This file is indexed.

/usr/lib/python3/dist-packages/cloudinit/util.py is in cloud-init 18.2-14-g6d48d265-0ubuntu1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

   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
# Copyright (C) 2012 Canonical Ltd.
# Copyright (C) 2012, 2013 Hewlett-Packard Development Company, L.P.
# Copyright (C) 2012 Yahoo! Inc.
#
# Author: Scott Moser <scott.moser@canonical.com>
# Author: Juerg Haefliger <juerg.haefliger@hp.com>
# Author: Joshua Harlow <harlowja@yahoo-inc.com>
#
# This file is part of cloud-init. See LICENSE file for license information.

import contextlib
import copy as obj_copy
import ctypes
import email
import glob
import grp
import gzip
import hashlib
import json
import os
import os.path
import platform
import pwd
import random
import re
import shlex
import shutil
import socket
import stat
import string
import subprocess
import sys
import time

from errno import ENOENT, ENOEXEC

from base64 import b64decode, b64encode
from six.moves.urllib import parse as urlparse

import six
import yaml

from cloudinit import importer
from cloudinit import log as logging
from cloudinit import mergers
from cloudinit import safeyaml
from cloudinit import temp_utils
from cloudinit import type_utils
from cloudinit import url_helper
from cloudinit import version

from cloudinit.settings import (CFG_BUILTIN)

try:
    string_types = (basestring,)
except NameError:
    string_types = (str,)

_DNS_REDIRECT_IP = None
LOG = logging.getLogger(__name__)

# Helps cleanup filenames to ensure they aren't FS incompatible
FN_REPLACEMENTS = {
    os.sep: '_',
}
FN_ALLOWED = ('_-.()' + string.digits + string.ascii_letters)

TRUE_STRINGS = ('true', '1', 'on', 'yes')
FALSE_STRINGS = ('off', '0', 'no', 'false')


# Helper utils to see if running in a container
CONTAINER_TESTS = (['systemd-detect-virt', '--quiet', '--container'],
                   ['running-in-container'],
                   ['lxc-is-container'])

PROC_CMDLINE = None

_LSB_RELEASE = {}
PY26 = sys.version_info[0:2] == (2, 6)


def get_architecture(target=None):
    out, _ = subp(['dpkg', '--print-architecture'], capture=True,
                  target=target)
    return out.strip()


def _lsb_release(target=None):
    fmap = {'Codename': 'codename', 'Description': 'description',
            'Distributor ID': 'id', 'Release': 'release'}

    data = {}
    try:
        out, _ = subp(['lsb_release', '--all'], capture=True, target=target)
        for line in out.splitlines():
            fname, _, val = line.partition(":")
            if fname in fmap:
                data[fmap[fname]] = val.strip()
        missing = [k for k in fmap.values() if k not in data]
        if len(missing):
            LOG.warning("Missing fields in lsb_release --all output: %s",
                        ','.join(missing))

    except ProcessExecutionError as err:
        LOG.warning("Unable to get lsb_release --all: %s", err)
        data = dict((v, "UNAVAILABLE") for v in fmap.values())

    return data


def lsb_release(target=None):
    if target_path(target) != "/":
        # do not use or update cache if target is provided
        return _lsb_release(target)

    global _LSB_RELEASE
    if not _LSB_RELEASE:
        data = _lsb_release()
        _LSB_RELEASE.update(data)
    return _LSB_RELEASE


def target_path(target, path=None):
    # return 'path' inside target, accepting target as None
    if target in (None, ""):
        target = "/"
    elif not isinstance(target, string_types):
        raise ValueError("Unexpected input for target: %s" % target)
    else:
        target = os.path.abspath(target)
        # abspath("//") returns "//" specifically for 2 slashes.
        if target.startswith("//"):
            target = target[1:]

    if not path:
        return target

    # os.path.join("/etc", "/foo") returns "/foo". Chomp all leading /.
    while len(path) and path[0] == "/":
        path = path[1:]

    return os.path.join(target, path)


def decode_binary(blob, encoding='utf-8'):
    # Converts a binary type into a text type using given encoding.
    if isinstance(blob, six.string_types):
        return blob
    return blob.decode(encoding)


def encode_text(text, encoding='utf-8'):
    # Converts a text string into a binary type using given encoding.
    if isinstance(text, six.binary_type):
        return text
    return text.encode(encoding)


def b64d(source):
    # Base64 decode some data, accepting bytes or unicode/str, and returning
    # str/unicode if the result is utf-8 compatible, otherwise returning bytes.
    decoded = b64decode(source)
    try:
        return decoded.decode('utf-8')
    except UnicodeDecodeError:
        return decoded


def b64e(source):
    # Base64 encode some data, accepting bytes or unicode/str, and returning
    # str/unicode if the result is utf-8 compatible, otherwise returning bytes.
    if not isinstance(source, bytes):
        source = source.encode('utf-8')
    return b64encode(source).decode('utf-8')


def fully_decoded_payload(part):
    # In Python 3, decoding the payload will ironically hand us a bytes object.
    # 'decode' means to decode according to Content-Transfer-Encoding, not
    # according to any charset in the Content-Type.  So, if we end up with
    # bytes, first try to decode to str via CT charset, and failing that, try
    # utf-8 using surrogate escapes.
    cte_payload = part.get_payload(decode=True)
    if (six.PY3 and
            part.get_content_maintype() == 'text' and
            isinstance(cte_payload, bytes)):
        charset = part.get_charset()
        if charset and charset.input_codec:
            encoding = charset.input_codec
        else:
            encoding = 'utf-8'
        return cte_payload.decode(encoding, 'surrogateescape')
    return cte_payload


# Path for DMI Data
DMI_SYS_PATH = "/sys/class/dmi/id"

# dmidecode and /sys/class/dmi/id/* use different names for the same value,
# this allows us to refer to them by one canonical name
DMIDECODE_TO_DMI_SYS_MAPPING = {
    'baseboard-asset-tag': 'board_asset_tag',
    'baseboard-manufacturer': 'board_vendor',
    'baseboard-product-name': 'board_name',
    'baseboard-serial-number': 'board_serial',
    'baseboard-version': 'board_version',
    'bios-release-date': 'bios_date',
    'bios-vendor': 'bios_vendor',
    'bios-version': 'bios_version',
    'chassis-asset-tag': 'chassis_asset_tag',
    'chassis-manufacturer': 'chassis_vendor',
    'chassis-serial-number': 'chassis_serial',
    'chassis-version': 'chassis_version',
    'system-manufacturer': 'sys_vendor',
    'system-product-name': 'product_name',
    'system-serial-number': 'product_serial',
    'system-uuid': 'product_uuid',
    'system-version': 'product_version',
}


class ProcessExecutionError(IOError):

    MESSAGE_TMPL = ('%(description)s\n'
                    'Command: %(cmd)s\n'
                    'Exit code: %(exit_code)s\n'
                    'Reason: %(reason)s\n'
                    'Stdout: %(stdout)s\n'
                    'Stderr: %(stderr)s')
    empty_attr = '-'

    def __init__(self, stdout=None, stderr=None,
                 exit_code=None, cmd=None,
                 description=None, reason=None,
                 errno=None):
        if not cmd:
            self.cmd = self.empty_attr
        else:
            self.cmd = cmd

        if not description:
            if not exit_code and errno == ENOEXEC:
                self.description = 'Exec format error. Missing #! in script?'
            else:
                self.description = 'Unexpected error while running command.'
        else:
            self.description = description

        if not isinstance(exit_code, six.integer_types):
            self.exit_code = self.empty_attr
        else:
            self.exit_code = exit_code

        if not stderr:
            if stderr is None:
                self.stderr = self.empty_attr
            else:
                self.stderr = stderr
        else:
            self.stderr = self._indent_text(stderr)

        if not stdout:
            if stdout is None:
                self.stdout = self.empty_attr
            else:
                self.stdout = stdout
        else:
            self.stdout = self._indent_text(stdout)

        if reason:
            self.reason = reason
        else:
            self.reason = self.empty_attr

        self.errno = errno
        message = self.MESSAGE_TMPL % {
            'description': self._ensure_string(self.description),
            'cmd': self._ensure_string(self.cmd),
            'exit_code': self._ensure_string(self.exit_code),
            'stdout': self._ensure_string(self.stdout),
            'stderr': self._ensure_string(self.stderr),
            'reason': self._ensure_string(self.reason),
        }
        IOError.__init__(self, message)

