
  uint32 inappropriately), but we do the best we can.

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    linenum: The number of the line to check.
    file_extension: The extension (without the dot) of the filename.
    include_state: An _IncludeState instance in which the headers are inserted.
    error: The function to call with any errors found.
  """
  # If the line is empty or consists of entirely a comment, no need to
  # check it.
  line = clean_lines.elided[linenum]
  if not line:
    return

  match = _RE_PATTERN_INCLUDE.search(line)
  if match:
    CheckIncludeLine(filename, clean_lines, linenum, include_state, error)
    CheckGlobalInclude(filename, clean_lines, linenum, include_state, error)
    return

  # Create an extended_line, which is the concatenation of the current and
  # next lines, for more effective checking of code that may span more than one
  # line.
  if linenum + 1 < clean_lines.NumLines():
    extended_line = line + clean_lines.elided[linenum + 1]
  else:
    extended_line = line

  # Make Windows paths like Unix.
  fullname = os.path.abspath(filename).replace('\\', '/')

  # TODO(unknown): figure out if they're using default arguments in fn proto.

  # Check to see if they're using an conversion function cast.
  # I just try to capture the most common basic types, though there are more.
  # Parameterless conversion functions, such as bool(), are allowed as they are
  # probably a member operator declaration or default constructor.
  match = Search(
      r'\b(int|float|double|bool|char|int32|uint32|int64|uint64)\([^)]', line)
  if match:
    # gMock methods are defined using some variant of MOCK_METHODx(name, type)
    # where type may be float(), int(string), etc.  Without context they are
    # virtually indistinguishable from int(x) casts.
    if not Match(r'^\s*MOCK_(CONST_)?METHOD\d+(_T)?\(', line):
      error(filename, linenum, 'readability/casting', 4,
            'Using deprecated casting style.  '
            'Use static_cast<%s>(...) instead' %
            match.group(1))

  CheckCStyleCast(filename, linenum, line, clean_lines.raw_lines[linenum],
                  'static_cast',
                  r'\((int|float|double|bool|char|u?int(16|32|64))\)',
                  error)
  # This doesn't catch all cases.  Consider (const char * const)"hello".
  CheckCStyleCast(filename, linenum, line, clean_lines.raw_lines[linenum],
                  'reinterpret_cast', r'\((\w+\s?\*+\s?)\)', error)

  # In addition, we look for people taking the address of a cast.  This
  # is dangerous -- casts can assign to temporaries, so the pointer doesn't
  # point where you think.
  if Search(
      r'(&\([^)]+\)[\w(])|(&(static|dynamic|reinterpret)_cast\b)', line):
    error(filename, linenum, 'runtime/casting', 4,
          ('Are you taking an address of a cast?  '
           'This is dangerous: could be a temp var.  '
           'Take the address before doing the cast, rather than after'))

  # Check for people declaring static/global STL strings at the top level.
  # This is dangerous because the C++ language does not guarantee that
  # globals with constructors are initialized before the first access.
  match = Match(
      r'((?:|static +)(?:|const +))string +([a-zA-Z0-9_:]+)\b(.*)',
      line)
  # Make sure it's not a function.
  # Function template specialization looks like: "string foo<Type>(...".
  # Class template definitions look like: "string Foo<Type>::Method(...".
  if match and not Match(r'\s*(<.*>)?(::[a-zA-Z0-9_]+)?\s*\(([^"]|$)',
                         match.group(3)):
    error(filename, linenum, 'runtime/string', 4,
          'For a static/global string constant, use a C style string instead: '
          '"%schar %s[]".' %
          (match.group(1), match.group(2)))

  # Check that we're not using RTTI outside of testing code.
  if Search(r'\bdynamic_cast<', line) and not _IsTestFilename(filename):
    error(filename, linenum, 'runtime/rtti', 5,
          'Do not use dynamic_cast<>.  If you need to cast within a class '
          "hierarchy, use static_cast<> to upcast.  Google doesn't support "
          'RTTI.')

  if Search(r'\b([A-Za-z0-9_]*_)\(\1\)', line):
    error(filename, linenum, 'runtime/init', 4,
          'You seem to be initializing a member variable with itself.')