    def _ensure_string(self, text):
        """
        if data is bytes object, decode
        """
        return text.decode() if isinstance(text, six.binary_type) else text

    def _indent_text(self, text, indent_level=8):
        """
        indent text on all but the first line, allowing for easy to read output
        """
        cr = '\n'
        indent = ' ' * indent_level
        # if input is bytes, return bytes
        if isinstance(text, six.binary_type):
            cr = cr.encode()
            indent = indent.encode()
        # remove any newlines at end of text first to prevent unneeded blank
        # line in output
        return text.rstrip(cr).replace(cr, cr + indent)


class SeLinuxGuard(object):
    def __init__(self, path, recursive=False):
        # Late import since it might not always
        # be possible to use this
        try:
            self.selinux = importer.import_module('selinux')
        except ImportError:
            self.selinux = None
        self.path = path
        self.recursive = recursive

    def __enter__(self):
        if self.selinux and self.selinux.is_selinux_enabled():
            return True
        else:
            return False

    def __exit__(self, excp_type, excp_value, excp_traceback):
        if not self.selinux or not self.selinux.is_selinux_enabled():
            return
        if not os.path.lexists(self.path):
            return

        path = os.path.realpath(self.path)
        # path should be a string, not unicode
        if six.PY2:
            path = str(path)
        try:
            stats = os.lstat(path)
            self.selinux.matchpathcon(path, stats[stat.ST_MODE])
        except OSError:
            return

        LOG.debug("Restoring selinux mode for %s (recursive=%s)",
                  path, self.recursive)
        try:
            self.selinux.restorecon(path, recursive=self.recursive)
        except OSError as e:
            LOG.warning('restorecon failed on %s,%s maybe badness? %s',
                        path, self.recursive, e)


class MountFailedError(Exception):
    pass


class DecompressionError(Exception):
    pass


def fork_cb(child_cb, *args, **kwargs):
    fid = os.fork()
    if fid == 0:
        try:
            child_cb(*args, **kwargs)
            os._exit(0)
        except Exception:
            logexc(LOG, "Failed forking and calling callback %s",
                   type_utils.obj_name(child_cb))
            os._exit(1)
    else:
        LOG.debug("Forked child %s who will run callback %s",
                  fid, type_utils.obj_name(child_cb))


def is_true(val, addons=None):
    if isinstance(val, (bool)):
        return val is True
    check_set = TRUE_STRINGS
    if addons:
        check_set = list(check_set) + addons
    if six.text_type(val).lower().strip() in check_set:
        return True
    return False


def is_false(val, addons=None):
    if isinstance(val, (bool)):
        return val is False
    check_set = FALSE_STRINGS
    if addons:
        check_set = list(check_set) + addons
    if six.text_type(val).lower().strip() in check_set:
        return True
    return False


def translate_bool(val, addons=None):
    if not val:
        # This handles empty lists and false and
        # other things that python believes are false
        return False
    # If its already a boolean skip
    if isinstance(val, (bool)):
        return val
    return is_true(val, addons)


def rand_str(strlen=32, select_from=None):
    if not select_from:
        select_from = string.ascii_letters + string.digits
    return "".join([random.choice(select_from) for _x in range(0, strlen)])


def rand_dict_key(dictionary, postfix=None):
    if not postfix:
        postfix = ""
    while True:
        newkey = rand_str(strlen=8) + "_" + postfix
        if newkey not in dictionary:
            break
    return newkey


def read_conf(fname):
    try:
        return load_yaml(load_file(fname), default={})
    except IOError as e:
        if e.errno == ENOENT:
            return {}
        else:
            raise


# Merges X lists, and then keeps the
# unique ones, but orders by sort order
# instead of by the original order
def uniq_merge_sorted(*lists):
    return sorted(uniq_merge(*lists))


# Merges X lists and then iterates over those
# and only keeps the unique items (order preserving)
# and returns that merged and uniqued list as the
# final result.
#
# Note: if any entry is a string it will be
# split on commas and empty entries will be
# evicted and merged in accordingly.
def uniq_merge(*lists):
    combined_list = []
    for a_list in lists:
        if isinstance(a_list, six.string_types):
            a_list = a_list.strip().split(",")
            # Kickout the empty ones
            a_list = [a for a in a_list if len(a)]
        combined_list.extend(a_list)
    return uniq_list(combined_list)


def clean_filename(fn):
    for (k, v) in FN_REPLACEMENTS.items():
        fn = fn.replace(k, v)
    removals = []
    for k in fn:
        if k not in FN_ALLOWED:
            removals.append(k)
    for k in removals:
        fn = fn.replace(k, '')
    fn = fn.strip()
    return fn


def decomp_gzip(data, quiet=True, decode=True):
    try:
        buf = six.BytesIO(encode_text(data))
        with contextlib.closing(gzip.GzipFile(None, "rb", 1, buf)) as gh:
            # E1101 is https://github.com/PyCQA/pylint/issues/1444
            if decode:
                return decode_binary(gh.read())  # pylint: disable=E1101
            else:
                return gh.read()  # pylint: disable=E1101
    except Exception as e:
        if quiet:
            return data
        else:
            raise DecompressionError(six.text_type(e))


def extract_usergroup(ug_pair):
    if not ug_pair:
        return (None, None)
    ug_parted = ug_pair.split(':', 1)
    u = ug_parted[0].strip()
    if len(ug_parted) == 2:
        g = ug_parted[1].strip()
    else:
        g = None
    if not u or u == "-1" or u.lower() == "none":
        u = None
    if not g or g == "-1" or g.lower() == "none":
        g = None
    return (u, g)


def find_modules(root_dir):
    entries = dict()
    for fname in glob.glob(os.path.join(root_dir, "*.py")):
        if not os.path.isfile(fname):
            continue
        modname = os.path.basename(fname)[0:-3]
        modname = modname.strip()
        if modname and modname.find(".") == -1:
            entries[fname] = modname
    return entries


def multi_log(text, console=True, stderr=True,
              log=None, log_level=logging.DEBUG):
    if stderr:
        sys.stderr.write(text)
    if console:
        conpath = "/dev/console"
        if os.path.exists(conpath):
            with open(conpath, 'w') as wfh:
                wfh.write(text)
                wfh.flush()
        else:
            # A container may lack /dev/console (arguably a container bug).  If
            # it does not exist, then write output to stdout.  this will result
            # in duplicate stderr and stdout messages if stderr was True.
            #
            # even though upstart or systemd might have set up output to go to
            # /dev/console, the user may have configured elsewhere via
            # cloud-config 'output'.  If there is /dev/console, messages will
            # still get there.
            sys.stdout.write(text)
    if log:
        if text[-1] == "\n":
            log.log(log_level, text[:-1])
        else:
            log.log(log_level, text)


def is_ipv4(instr):
    """determine if input string is a ipv4 address. return boolean."""
    toks = instr.split('.')
    if len(toks) != 4:
        return False

    try:
        toks = [x for x in toks if 0 <= int(x) < 256]
    except Exception:
        return False

    return len(toks) == 4


def is_FreeBSD():
    return system_info()['variant'] == "freebsd"


def get_cfg_option_bool(yobj, key, default=False):
    if key not in yobj:
        return default
    return translate_bool(yobj[key])


def get_cfg_option_str(yobj, key, default=None):
    if key not in yobj:
        return default
    val = yobj[key]
    if not isinstance(val, six.string_types):
        val = str(val)
    return val


def get_cfg_option_int(yobj, key, default=0):
    return int(get_cfg_option_str(yobj, key, default=default))


def system_info():
    info = {
        'platform': platform.platform(),
        'system': platform.system(),
        'release': platform.release(),
        'python': platform.python_version(),
        'uname': platform.uname(),
        'dist': platform.dist(),  # pylint: disable=W1505
    }
    system = info['system'].lower()
    var = 'unknown'
    if system == "linux":
        linux_dist = info['dist'][0].lower()
        if linux_dist in ('centos', 'fedora', 'debian'):
            var = linux_dist
        elif linux_dist in ('ubuntu', 'linuxmint', 'mint'):
            var = 'ubuntu'
        elif linux_dist == 'redhat':
            var = 'rhel'
        elif linux_dist == 'suse':
            var = 'suse'
        else:
            var = 'linux'
    elif system in ('windows', 'darwin', "freebsd"):
        var = system

    info['variant'] = var

    return info


def get_cfg_option_list(yobj, key, default=None):
    """
    Gets the C{key} config option from C{yobj} as a list of strings. If the
    key is present as a single string it will be returned as a list with one
    string arg.