  if file_extension == 'h':
    # TODO(unknown): check that 1-arg constructors are explicit.
    #                How to tell it's a constructor?
    #                (handled in CheckForNonStandardConstructs for now)
    # TODO(unknown): check that classes have DISALLOW_EVIL_CONSTRUCTORS
    #                (level 1 error)
    pass

  # Check if people are using the verboten C basic types.  The only exception
  # we regularly allow is "unsigned short port" for port.
  if Search(r'\bshort port\b', line):
    if not Search(r'\bunsigned short port\b', line):
      error(filename, linenum, 'runtime/int', 4,
            'Use "unsigned short" for ports, not "short"')
  else:
    match = Search(r'\b(short|long(?! +double)|long long)\b', line)
    if match:
      error(filename, linenum, 'runtime/int', 4,
            'Use int16/int64/etc, rather than the C type %s' % match.group(1))

  # When snprintf is used, the second argument shouldn't be a literal.
  match = Search(r'snprintf\s*\(([^,]*),\s*([0-9]*)\s*,', line)
  if match:
    error(filename, linenum, 'runtime/printf', 3,
          'If you can, use sizeof(%s) instead of %s as the 2nd arg '
          'to snprintf.' % (match.group(1), match.group(2)))

  # Check if some verboten C functions are being used.
  if Search(r'\bsprintf\b', line):
    error(filename, linenum, 'runtime/printf', 5,
          'Never use sprintf.  Use snprintf instead.')
  match = Search(r'\b(strcpy|strcat)\b', line)
  if match:
    error(filename, linenum, 'runtime/printf', 4,
          'Almost always, snprintf is better than %s' % match.group(1))

  if Search(r'\bsscanf\b', line):
    error(filename, linenum, 'runtime/printf', 1,
          'sscanf can be ok, but is slow and can overflow buffers.')

  # Check for suspicious usage of "if" like
  # } if (a == b) {
  if Search(r'\}\s*if\s*\(', line):
    error(filename, linenum, 'readability/braces', 4,
          'Did you mean "else if"? If not, start a new line for "if".')

  # Check for potential format string bugs like printf(foo).
  # We constrain the pattern not to pick things like DocidForPrintf(foo).
  # Not perfect but it can catch printf(foo.c_str()) and printf(foo->c_str())
  match = re.search(r'\b((?:string)?printf)\s*\(([\w.\->()]+)\)', line, re.I)
  if match:
    error(filename, linenum, 'runtime/printf', 4,
          'Potential format string bug. Do %s("%%s", %s) instead.'
          % (match.group(1), match.group(2)))

  # Check for potential memset bugs like memset(buf, sizeof(buf), 0).
  match = Search(r'memset\s*\(([^,]*),\s*([^,]*),\s*0\s*\)', line)
  if match and not Match(r"^''|-?[0-9]+|0x[0-9A-Fa-f]$", match.group(2)):
    error(filename, linenum, 'runtime/memset', 4,
          'Did you mean "memset(%s, 0, %s)"?'
          % (match.group(1), match.group(2)))

  if Search(r'\busing namespace\b', line) and filename.endswith(".h"):
    error(filename, linenum, 'build/namespaces', 5,
          'Do not use namespace using-directives in headers.  ')

  # Detect variable-length arrays.
  match = Match(r'\s*(.+::)?(\w+) [a-z]\w*\[(.+)];', line)
  if (match and match.group(2) != 'return' and match.group(2) != 'delete' and
      match.group(3).find(']') == -1):
    # Split the size using space and arithmetic operators as delimiters.
    # If any of the resulting tokens are not compile time constants then
    # report the error.
    tokens = re.split(r'\s|\+|\-|\*|\/|<<|>>]', match.group(3))
    is_const = True
    skip_next = False
    for tok in tokens:
      if skip_next:
        skip_next = False
        continue

      if Search(r'sizeof\(.+\)', tok): continue
      if Search(r'arraysize\(\w+\)', tok): continue