    @param yobj: The configuration object.
    @param key: The configuration key to get.
    @param default: The default to return if key is not found.
    @return: The configuration option as a list of strings or default if key
        is not found.
    """
    if key not in yobj:
        return default
    if yobj[key] is None:
        return []
    val = yobj[key]
    if isinstance(val, (list)):
        cval = [v for v in val]
        return cval
    if not isinstance(val, six.string_types):
        val = str(val)
    return [val]


# get a cfg entry by its path array
# for f['a']['b']: get_cfg_by_path(mycfg,('a','b'))
def get_cfg_by_path(yobj, keyp, default=None):
    cur = yobj
    for tok in keyp:
        if tok not in cur:
            return default
        cur = cur[tok]
    return cur


def fixup_output(cfg, mode):
    (outfmt, errfmt) = get_output_cfg(cfg, mode)
    redirect_output(outfmt, errfmt)
    return (outfmt, errfmt)


# redirect_output(outfmt, errfmt, orig_out, orig_err)
#  replace orig_out and orig_err with filehandles specified in outfmt or errfmt
#  fmt can be:
#   > FILEPATH
#   >> FILEPATH
#   | program [ arg1 [ arg2 [ ... ] ] ]
#
#   with a '|', arguments are passed to shell, so one level of
#   shell escape is required.
#
#   if _CLOUD_INIT_SAVE_STDOUT is set in environment to a non empty and true
#   value then output input will not be closed (useful for debugging).
#
def redirect_output(outfmt, errfmt, o_out=None, o_err=None):

    if is_true(os.environ.get("_CLOUD_INIT_SAVE_STDOUT")):
        LOG.debug("Not redirecting output due to _CLOUD_INIT_SAVE_STDOUT")
        return

    if not o_out:
        o_out = sys.stdout
    if not o_err:
        o_err = sys.stderr

    if outfmt:
        LOG.debug("Redirecting %s to %s", o_out, outfmt)
        (mode, arg) = outfmt.split(" ", 1)
        if mode == ">" or mode == ">>":
            owith = "ab"
            if mode == ">":
                owith = "wb"
            new_fp = open(arg, owith)
        elif mode == "|":
            proc = subprocess.Popen(arg, shell=True, stdin=subprocess.PIPE)
            new_fp = proc.stdin
        else:
            raise TypeError("Invalid type for output format: %s" % outfmt)

        if o_out:
            os.dup2(new_fp.fileno(), o_out.fileno())

        if errfmt == outfmt:
            LOG.debug("Redirecting %s to %s", o_err, outfmt)
            os.dup2(new_fp.fileno(), o_err.fileno())
            return

    if errfmt:
        LOG.debug("Redirecting %s to %s", o_err, errfmt)
        (mode, arg) = errfmt.split(" ", 1)
        if mode == ">" or mode == ">>":
            owith = "ab"
            if mode == ">":
                owith = "wb"
            new_fp = open(arg, owith)
        elif mode == "|":
            proc = subprocess.Popen(arg, shell=True, stdin=subprocess.PIPE)
            new_fp = proc.stdin
        else:
            raise TypeError("Invalid type for error format: %s" % errfmt)

        if o_err:
            os.dup2(new_fp.fileno(), o_err.fileno())


def make_url(scheme, host, port=None,
             path='', params='', query='', fragment=''):

    pieces = [scheme or '']

    netloc = ''
    if host:
        netloc = str(host)

    if port is not None:
        netloc += ":" + "%s" % (port)

    pieces.append(netloc or '')
    pieces.append(path or '')
    pieces.append(params or '')
    pieces.append(query or '')
    pieces.append(fragment or '')

    return urlparse.urlunparse(pieces)


def mergemanydict(srcs, reverse=False):
    if reverse:
        srcs = reversed(srcs)
    merged_cfg = {}
    for cfg in srcs:
        if cfg:
            # Figure out which mergers to apply...
            mergers_to_apply = mergers.dict_extract_mergers(cfg)
            if not mergers_to_apply:
                mergers_to_apply = mergers.default_mergers()
            merger = mergers.construct(mergers_to_apply)
            merged_cfg = merger.merge(merged_cfg, cfg)
    return merged_cfg


@contextlib.contextmanager
def chdir(ndir):
    curr = os.getcwd()
    try:
        os.chdir(ndir)
        yield ndir
    finally:
        os.chdir(curr)


@contextlib.contextmanager
def umask(n_msk):
    old = os.umask(n_msk)
    try:
        yield old
    finally:
        os.umask(old)


def center(text, fill, max_len):
    return '{0:{fill}{align}{size}}'.format(text, fill=fill,
                                            align="^", size=max_len)


def del_dir(path):
    LOG.debug("Recursively deleting %s", path)
    shutil.rmtree(path)


def runparts(dirp, skip_no_exist=True, exe_prefix=None):
    if skip_no_exist and not os.path.isdir(dirp):
        return

    failed = []
    attempted = []

    if exe_prefix is None:
        prefix = []
    elif isinstance(exe_prefix, str):
        prefix = [str(exe_prefix)]
    elif isinstance(exe_prefix, list):
        prefix = exe_prefix
    else:
        raise TypeError("exe_prefix must be None, str, or list")

    for exe_name in sorted(os.listdir(dirp)):
        exe_path = os.path.join(dirp, exe_name)
        if os.path.isfile(exe_path) and os.access(exe_path, os.X_OK):
            attempted.append(exe_path)
            try:
                subp(prefix + [exe_path], capture=False)
            except ProcessExecutionError as e:
                logexc(LOG, "Failed running %s [%s]", exe_path, e.exit_code)
                failed.append(e)

    if failed and attempted:
        raise RuntimeError('Runparts: %s failures in %s attempted commands'
                           % (len(failed), len(attempted)))


# read_optional_seed
# returns boolean indicating success or failure (presense of files)
# if files are present, populates 'fill' dictionary with 'user-data' and
# 'meta-data' entries
def read_optional_seed(fill, base="", ext="", timeout=5):
    try:
        (md, ud) = read_seeded(base, ext, timeout)
        fill['user-data'] = ud
        fill['meta-data'] = md
        return True
    except url_helper.UrlError as e:
        if e.code == url_helper.NOT_FOUND:
            return False
        raise


def fetch_ssl_details(paths=None):
    ssl_details = {}
    # Lookup in these locations for ssl key/cert files
    ssl_cert_paths = [
        '/var/lib/cloud/data/ssl',
        '/var/lib/cloud/instance/data/ssl',
    ]
    if paths:
        ssl_cert_paths.extend([
            os.path.join(paths.get_ipath_cur('data'), 'ssl'),
            os.path.join(paths.get_cpath('data'), 'ssl'),
        ])
    ssl_cert_paths = uniq_merge(ssl_cert_paths)
    ssl_cert_paths = [d for d in ssl_cert_paths if d and os.path.isdir(d)]
    cert_file = None
    for d in ssl_cert_paths:
        if os.path.isfile(os.path.join(d, 'cert.pem')):
            cert_file = os.path.join(d, 'cert.pem')
            break
    key_file = None
    for d in ssl_cert_paths:
        if os.path.isfile(os.path.join(d, 'key.pem')):
            key_file = os.path.join(d, 'key.pem')
            break
    if cert_file and key_file:
        ssl_details['cert_file'] = cert_file
        ssl_details['key_file'] = key_file
    elif cert_file:
        ssl_details['cert_file'] = cert_file
    return ssl_details


def read_file_or_url(url, timeout=5, retries=10,
                     headers=None, data=None, sec_between=1, ssl_details=None,
                     headers_cb=None, exception_cb=None):
    url = url.lstrip()
    if url.startswith("/"):
        url = "file://%s" % url
    if url.lower().startswith("file://"):
        if data:
            LOG.warning("Unable to post data to file resource %s", url)
        file_path = url[len("file://"):]
        try:
            contents = load_file(file_path, decode=False)
        except IOError as e:
            code = e.errno
            if e.errno == ENOENT:
                code = url_helper.NOT_FOUND
            raise url_helper.UrlError(cause=e, code=code, headers=None,
                                      url=url)
        return url_helper.FileResponse(file_path, contents=contents)
    else:
        return url_helper.readurl(url,
                                  timeout=timeout,
                                  retries=retries,
                                  headers=headers,
                                  headers_cb=headers_cb,
                                  data=data,
                                  sec_between=sec_between,
                                  ssl_details=ssl_details,
                                  exception_cb=exception_cb)


def load_yaml(blob, default=None, allowed=(dict,)):
    loaded = default
    blob = decode_binary(blob)
    try:
        LOG.debug("Attempting to load yaml from string "
                  "of length %s with allowed root types %s",
                  len(blob), allowed)
        converted = safeyaml.load(blob)
        if converted is None:
            LOG.debug("loaded blob returned None, returning default.")
            converted = default
        elif not isinstance(converted, allowed):
            # Yes this will just be caught, but thats ok for now...
            raise TypeError(("Yaml load allows %s root types,"
                             " but got %s instead") %
                            (allowed, type_utils.obj_name(converted)))
        loaded = converted
    except (yaml.YAMLError, TypeError, ValueError):
        logexc(LOG, "Failed loading yaml blob")
    return loaded


def read_seeded(base="", ext="", timeout=5, retries=10, file_retries=0):
    if base.startswith("/"):
        base = "file://%s" % base

    # default retries for file is 0. for network is 10
    if base.startswith("file://"):
        retries = file_retries

    if base.find("%s") >= 0:
        ud_url = base % ("user-data" + ext)
        md_url = base % ("meta-data" + ext)
    else:
        ud_url = "%s%s%s" % (base, "user-data", ext)
        md_url = "%s%s%s" % (base, "meta-data", ext)

    md_resp = read_file_or_url(md_url, timeout, retries, file_retries)
    md = None
    if md_resp.ok():
        md = load_yaml(decode_binary(md_resp.contents), default={})

    ud_resp = read_file_or_url(ud_url, timeout, retries, file_retries)
    ud = None
    if ud_resp.ok():
        ud = ud_resp.contents

    return (md, ud)


def read_conf_d(confd):
    # Get reverse sorted list (later trumps newer)
    confs = sorted(os.listdir(confd), reverse=True)

    # Remove anything not ending in '.cfg'
    confs = [f for f in confs if f.endswith(".cfg")]

    # Remove anything not a file
    confs = [f for f in confs
             if os.path.isfile(os.path.join(confd, f))]

    # Load them all so that they can be merged
    cfgs = []
    for fn in confs:
        cfgs.append(read_conf(os.path.join(confd, fn)))

    return mergemanydict(cfgs)


def read_conf_with_confd(cfgfile):
    cfg = read_conf(cfgfile)

    confd = False
    if "conf_d" in cfg:
        confd = cfg['conf_d']
        if confd:
            if not isinstance(confd, six.string_types):
                raise TypeError(("Config file %s contains 'conf_d' "
                                 "with non-string type %s") %
                                (cfgfile, type_utils.obj_name(confd)))
            else:
                confd = str(confd).strip()
    elif os.path.isdir("%s.d" % cfgfile):
        confd = "%s.d" % cfgfile

    if not confd or not os.path.isdir(confd):
        return cfg

    # Conf.d settings override input configuration
    confd_cfg = read_conf_d(confd)
    return mergemanydict([confd_cfg, cfg])


def read_conf_from_cmdline(cmdline=None):
    # return a dictionary or config on the cmdline or None
    return load_yaml(read_cc_from_cmdline(cmdline=cmdline))


def read_cc_from_cmdline(cmdline=None):
    # this should support reading cloud-config information from
    # the kernel command line.  It is intended to support content of the
    # format:
    #  cc: <yaml content here> [end_cc]
    # this would include:
    # cc: ssh_import_id: [smoser, kirkland]\\n
    # cc: ssh_import_id: [smoser, bob]\\nruncmd: [ [ ls, -l ], echo hi ] end_cc
    # cc:ssh_import_id: [smoser] end_cc cc:runcmd: [ [ ls, -l ] ] end_cc
    if cmdline is None:
        cmdline = get_cmdline()

    tag_begin = "cc:"
    tag_end = "end_cc"
    begin_l = len(tag_begin)
    end_l = len(tag_end)
    clen = len(cmdline)
    tokens = []
    begin = cmdline.find(tag_begin)
    while begin >= 0:
        end = cmdline.find(tag_end, begin + begin_l)
        if end < 0:
            end = clen
        tokens.append(cmdline[begin + begin_l:end].lstrip().replace("\\n",
                                                                    "\n"))

        begin = cmdline.find(tag_begin, end + end_l)

    return '\n'.join(tokens)


def dos2unix(contents):
    # find first end of line
    pos = contents.find('\n')
    if pos <= 0 or contents[pos - 1] != '\r':
        return contents
    return contents.replace('\r\n', '\n')


def get_hostname_fqdn(cfg, cloud, metadata_only=False):
    """Get hostname and fqdn from config if present and fallback to cloud.

    @param cfg: Dictionary of merged user-data configuration (from init.cfg).
    @param cloud: Cloud instance from init.cloudify().
    @param metadata_only: Boolean, set True to only query cloud meta-data,
        returning None if not present in meta-data.
    @return: a Tuple of strings <hostname>, <fqdn>. Values can be none when
        metadata_only is True and no cfg or metadata provides hostname info.
    """
    if "fqdn" in cfg:
        # user specified a fqdn.  Default hostname then is based off that
        fqdn = cfg['fqdn']
        hostname = get_cfg_option_str(cfg, "hostname", fqdn.split('.')[0])
    else:
        if "hostname" in cfg and cfg['hostname'].find('.') > 0:
            # user specified hostname, and it had '.' in it
            # be nice to them.  set fqdn and hostname from that
            fqdn = cfg['hostname']
            hostname = cfg['hostname'][:fqdn.find('.')]
        else:
            # no fqdn set, get fqdn from cloud.
            # get hostname from cfg if available otherwise cloud
            fqdn = cloud.get_hostname(fqdn=True, metadata_only=metadata_only)
            if "hostname" in cfg:
                hostname = cfg['hostname']
            else:
                hostname = cloud.get_hostname(metadata_only=metadata_only)
    return (hostname, fqdn)


def get_fqdn_from_hosts(hostname, filename="/etc/hosts"):
    """
    For each host a single line should be present with
      the following information:

        IP_address canonical_hostname [aliases...]

      Fields of the entry are separated by any number of  blanks  and/or  tab
      characters.  Text  from a "#" character until the end of the line is a
      comment, and is ignored. Host  names  may  contain  only  alphanumeric
      characters, minus signs ("-"), and periods (".").  They must begin with
      an  alphabetic  character  and  end  with  an  alphanumeric  character.
      Optional aliases provide for name changes, alternate spellings, shorter
      hostnames, or generic hostnames (for example, localhost).
    """
    fqdn = None
    try:
        for line in load_file(filename).splitlines():
            hashpos = line.find("#")
            if hashpos >= 0:
                line = line[0:hashpos]
            line = line.strip()
            if not line:
                continue

            # If there there is less than 3 entries
            # (IP_address, canonical_hostname, alias)
            # then ignore this line
            toks = line.split()
            if len(toks) < 3:
                continue

            if hostname in toks[2:]:
                fqdn = toks[1]
                break
    except IOError:
        pass
    return fqdn


def is_resolvable(name):
    """determine if a url is resolvable, return a boolean
    This also attempts to be resilent against dns redirection.

    Note, that normal nsswitch resolution is used here.  So in order
    to avoid any utilization of 'search' entries in /etc/resolv.conf
    we have to append '.'.