      tok = tok.lstrip('(')
      tok = tok.rstrip(')')
      if not tok: continue
      if Match(r'\d+', tok): continue
      if Match(r'0[xX][0-9a-fA-F]+', tok): continue
      if Match(r'k[A-Z0-9]\w*', tok): continue
      if Match(r'(.+::)?k[A-Z0-9]\w*', tok): continue
      if Match(r'(.+::)?[A-Z][A-Z0-9_]*', tok): continue
      # A catch all for tricky sizeof cases, including 'sizeof expression',
      # 'sizeof(*type)', 'sizeof(const type)', 'sizeof(struct StructName)'
      # requires skipping the next token becasue we split on ' ' and '*'.
      if tok.startswith('sizeof'):
        skip_next = True
        continue
      is_const = False
      break
    if not is_const:
      error(filename, linenum, 'runtime/arrays', 1,
            'Do not use variable-length arrays.  Use an appropriately named '
            "('k' followed by CamelCase) compile-time constant for the size.")

  # If DISALLOW_EVIL_CONSTRUCTORS, DISALLOW_COPY_AND_ASSIGN, or
  # DISALLOW_IMPLICIT_CONSTRUCTORS is present, then it should be the last thing
  # in the class declaration.
  match = Match(
      (r'\s*'
       r'(DISALLOW_(EVIL_CONSTRUCTORS|COPY_AND_ASSIGN|IMPLICIT_CONSTRUCTORS))'
       r'\(.*\);$'),
      line)
  if match and linenum + 1 < clean_lines.NumLines():
    next_line = clean_lines.elided[linenum + 1]
    if not Search(r'^\s*};', next_line):
      error(filename, linenum, 'readability/constructors', 3,
            match.group(1) + ' should be the last thing in the class')

  # Check for use of unnamed namespaces in header files.  Registration
  # macros are typically OK, so we allow use of "namespace {" on lines
  # that end with backslashes.
  if (file_extension == 'h'
      and Search(r'\bnamespace\s*{', line)
      and line[-1] != '\\'):
    error(filename, linenum, 'build/namespaces', 4,
          'Do not use unnamed namespaces in header files.  See '
          'http://google-styleguide.googlecode.com/svn/trunk/cppguide.xml#Namespaces'
          ' for more information.')


def CheckCStyleCast(filename, linenum, line, raw_line, cast_type, pattern,
                    error):
  """Checks for a C-style cast by looking for the pattern.

  This also handles sizeof(type) warnings, due to similarity of content.

  Args:
    filename: The name of the current file.
    linenum: The number of the line to check.
    line: The line of code to check.
    raw_line: The raw line of code to check, with comments.
    cast_type: The string for the C++ cast to recommend.  This is either
      reinterpret_cast or static_cast, depending.
    pattern: The regular expression used to find C-style casts.
    error: The function to call with any errors found.
  """
  match = Search(pattern, line)
  if not match:
    return

  # e.g., sizeof(int)
  sizeof_match = Match(r'.*sizeof\s*$', line[0:match.start(1) - 1])
  if sizeof_match:
    error(filename, linenum, 'runtime/sizeof', 1,
          'Using sizeof(type).  Use sizeof(varname) instead if possible')
    return

  remainder = line[match.end(0):]

  # The close paren is for function pointers as arguments to a function.
  # eg, void foo(void (*bar)(int));
  # The semicolon check is a more basic function check; also possibly a
  # function pointer typedef.
  # eg, void foo(int); or void foo(int) const;
  # The equals check is for function pointer assignment.
  # eg, void *(*foo)(int) = ...
  #
  # Right now, this will only catch cases where there's a single argument, and
  # it's unnamed.  It should probably be expanded to check for multiple
  # arguments with some unnamed.
  function_match = Match(r'\s*(\)|=|(const)?\s*(;|\{|throw\(\)))', remainder)
  if function_match:
    if (not function_match.group(3) or
        function_match.group(3) == ';' or
        raw_line.find('/*') < 0):
      error(filename, linenum, 'readability/function', 3,
            'All parameters should be named in a function')
    return

  # At this point, all that should be left is actual casts.
  error(filename, linenum, 'readability/casting', 4,
        'Using C-style cast.  Use %s<%s>(...) instead' %
        (cast_type, match.group(1)))