    The top level 'invalid' domain is invalid per RFC.  And example.com
    should also not exist.  The '__cloud_init_expected_not_found__' entry will
    be resolved inside the search list.
    """
    global _DNS_REDIRECT_IP
    if _DNS_REDIRECT_IP is None:
        badips = set()
        badnames = ("does-not-exist.example.com.", "example.invalid.",
                    "__cloud_init_expected_not_found__")
        badresults = {}
        for iname in badnames:
            try:
                result = socket.getaddrinfo(iname, None, 0, 0,
                                            socket.SOCK_STREAM,
                                            socket.AI_CANONNAME)
                badresults[iname] = []
                for (_fam, _stype, _proto, cname, sockaddr) in result:
                    badresults[iname].append("%s: %s" % (cname, sockaddr[0]))
                    badips.add(sockaddr[0])
            except (socket.gaierror, socket.error):
                pass
        _DNS_REDIRECT_IP = badips
        if badresults:
            LOG.debug("detected dns redirection: %s", badresults)

    try:
        result = socket.getaddrinfo(name, None)
        # check first result's sockaddr field
        addr = result[0][4][0]
        if addr in _DNS_REDIRECT_IP:
            return False
        return True
    except (socket.gaierror, socket.error):
        return False


def get_hostname():
    hostname = socket.gethostname()
    return hostname


def gethostbyaddr(ip):
    try:
        return socket.gethostbyaddr(ip)[0]
    except socket.herror:
        return None


def is_resolvable_url(url):
    """determine if this url is resolvable (existing or ip)."""
    return is_resolvable(urlparse.urlparse(url).hostname)


def search_for_mirror(candidates):
    """
    Search through a list of mirror urls for one that works
    This needs to return quickly.
    """
    for cand in candidates:
        try:
            if is_resolvable_url(cand):
                return cand
        except Exception:
            pass
    return None


def close_stdin():
    """
    reopen stdin as /dev/null so even subprocesses or other os level things get
    /dev/null as input.

    if _CLOUD_INIT_SAVE_STDIN is set in environment to a non empty and true
    value then input will not be closed (useful for debugging).
    """
    if is_true(os.environ.get("_CLOUD_INIT_SAVE_STDIN")):
        return
    with open(os.devnull) as fp:
        os.dup2(fp.fileno(), sys.stdin.fileno())


def find_devs_with(criteria=None, oformat='device',
                   tag=None, no_cache=False, path=None):
    """
    find devices matching given criteria (via blkid)
    criteria can be *one* of:
      TYPE=<filesystem>
      LABEL=<label>
      UUID=<uuid>
    """
    blk_id_cmd = ['blkid']
    options = []
    if criteria:
        # Search for block devices with tokens named NAME that
        # have the value 'value' and display any devices which are found.
        # Common values for NAME include  TYPE, LABEL, and UUID.
        # If there are no devices specified on the command line,
        # all block devices will be searched; otherwise,
        # only search the devices specified by the user.
        options.append("-t%s" % (criteria))
    if tag:
        # For each (specified) device, show only the tags that match tag.
        options.append("-s%s" % (tag))
    if no_cache:
        # If you want to start with a clean cache
        # (i.e. don't report devices previously scanned
        # but not necessarily available at this time), specify /dev/null.
        options.extend(["-c", "/dev/null"])
    if oformat:
        # Display blkid's output using the specified format.
        # The format parameter may be:
        # full, value, list, device, udev, export
        options.append('-o%s' % (oformat))
    if path:
        options.append(path)
    cmd = blk_id_cmd + options
    # See man blkid for why 2 is added
    try:
        (out, _err) = subp(cmd, rcs=[0, 2])
    except ProcessExecutionError as e:
        if e.errno == ENOENT:
            # blkid not found...
            out = ""
        else:
            raise
    entries = []
    for line in out.splitlines():
        line = line.strip()
        if line:
            entries.append(line)
    return entries


def blkid(devs=None, disable_cache=False):
    """Get all device tags details from blkid.

    @param devs: Optional list of device paths you wish to query.
    @param disable_cache: Bool, set True to start with clean cache.

    @return: Dict of key value pairs of info for the device.
    """
    if devs is None:
        devs = []
    else:
        devs = list(devs)

    cmd = ['blkid', '-o', 'full']
    if disable_cache:
        cmd.extend(['-c', '/dev/null'])
    cmd.extend(devs)

    # we have to decode with 'replace' as shelx.split (called by
    # load_shell_content) can't take bytes.  So this is potentially
    # lossy of non-utf-8 chars in blkid output.
    out, _ = subp(cmd, capture=True, decode="replace")
    ret = {}
    for line in out.splitlines():
        dev, _, data = line.partition(":")
        ret[dev] = load_shell_content(data)
        ret[dev]["DEVNAME"] = dev

    return ret


def peek_file(fname, max_bytes):
    LOG.debug("Peeking at %s (max_bytes=%s)", fname, max_bytes)
    with open(fname, 'rb') as ifh:
        return ifh.read(max_bytes)


def uniq_list(in_list):
    out_list = []
    for i in in_list:
        if i in out_list:
            continue
        else:
            out_list.append(i)
    return out_list


def load_file(fname, read_cb=None, quiet=False, decode=True):
    LOG.debug("Reading from %s (quiet=%s)", fname, quiet)
    ofh = six.BytesIO()
    try:
        with open(fname, 'rb') as ifh:
            pipe_in_out(ifh, ofh, chunk_cb=read_cb)
    except IOError as e:
        if not quiet:
            raise
        if e.errno != ENOENT:
            raise
    contents = ofh.getvalue()
    LOG.debug("Read %s bytes from %s", len(contents), fname)
    if decode:
        return decode_binary(contents)
    else:
        return contents


def get_cmdline():
    if 'DEBUG_PROC_CMDLINE' in os.environ:
        return os.environ["DEBUG_PROC_CMDLINE"]

    global PROC_CMDLINE
    if PROC_CMDLINE is not None:
        return PROC_CMDLINE

    if is_container():
        try:
            contents = load_file("/proc/1/cmdline")
            # replace nulls with space and drop trailing null
            cmdline = contents.replace("\x00", " ")[:-1]
        except Exception as e:
            LOG.warning("failed reading /proc/1/cmdline: %s", e)
            cmdline = ""
    else:
        try:
            cmdline = load_file("/proc/cmdline").strip()
        except Exception:
            cmdline = ""

    PROC_CMDLINE = cmdline
    return cmdline


def pipe_in_out(in_fh, out_fh, chunk_size=1024, chunk_cb=None):
    bytes_piped = 0
    while True:
        data = in_fh.read(chunk_size)
        if len(data) == 0:
            break
        else:
            out_fh.write(data)
            bytes_piped += len(data)
            if chunk_cb:
                chunk_cb(bytes_piped)
    out_fh.flush()
    return bytes_piped


def chownbyid(fname, uid=None, gid=None):
    if uid in [None, -1] and gid in [None, -1]:
        # Nothing to do
        return
    LOG.debug("Changing the ownership of %s to %s:%s", fname, uid, gid)
    os.chown(fname, uid, gid)


def chownbyname(fname, user=None, group=None):
    uid = -1
    gid = -1
    try:
        if user:
            uid = pwd.getpwnam(user).pw_uid
        if group:
            gid = grp.getgrnam(group).gr_gid
    except KeyError as e:
        raise OSError("Unknown user or group: %s" % (e))
    chownbyid(fname, uid, gid)


# Always returns well formated values
# cfg is expected to have an entry 'output' in it, which is a dictionary
# that includes entries for 'init', 'config', 'final' or 'all'
#   init: /var/log/cloud.out
#   config: [ ">> /var/log/cloud-config.out", /var/log/cloud-config.err ]
#   final:
#     output: "| logger -p"
#     error: "> /dev/null"
# this returns the specific 'mode' entry, cleanly formatted, with value
def get_output_cfg(cfg, mode):
    ret = [None, None]
    if not cfg or 'output' not in cfg:
        return ret

    outcfg = cfg['output']
    if mode in outcfg:
        modecfg = outcfg[mode]
    else:
        if 'all' not in outcfg:
            return ret
        # if there is a 'all' item in the output list
        # then it applies to all users of this (init, config, final)
        modecfg = outcfg['all']

    # if value is a string, it specifies stdout and stderr
    if isinstance(modecfg, str):
        ret = [modecfg, modecfg]

    # if its a list, then we expect (stdout, stderr)
    if isinstance(modecfg, list):
        if len(modecfg) > 0:
            ret[0] = modecfg[0]
        if len(modecfg) > 1:
            ret[1] = modecfg[1]

    # if it is a dictionary, expect 'out' and 'error'
    # items, which indicate out and error
    if isinstance(modecfg, dict):
        if 'output' in modecfg:
            ret[0] = modecfg['output']
        if 'error' in modecfg:
            ret[1] = modecfg['error']

    # if err's entry == "&1", then make it same as stdout
    # as in shell syntax of "echo foo >/dev/null 2>&1"
    if ret[1] == "&1":
        ret[1] = ret[0]

    swlist = [">>", ">", "|"]
    for i in range(len(ret)):
        if not ret[i]:
            continue
        val = ret[i].lstrip()
        found = False
        for s in swlist:
            if val.startswith(s):
                val = "%s %s" % (s, val[len(s):].strip())
                found = True
                break
        if not found:
            # default behavior is append
            val = "%s %s" % (">>", val.strip())
        ret[i] = val

    return ret


def get_config_logfiles(cfg):
    """Return a list of log file paths from the configuration dictionary.

    @param cfg: The cloud-init merged configuration dictionary.
    """
    logs = []
    if not cfg or not isinstance(cfg, dict):
        return logs
    default_log = cfg.get('def_log_file')
    if default_log:
        logs.append(default_log)
    for fmt in get_output_cfg(cfg, None):
        if not fmt:
            continue
        match = re.match(r'(?P<type>\||>+)\s*(?P<target>.*)', fmt)
        if not match:
            continue
        target = match.group('target')
        parts = target.split()
        if len(parts) == 1:
            logs.append(target)
        elif ['tee', '-a'] == parts[:2]:
            logs.append(parts[2])
    return list(set(logs))


def logexc(log, msg, *args):
    # Setting this here allows this to change
    # levels easily (not always error level)
    # or even desirable to have that much junk
    # coming out to a non-debug stream
    if msg:
        log.warning(msg, *args)
    # Debug gets the full trace.  However, nose has a bug whereby its
    # logcapture plugin doesn't properly handle the case where there is no
    # actual exception.  To avoid tracebacks during the test suite then, we'll
    # do the actual exc_info extraction here, and if there is no exception in
    # flight, we'll just pass in None.
    exc_info = sys.exc_info()
    if exc_info == (None, None, None):
        exc_info = None
    log.debug(msg, exc_info=exc_info, *args)


def hash_blob(blob, routine, mlen=None):
    hasher = hashlib.new(routine)
    hasher.update(encode_text(blob))
    digest = hasher.hexdigest()
    # Don't get to long now
    if mlen is not None:
        return digest[0:mlen]
    else:
        return digest


def is_user(name):
    try:
        if pwd.getpwnam(name):
            return True
    except KeyError:
        return False


def is_group(name):
    try:
        if grp.getgrnam(name):
            return True
    except KeyError:
        return False


def rename(src, dest):
    LOG.debug("Renaming %s to %s", src, dest)
    # TODO(harlowja) use a se guard here??
    os.rename(src, dest)


def ensure_dirs(dirlist, mode=0o755):
    for d in dirlist:
        ensure_dir(d, mode)


def load_json(text, root_types=(dict,)):
    decoded = json.loads(decode_binary(text))
    if not isinstance(decoded, tuple(root_types)):
        expected_types = ", ".join([str(t) for t in root_types])
        raise TypeError("(%s) root types expected, got %s instead"
                        % (expected_types, type(decoded)))
    return decoded


def json_serialize_default(_obj):
    """Handler for types which aren't json serializable."""
    try:
        return 'ci-b64:{0}'.format(b64e(_obj))
    except AttributeError:
        return 'Warning: redacted unserializable type {0}'.format(type(_obj))


def json_dumps(data):
    """Return data in nicely formatted json."""
    return json.dumps(data, indent=1, sort_keys=True,
                      separators=(',', ': '), default=json_serialize_default)


def yaml_dumps(obj, explicit_start=True, explicit_end=True):
    """Return data in nicely formatted yaml."""
    return yaml.safe_dump(obj,
                          line_break="\n",
                          indent=4,
                          explicit_start=explicit_start,
                          explicit_end=explicit_end,
                          default_flow_style=False)


def ensure_dir(path, mode=None):
    if not os.path.isdir(path):
        # Make the dir and adjust the mode
        with SeLinuxGuard(os.path.dirname(path), recursive=True):
            os.makedirs(path)
        chmod(path, mode)
    else:
        # Just adjust the mode
        chmod(path, mode)


@contextlib.contextmanager
def unmounter(umount):
    try:
        yield umount
    finally:
        if umount:
            umount_cmd = ["umount", umount]
            subp(umount_cmd)


def mounts():
    mounted = {}
    try:
        # Go through mounts to see what is already mounted
        if os.path.exists("/proc/mounts"):
            mount_locs = load_file("/proc/mounts").splitlines()
            method = 'proc'
        else:
            (mountoutput, _err) = subp("mount")
            mount_locs = mountoutput.splitlines()
            method = 'mount'
        mountre = r'^(/dev/[\S]+) on (/.*) \((.+), .+, (.+)\)$'
        for mpline in mount_locs:
            # Linux: /dev/sda1 on /boot type ext4 (rw,relatime,data=ordered)
            # FreeBSD: /dev/vtbd0p2 on / (ufs, local, journaled soft-updates)
            try:
                if method == 'proc':
                    (dev, mp, fstype, opts, _freq, _passno) = mpline.split()
                else:
                    m = re.search(mountre, mpline)
                    dev = m.group(1)
                    mp = m.group(2)
                    fstype = m.group(3)
                    opts = m.group(4)
            except Exception:
                continue
            # If the name of the mount point contains spaces these
            # can be escaped as '\040', so undo that..
            mp = mp.replace("\\040", " ")
            mounted[dev] = {
                'fstype': fstype,
                'mountpoint': mp,
                'opts': opts,
            }
        LOG.debug("Fetched %s mounts from %s", mounted, method)
    except (IOError, OSError):
        logexc(LOG, "Failed fetching mount points")
    return mounted


def mount_cb(device, callback, data=None, rw=False, mtype=None, sync=True):
    """
    Mount the device, call method 'callback' passing the directory
    in which it was mounted, then unmount.  Return whatever 'callback'
    returned.  If data != None, also pass data to callback.

    mtype is a filesystem type.  it may be a list, string (a single fsname)
    or a list of fsnames.
    """

    if isinstance(mtype, str):
        mtypes = [mtype]
    elif isinstance(mtype, (list, tuple)):
        mtypes = list(mtype)
    elif mtype is None:
        mtypes = None
    else:
        raise TypeError(
            'Unsupported type provided for mtype parameter: {_type}'.format(
                _type=type(mtype)))

    # clean up 'mtype' input a bit based on platform.
    platsys = platform.system().lower()
    if platsys == "linux":
        if mtypes is None:
            mtypes = ["auto"]
    elif platsys.endswith("bsd"):
        if mtypes is None:
            mtypes = ['ufs', 'cd9660', 'vfat']
        for index, mtype in enumerate(mtypes):
            if mtype == "iso9660":
                mtypes[index] = "cd9660"
    else:
        # we cannot do a smart "auto", so just call 'mount' once with no -t
        mtypes = ['']

    mounted = mounts()
    with temp_utils.tempdir() as tmpd:
        umount = False
        if os.path.realpath(device) in mounted:
            mountpoint = mounted[os.path.realpath(device)]['mountpoint']
        else:
            failure_reason = None
            for mtype in mtypes:
                mountpoint = None
                try:
                    mountcmd = ['mount']
                    mountopts = []
                    if rw:
                        mountopts.append('rw')
                    else:
                        mountopts.append('ro')
                    if sync:
                        # This seems like the safe approach to do
                        # (ie where this is on by default)
                        mountopts.append("sync")
                    if mountopts:
                        mountcmd.extend(["-o", ",".join(mountopts)])
                    if mtype:
                        mountcmd.extend(['-t', mtype])
                    mountcmd.append(device)
                    mountcmd.append(tmpd)
                    subp(mountcmd)
                    umount = tmpd  # This forces it to be unmounted (when set)
                    mountpoint = tmpd
                    break
                except (IOError, OSError) as exc:
                    LOG.debug("Failed mount of '%s' as '%s': %s",
                              device, mtype, exc)
                    failure_reason = exc
            if not mountpoint:
                raise MountFailedError("Failed mounting %s to %s due to: %s" %
                                       (device, tmpd, failure_reason))