_HEADERS_CONTAINING_TEMPLATES = (
    ('<deque>', ('deque',)),
    ('<functional>', ('unary_function', 'binary_function',
                      'plus', 'minus', 'multiplies', 'divides', 'modulus',
                      'negate',
                      'equal_to', 'not_equal_to', 'greater', 'less',
                      'greater_equal', 'less_equal',
                      'logical_and', 'logical_or', 'logical_not',
                      'unary_negate', 'not1', 'binary_negate', 'not2',
                      'bind1st', 'bind2nd',
                      'pointer_to_unary_function',
                      'pointer_to_binary_function',
                      'ptr_fun',
                      'mem_fun_t', 'mem_fun', 'mem_fun1_t', 'mem_fun1_ref_t',
                      'mem_fun_ref_t',
                      'const_mem_fun_t', 'const_mem_fun1_t',
                      'const_mem_fun_ref_t', 'const_mem_fun1_ref_t',
                      'mem_fun_ref',
                     )),
    ('<limits>', ('numeric_limits',)),
    ('<list>', ('list',)),
    ('<map>', ('map', 'multimap',)),
    ('<memory>', ('allocator',)),
    ('<queue>', ('queue', 'priority_queue',)),
    ('<set>', ('set', 'multiset',)),
    ('<stack>', ('stack',)),
    ('<string>', ('char_traits', 'basic_string',)),
    ('<utility>', ('pair',)),
    ('<vector>', ('vector',)),

    # gcc extensions.
    # Note: std::hash is their hash, ::hash is our hash
    ('<hash_map>', ('hash_map', 'hash_multimap',)),
    ('<hash_set>', ('hash_set', 'hash_multiset',)),
    ('<slist>', ('slist',)),
    )

_HEADERS_ACCEPTED_BUT_NOT_PROMOTED = {
    # We can trust with reasonable confidence that map gives us pair<>, too.
    'pair<>': ('map', 'multimap', 'hash_map', 'hash_multimap')
}

_RE_PATTERN_STRING = re.compile(r'\bstring\b')

_re_pattern_algorithm_header = []
for _template in ('copy', 'max', 'min', 'min_element', 'sort', 'swap',
                  'transform'):
  # Match max<type>(..., ...), max(..., ...), but not foo->max, foo.max or
  # type::max().
  _re_pattern_algorithm_header.append(
      (re.compile(r'[^>.]\b' + _template + r'(<.*?>)?\([^\)]'),
       _template,
       '<algorithm>'))

_re_pattern_templates = []
for _header, _templates in _HEADERS_CONTAINING_TEMPLATES:
  for _template in _templates:
    _re_pattern_templates.append(
        (re.compile(r'(\<|\b)' + _template + r'\s*\<'),
         _template + '<>',
         _header))


def FilesBelongToSameModule(filename_cc, filename_h):
  """Check if these two filenames belong to the same module.

  The concept of a 'module' here is a as follows:
  foo.h, foo-inl.h, foo.cc, foo_test.cc and foo_unittest.cc belong to the
  same 'module' if they are in the same directory.
  some/path/public/xyzzy and some/path/internal/xyzzy are also considered
  to belong to the same module here.

  If the filename_cc contains a longer path than the filename_h, for example,
  '/absolute/path/to/base/sysinfo.cc', and this file would include
  'base/sysinfo.h', this function also produces the prefix needed to open the
  header. This is used by the caller of this function to more robustly open the
  header file. We don't have access to the real include paths in this context,
  so we need this guesswork here.

  Known bugs: tools/base/bar.cc and base/bar.h belong to the same module
  according to this implementation. Because of this, this function gives
  some false positives. This should be sufficiently rare in practice.

  Args:
    filename_cc: is the path for the .cc file
    filename_h: is the path for the header path

  Returns:
    Tuple with a bool and a string:
    bool: True if filename_cc and filename_h belong to the same module.
    string: the additional prefix needed to open the header file.
  """

  if not filename_cc.endswith('.cc'):
    return (False, '')
  filename_cc = filename_cc[:-len('.cc')]
  if filename_cc.endswith('_unittest'):
    filename_cc = filename_cc[:-len('_unittest')]
  elif filename_cc.endswith('_test'):
    filename_cc = filename_cc[:-len('_test')]
  filename_cc = filename_cc.replace('/public/', '/')
  filename_cc = filename_cc.replace('/internal/', '/')

  if not filename_h.endswith('.h'):
    return (False, '')
  filename_h = filename_h[:-len('.h')]
  if filename_h.endswith('-inl'):
    filename_h = filename_h[:-len('-inl')]
  filename_h = filename_h.replace('/public/', '/')
  filename_h = filename_h.replace('/internal/', '/')

  files_belong_to_same_module = filename_cc.endswith(filename_h)
  common_path = ''
  if files_belong_to_same_module:
    common_path = filename_cc[:-len(filename_h)]
  return files_belong_to_same_module, common_path


def UpdateIncludeState(filename, include_state, io=codecs):
  """Fill up the include_state with new includes found from the file.

  Args:
    filename: the name of the header to read.
    include_state: an _IncludeState instance in which the headers are inserted.
    io: The io factory to use to read the file. Provided for testability.

  Returns:
    True if a header was succesfully added. False otherwise.
  """
  headerfile = None
  try:
    headerfile = io.open(filename, 'r', 'utf8', 'replace')
  except IOError:
    return False
  _cpplint_state.seen_file(filename)
  linenum = 0
  for line in headerfile:
    linenum += 1
    clean_line = CleanseComments(line)
    match = _RE_PATTERN_INCLUDE.search(clean_line)
    if match:
      include = match.group(2)
      # The value formatting is cute, but not really used right now.
      # What matters here is that the key is in include_state.
      include_state.setdefault(include, '%s:%d' % (filename, linenum))
  return True


def CheckForIncludeWhatYouUse(filename, clean_lines, include_state, error,
                              io=codecs):
  """Reports for missing stl includes.

  This function will output warnings to make sure you are including the headers
  necessary for the stl containers and functions that you use. We only give one
  reason to include a header. For example, if you use both equal_to<> and
  less<> in a .h file, only one (the latter in the file) of these will be
  reported as a reason to include the <functional>.

  Args:
    filename: The name of the current file.
    clean_lines: A CleansedLines instance containing the file.
    include_state: An _IncludeState instance.
    error: The function to call with any errors found.
    io: The IO factory to use to read the header file. Provided for unittest
        injection.
  """
  required = {}  # A map of header name to linenumber and the template entity.
                 # Example of required: { '<functional>': (1219, 'less<>') }

  for linenum in xrange(clean_lines.NumLines()):
    line = clean_lines.elided[linenum]
    if not line or line[0] == '#':
      continue

    # String is special -- it is a non-templatized type in STL.
    if _RE_PATTERN_STRING.search(line):
      required['<string>'] = (linenum, 'string')

    for pattern, template, header in _re_pattern_algorithm_header:
      if pattern.search(line):
        required[header] = (linenum, template)

    # The following function is just a speed up, no semantics are changed.
    if not '<' in line:  # Reduces the cpu time usage by skipping lines.
      continue

    for pattern, template, header in _re_pattern_templates:
      if pattern.search(line):
        required[header] = (linenum, template)

  # The policy is that if you #include something in foo.h you don't need to
  # include it again in foo.cc. Here, we will look at possible includes.
  # Let's copy the include_state so it is only messed up within this function.
  include_state = include_state.copy()

  # Did we find the header for this file (if any) and succesfully load it?
  header_found = False

  # Use the absolute path so that matching works properly.
  abs_filename = os.path.abspath(filename)

  # For Emacs's flymake.
  # If cpplint is invoked from Emacs's flymake, a temporary file is generated
  # by flymake and that file name might end with '_flymake.cc'. In that case,
  # restore original file name here so that the corresponding header file can be
  # found.
  # e.g. If the file name is 'foo_flymake.cc', we should search for 'foo.h'
  # instead of 'foo_flymake.h'
  emacs_flymake_suffix = '_flymake.cc'
  if abs_filename.endswith(emacs_flymake_suffix):
    abs_filename = abs_filename[:-len(emacs_flymake_suffix)] + '.cc'

  # include_state is modified during iteration, so we iterate over a copy of
  # the keys.
  for header in include_state.keys():  #NOLINT
    (same_module, common_path) = FilesBelongToSameModule(abs_filename, header)
    fullpath = common_path + header
    if same_module and UpdateIncludeState(fullpath, include_state, io):
      header_found = True