        # Be nice and ensure it ends with a slash
        if not mountpoint.endswith("/"):
            mountpoint += "/"
        with unmounter(umount):
            if data is None:
                ret = callback(mountpoint)
            else:
                ret = callback(mountpoint, data)
            return ret


def get_builtin_cfg():
    # Deep copy so that others can't modify
    return obj_copy.deepcopy(CFG_BUILTIN)


def is_link(path):
    LOG.debug("Testing if a link exists for %s", path)
    return os.path.islink(path)


def sym_link(source, link, force=False):
    LOG.debug("Creating symbolic link from %r => %r", link, source)
    if force and os.path.exists(link):
        del_file(link)
    os.symlink(source, link)


def del_file(path):
    LOG.debug("Attempting to remove %s", path)
    try:
        os.unlink(path)
    except OSError as e:
        if e.errno != ENOENT:
            raise e


def copy(src, dest):
    LOG.debug("Copying %s to %s", src, dest)
    shutil.copy(src, dest)


def time_rfc2822():
    try:
        ts = time.strftime("%a, %d %b %Y %H:%M:%S %z", time.gmtime())
    except Exception:
        ts = "??"
    return ts


def uptime():
    uptime_str = '??'
    method = 'unknown'
    try:
        if os.path.exists("/proc/uptime"):
            method = '/proc/uptime'
            contents = load_file("/proc/uptime")
            if contents:
                uptime_str = contents.split()[0]
        else:
            method = 'ctypes'
            libc = ctypes.CDLL('/lib/libc.so.7')
            size = ctypes.c_size_t()
            buf = ctypes.c_int()
            size.value = ctypes.sizeof(buf)
            libc.sysctlbyname("kern.boottime", ctypes.byref(buf),
                              ctypes.byref(size), None, 0)
            now = time.time()
            bootup = buf.value
            uptime_str = now - bootup

    except Exception:
        logexc(LOG, "Unable to read uptime using method: %s" % method)
    return uptime_str


def append_file(path, content):
    write_file(path, content, omode="ab", mode=None)


def ensure_file(path, mode=0o644):
    write_file(path, content='', omode="ab", mode=mode)


def safe_int(possible_int):
    try:
        return int(possible_int)
    except (ValueError, TypeError):
        return None


def chmod(path, mode):
    real_mode = safe_int(mode)
    if path and real_mode:
        with SeLinuxGuard(path):
            os.chmod(path, real_mode)


def write_file(filename, content, mode=0o644, omode="wb", copy_mode=False):
    """
    Writes a file with the given content and sets the file mode as specified.
    Restores the SELinux context if possible.

    @param filename: The full path of the file to write.
    @param content: The content to write to the file.
    @param mode: The filesystem mode to set on the file.
    @param omode: The open mode used when opening the file (w, wb, a, etc.)
    """

    if copy_mode:
        try:
            file_stat = os.stat(filename)
            mode = stat.S_IMODE(file_stat.st_mode)
        except OSError:
            pass

    ensure_dir(os.path.dirname(filename))
    if 'b' in omode.lower():
        content = encode_text(content)
        write_type = 'bytes'
    else:
        content = decode_binary(content)
        write_type = 'characters'
    try:
        mode_r = "%o" % mode
    except TypeError:
        mode_r = "%r" % mode
    LOG.debug("Writing to %s - %s: [%s] %s %s",
              filename, omode, mode_r, len(content), write_type)
    with SeLinuxGuard(path=filename):
        with open(filename, omode) as fh:
            fh.write(content)
            fh.flush()
    chmod(filename, mode)


def delete_dir_contents(dirname):
    """
    Deletes all contents of a directory without deleting the directory itself.

    @param dirname: The directory whose contents should be deleted.
    """
    for node in os.listdir(dirname):
        node_fullpath = os.path.join(dirname, node)
        if os.path.isdir(node_fullpath):
            del_dir(node_fullpath)
        else:
            del_file(node_fullpath)


def subp_blob_in_tempfile(blob, *args, **kwargs):
    """Write blob to a tempfile, and call subp with args, kwargs. Then cleanup.

    'basename' as a kwarg allows providing the basename for the file.
    The 'args' argument to subp will be updated with the full path to the
    filename as the first argument.
    """
    basename = kwargs.pop('basename', "subp_blob")

    if len(args) == 0 and 'args' not in kwargs:
        args = [tuple()]

    # Use tmpdir over tmpfile to avoid 'text file busy' on execute
    with temp_utils.tempdir(needs_exe=True) as tmpd:
        tmpf = os.path.join(tmpd, basename)
        if 'args' in kwargs:
            kwargs['args'] = [tmpf] + list(kwargs['args'])
        else:
            args = list(args)
            args[0] = [tmpf] + args[0]

        write_file(tmpf, blob, mode=0o700)
        return subp(*args, **kwargs)


def subp(args, data=None, rcs=None, env=None, capture=True, shell=False,
         logstring=False, decode="replace", target=None, update_env=None,
         status_cb=None):

    # not supported in cloud-init (yet), for now kept in the call signature
    # to ease maintaining code shared between cloud-init and curtin
    if target is not None:
        raise ValueError("target arg not supported by cloud-init")

    if rcs is None:
        rcs = [0]

    devnull_fp = None

    if update_env:
        if env is None:
            env = os.environ
        env = env.copy()
        env.update(update_env)

    if target_path(target) != "/":
        args = ['chroot', target] + list(args)

    if status_cb:
        command = ' '.join(args) if isinstance(args, list) else args
        status_cb('Begin run command: {command}\n'.format(command=command))
    if not logstring:
        LOG.debug(("Running command %s with allowed return codes %s"
                   " (shell=%s, capture=%s)"), args, rcs, shell, capture)
    else:
        LOG.debug(("Running hidden command to protect sensitive "
                   "input/output logstring: %s"), logstring)

    stdin = None
    stdout = None
    stderr = None
    if capture:
        stdout = subprocess.PIPE
        stderr = subprocess.PIPE
    if data is None:
        # using devnull assures any reads get null, rather
        # than possibly waiting on input.
        devnull_fp = open(os.devnull)
        stdin = devnull_fp
    else:
        stdin = subprocess.PIPE
        if not isinstance(data, bytes):
            data = data.encode()

    # Popen converts entries in the arguments array from non-bytes to bytes.
    # When locale is unset it may use ascii for that encoding which can
    # cause UnicodeDecodeErrors. (LP: #1751051)
    if isinstance(args, six.binary_type):
        bytes_args = args
    elif isinstance(args, six.string_types):
        bytes_args = args.encode("utf-8")
    else:
        bytes_args = [
            x if isinstance(x, six.binary_type) else x.encode("utf-8")
            for x in args]
    try:
        sp = subprocess.Popen(bytes_args, stdout=stdout,
                              stderr=stderr, stdin=stdin,
                              env=env, shell=shell)
        (out, err) = sp.communicate(data)
    except OSError as e:
        if status_cb:
            status_cb('ERROR: End run command: invalid command provided\n')
        raise ProcessExecutionError(
            cmd=args, reason=e, errno=e.errno,
            stdout="-" if decode else b"-",
            stderr="-" if decode else b"-")
    finally:
        if devnull_fp:
            devnull_fp.close()

    # Just ensure blank instead of none.
    if not out and capture:
        out = b''
    if not err and capture:
        err = b''
    if decode:
        def ldecode(data, m='utf-8'):
            if not isinstance(data, bytes):
                return data
            return data.decode(m, decode)

        out = ldecode(out)
        err = ldecode(err)

    rc = sp.returncode
    if rc not in rcs:
        if status_cb:
            status_cb(
                'ERROR: End run command: exit({code})\n'.format(code=rc))
        raise ProcessExecutionError(stdout=out, stderr=err,
                                    exit_code=rc,
                                    cmd=args)
    if status_cb:
        status_cb('End run command: exit({code})\n'.format(code=rc))
    return (out, err)


def make_header(comment_char="#", base='created'):
    ci_ver = version.version_string()
    header = str(comment_char)
    header += " %s by cloud-init v. %s" % (base.title(), ci_ver)
    header += " on %s" % time_rfc2822()
    return header


def abs_join(*paths):
    return os.path.abspath(os.path.join(*paths))


# shellify, takes a list of commands
#  for each entry in the list
#    if it is an array, shell protect it (with single ticks)
#    if it is a string, do nothing
def shellify(cmdlist, add_header=True):
    if not isinstance(cmdlist, (tuple, list)):
        raise TypeError(
            "Input to shellify was type '%s'. Expected list or tuple." %
            (type_utils.obj_name(cmdlist)))

    content = ''
    if add_header:
        content += "#!/bin/sh\n"
    escaped = "%s%s%s%s" % ("'", '\\', "'", "'")
    cmds_made = 0
    for args in cmdlist:
        # If the item is a list, wrap all items in single tick.
        # If its not, then just write it directly.
        if isinstance(args, (list, tuple)):
            fixed = []
            for f in args:
                fixed.append("'%s'" % (six.text_type(f).replace("'", escaped)))
            content = "%s%s\n" % (content, ' '.join(fixed))
            cmds_made += 1
        elif isinstance(args, six.string_types):
            content = "%s%s\n" % (content, args)
            cmds_made += 1
        else:
            raise TypeError(
                "Unable to shellify type '%s'. Expected list, string, tuple. "
                "Got: %s" % (type_utils.obj_name(args), args))