  # If we can't find the header file for a .cc, assume it's because we don't
  # know where to look. In that case we'll give up as we're not sure they
  # didn't include it in the .h file.
  # TODO(unknown): Do a better job of finding .h files so we are confident that
  # not having the .h file means there isn't one.
  if filename.endswith('.cc') and not header_found:
    return

  # All the lines have been processed, report the errors found.
  for required_header_unstripped in required:
    template = required[required_header_unstripped][1]
    if template in _HEADERS_ACCEPTED_BUT_NOT_PROMOTED:
      headers = _HEADERS_ACCEPTED_BUT_NOT_PROMOTED[template]
      if [True for header in headers if header in include_state]:
        continue
    if required_header_unstripped.strip('<>"') not in include_state:
      error(filename, required[required_header_unstripped][0],
            'build/include_what_you_use', 4,
            'Add #include ' + required_header_unstripped + ' for ' + template)


def ProcessLine(filename, file_extension,
                clean_lines, line, include_state, function_state,
                class_state, error):
  """Processes a single line in the file.

  Args:
    filename: Filename of the file that is being processed.
    file_extension: The extension (dot not included) of the file.
    clean_lines: An array of strings, each representing a line of the file,
                 with comments stripped.
    line: Number of line being processed.
    include_state: An _IncludeState instance in which the headers are inserted.
    function_state: A _FunctionState instance which counts function lines, etc.
    class_state: A _ClassState instance which maintains information about
                 the current stack of nested class declarations being parsed.
    error: A callable to which errors are reported, which takes 4 arguments:
           filename, line number, error level, and message

  """
  raw_lines = clean_lines.raw_lines
  CheckForFunctionLengths(filename, clean_lines, line, function_state, error)
  if Search(r'\bNOLINT\b', raw_lines[line]):  # ignore nolint lines
    return
  CheckForMultilineCommentsAndStrings(filename, clean_lines, line, error)
  CheckStyle(filename, clean_lines, line, file_extension, error)
  CheckLanguage(filename, clean_lines, line, file_extension, include_state,
                error)
  CheckForNonStandardConstructs(filename, clean_lines, line,
                                class_state, error)
  CheckPosixThreading(filename, clean_lines, line, error)
  CheckInvalidIncrement(filename, clean_lines, line, error)


def ProcessFileData(filename, file_extension, lines, error):
  """Performs lint checks and reports any errors to the given error function.

  Args:
    filename: Filename of the file that is being processed.
    file_extension: The extension (dot not included) of the file.
    lines: An array of strings, each representing a line of the file, with the
           last element being empty if the file is termined with a newline.
    error: A callable to which errors are reported, which takes 4 arguments:
  """
  lines = (['// marker so line numbers and indices both start at 1'] + lines +
           ['// marker so line numbers end in a known way'])

  include_state = _IncludeState()
  function_state = _FunctionState()
  class_state = _ClassState()

  CheckForCopyright(filename, lines, error)

  if file_extension == 'h':
    CheckForHeaderGuard(filename, lines, error)

  RemoveMultiLineComments(filename, lines, error)
  clean_lines = CleansedLines(lines)
  for line in xrange(clean_lines.NumLines()):
    ProcessLine(filename, file_extension, clean_lines, line,
                include_state, function_state, class_state, error)
  class_state.CheckFinished(filename, error)

  CheckForIncludeWhatYouUse(filename, clean_lines, include_state, error)

  # We check here rather than inside ProcessLine so that we see raw
  # lines rather than "cleaned" lines.
  CheckForUnicodeReplacementCharacters(filename, lines, error)

  CheckForNewlineAtEOF(filename, lines, error)


def ProcessFile(filename, vlevel):
  """Does google-lint on a single file.

  Args:
    filename: The name of the file to parse.

    vlevel: The level of errors to report.  Every error of confidence
    >= verbose_level will be reported.  0 is a good default.
  """

  _SetVerboseLevel(vlevel)

  try:
    # Support the UNIX convention of using "-" for stdin.  Note that
    # we are not opening the file with universal newline support
    # (which codecs doesn't support anyway), so the resulting lines do
    # contain trailing '\r' characters if we are reading a file that
    # has CRLF endings.
    # If after the split a trailing '\r' is present, it is removed
    # below. If it is not expected to be present (i.e. os.linesep !=
    # '\r\n' as in Windows), a warning is issued below if this file
    # is processed.

    if filename == '-':
      lines = codecs.StreamReaderWriter(sys.stdin,
                                        codecs.getreader('utf8'),
                                        codecs.getwriter('utf8'),
                                        'replace').read().split('\n')
    else:
      _cpplint_state.seen_file(filename)
      lines = codecs.open(filename, 'r', 'utf8', 'replace').read().split('\n')

    carriage_return_found = False
    # Remove trailing '\r'.
    for linenum in range(len(lines)):
      if lines[linenum].endswith('\r'):
        lines[linenum] = lines[linenum].rstrip('\r')
        carriage_return_found = True

  except IOError:
    sys.stderr.write(
        "Skipping input '%s': Can't open for reading\n" % filename)
    return

  # Note, if no dot is found, this will give the entire filename as the ext.
  file_extension = filename[filename.rfind('.') + 1:]

  # When reading from stdin, the extension is unknown, so no cpplint tests
  # should rely on the extension.
  if (filename != '-' and file_extension != 'cc' and file_extension != 'h'
      and file_extension != 'cpp'):
    sys.stderr.write('Ignoring %s; not a .cc or .h file\n' % filename)
  else:
    ProcessFileData(filename, file_extension, lines, Error)
    if carriage_return_found and os.linesep != '\r\n':
      # Use 0 for linenum since outputing only one error for potentially
      # several lines.
      Error(filename, 0, 'whitespace/newline', 1,
            'One or more unexpected \\r (^M) found;'
            'better to use only a \\n')

  sys.stderr.write('Done processing %s\n' % filename)


def PrintUsage(message):
  """Prints a brief usage string and exits, optionally with an error message.

  Args:
    message: The optional error message.
  """
  sys.stderr.write(_USAGE)
  if message:
    sys.exit('\nFATAL ERROR: ' + message)
  else:
    sys.exit(1)


def PrintCategories():
  """Prints a list of all the error-categories used by error messages.

  These are the categories used to filter messages via --filter.
  """
  sys.stderr.write(_ERROR_CATEGORIES)
  sys.exit(0)


def ParseArguments(args):
  """Parses the command line arguments.

  This may set the output format and verbosity level as side-effects.

  Args:
    args: The command line arguments:

  Returns:
    The list of filenames to lint.
  """
  try:
    (opts, filenames) = getopt.getopt(args, '',
        ['help', 'output=', 'verbose=', 'deps=', 'filter='])
  except getopt.GetoptError:
    PrintUsage('Invalid arguments.')

  verbosity = _VerboseLevel()
  output_format = _OutputFormat()
  filters = ''

  for (opt, val) in opts:
    if opt == '--help':
      PrintUsage(None)
    elif opt == '--output':
      if not val in ('emacs', 'vs7'):
        PrintUsage('The only allowed output formats are emacs and vs7.')
      output_format = val
    elif opt == '--verbose':
      verbosity = int(val)
    elif opt == '--filter':
      filters = val
      if not filters:
        PrintCategories()
    elif opt == '--deps':
        _cpplint_state.depfilename = val

  if not filenames:
    PrintUsage('No files were specified.')

  _SetOutputFormat(output_format)
  _SetVerboseLevel(verbosity)
  _SetFilters(filters)

  return filenames


def main():
  filenames = ParseArguments(sys.argv[1:])

  # Change stderr to write with replacement characters so we don't die
  # if we try to print something containing non-ASCII characters.
  sys.stderr = codecs.StreamReaderWriter(sys.stderr,
                                         codecs.getreader('utf8'),
                                         codecs.getwriter('utf8'),
                                         'replace')

  _cpplint_state.ResetErrorCount()
  for filename in filenames:
    ProcessFile(filename, _cpplint_state.verbose_level)
  _cpplint_state.finished()
  sys.stderr.write('Total errors found: %d\n' % _cpplint_state.error_count)
  sys.exit(_cpplint_state.error_count > 0)


if __name__ == '__main__':
  main()