    LOG.debug("Shellified %s commands.", cmds_made)
    return content


def strip_prefix_suffix(line, prefix=None, suffix=None):
    if prefix and line.startswith(prefix):
        line = line[len(prefix):]
    if suffix and line.endswith(suffix):
        line = line[:-len(suffix)]
    return line


def is_container():
    """
    Checks to see if this code running in a container of some sort
    """

    for helper in CONTAINER_TESTS:
        try:
            # try to run a helper program. if it returns true/zero
            # then we're inside a container. otherwise, no
            subp(helper)
            return True
        except (IOError, OSError):
            pass

    # this code is largely from the logic in
    # ubuntu's /etc/init/container-detect.conf
    try:
        # Detect old-style libvirt
        # Detect OpenVZ containers
        pid1env = get_proc_env(1)
        if "container" in pid1env:
            return True
        if "LIBVIRT_LXC_UUID" in pid1env:
            return True
    except (IOError, OSError):
        pass

    # Detect OpenVZ containers
    if os.path.isdir("/proc/vz") and not os.path.isdir("/proc/bc"):
        return True

    try:
        # Detect Vserver containers
        lines = load_file("/proc/self/status").splitlines()
        for line in lines:
            if line.startswith("VxID:"):
                (_key, val) = line.strip().split(":", 1)
                if val != "0":
                    return True
    except (IOError, OSError):
        pass

    return False


def get_proc_env(pid):
    """
    Return the environment in a dict that a given process id was started with.
    """

    env = {}
    fn = os.path.join("/proc/", str(pid), "environ")
    try:
        contents = load_file(fn)
        toks = contents.split("\x00")
        for tok in toks:
            if tok == "":
                continue
            (name, val) = tok.split("=", 1)
            if name:
                env[name] = val
    except (IOError, OSError):
        pass
    return env


def keyval_str_to_dict(kvstring):
    ret = {}
    for tok in kvstring.split():
        try:
            (key, val) = tok.split("=", 1)
        except ValueError:
            key = tok
            val = True
        ret[key] = val
    return ret


def is_partition(device):
    if device.startswith("/dev/"):
        device = device[5:]

    return os.path.isfile("/sys/class/block/%s/partition" % device)


def expand_package_list(version_fmt, pkgs):
    # we will accept tuples, lists of tuples, or just plain lists
    if not isinstance(pkgs, list):
        pkgs = [pkgs]

    pkglist = []
    for pkg in pkgs:
        if isinstance(pkg, six.string_types):
            pkglist.append(pkg)
            continue

        if isinstance(pkg, (tuple, list)):
            if len(pkg) < 1 or len(pkg) > 2:
                raise RuntimeError("Invalid package & version tuple.")

            if len(pkg) == 2 and pkg[1]:
                pkglist.append(version_fmt % tuple(pkg))
                continue

            pkglist.append(pkg[0])

        else:
            raise RuntimeError("Invalid package type.")

    return pkglist


def parse_mount_info(path, mountinfo_lines, log=LOG, get_mnt_opts=False):
    """Return the mount information for PATH given the lines from
    /proc/$$/mountinfo."""

    path_elements = [e for e in path.split('/') if e]
    devpth = None
    fs_type = None
    match_mount_point = None
    match_mount_point_elements = None
    for i, line in enumerate(mountinfo_lines):
        parts = line.split()

        # Completely fail if there is anything in any line that is
        # unexpected, as continuing to parse past a bad line could
        # cause an incorrect result to be returned, so it's better
        # return nothing than an incorrect result.

        # The minimum number of elements in a valid line is 10.
        if len(parts) < 10:
            log.debug("Line %d has two few columns (%d): %s",
                      i + 1, len(parts), line)
            return None

        mount_point = parts[4]
        mount_point_elements = [e for e in mount_point.split('/') if e]

        # Ignore mounts deeper than the path in question.
        if len(mount_point_elements) > len(path_elements):
            continue

        # Ignore mounts where the common path is not the same.
        x = min(len(mount_point_elements), len(path_elements))
        if mount_point_elements[0:x] != path_elements[0:x]:
            continue

        # Ignore mount points higher than an already seen mount
        # point.
        if (match_mount_point_elements is not None and
                len(match_mount_point_elements) > len(mount_point_elements)):
            continue

        # Find the '-' which terminates a list of optional columns to
        # find the filesystem type and the path to the device.  See
        # man 5 proc for the format of this file.
        try:
            i = parts.index('-')
        except ValueError:
            log.debug("Did not find column named '-' in line %d: %s",
                      i + 1, line)
            return None

        # Get the path to the device.
        try:
            fs_type = parts[i + 1]
            devpth = parts[i + 2]
        except IndexError:
            log.debug("Too few columns after '-' column in line %d: %s",
                      i + 1, line)
            return None

        match_mount_point = mount_point
        match_mount_point_elements = mount_point_elements
        mount_options = parts[5]

    if get_mnt_opts:
        if devpth and fs_type and match_mount_point and mount_options:
            return (devpth, fs_type, match_mount_point, mount_options)
    else:
        if devpth and fs_type and match_mount_point:
            return (devpth, fs_type, match_mount_point)

    return None


def parse_mtab(path):
    """On older kernels there's no /proc/$$/mountinfo, so use mtab."""
    for line in load_file("/etc/mtab").splitlines():
        devpth, mount_point, fs_type = line.split()[:3]
        if mount_point == path:
            return devpth, fs_type, mount_point
    return None


def find_freebsd_part(label_part):
    if label_part.startswith("/dev/label/"):
        target_label = label_part[5:]
        (label_part, err) = subp(['glabel', 'status', '-s'])
        for labels in label_part.split("\n"):
            items = labels.split()
            if len(items) > 0 and items[0].startswith(target_label):
                label_part = items[2]
                break
        label_part = str(label_part)
    return label_part


def get_path_dev_freebsd(path, mnt_list):
    path_found = None
    for line in mnt_list.split("\n"):
        items = line.split()
        if (len(items) > 2 and os.path.exists(items[1] + path)):
            path_found = line
            break
    return path_found


def get_mount_info_freebsd(path):
    (result, err) = subp(['mount', '-p', path], rcs=[0, 1])
    if len(err):
        # find a path if the input is not a mounting point
        (mnt_list, err) = subp(['mount', '-p'])
        path_found = get_path_dev_freebsd(path, mnt_list)
        if (path_found is None):
            return None
        result = path_found
    ret = result.split()
    label_part = find_freebsd_part(ret[0])
    return "/dev/" + label_part, ret[2], ret[1]


def get_device_info_from_zpool(zpool):
    # zpool has 10 second timeout waiting for /dev/zfs LP: #1760173
    if not os.path.exists('/dev/zfs'):
        LOG.debug('Cannot get zpool info, no /dev/zfs')
        return None
    try:
        (zpoolstatus, err) = subp(['zpool', 'status', zpool])
    except ProcessExecutionError as err:
        LOG.warning("Unable to get zpool status of %s: %s", zpool, err)
        return None
    if len(err):
        return None
    r = r'.*(ONLINE).*'
    for line in zpoolstatus.split("\n"):
        if re.search(r, line) and zpool not in line and "state" not in line:
            disk = line.split()[0]
            LOG.debug('found zpool "%s" on disk %s', zpool, disk)
            return disk


def parse_mount(path):
    (mountoutput, _err) = subp(['mount'])
    mount_locs = mountoutput.splitlines()
    # there are 2 types of mount outputs we have to parse therefore
    # the regex is a bit complex. to better understand this regex see:
    # https://regex101.com/r/2F6c1k/1
    # https://regex101.com/r/T2en7a/1
    regex = (r'^(/dev/[\S]+|.*zroot\S*?) on (/[\S]*) '
             r'(?=(?:type)[\s]+([\S]+)|\(([^,]*))')
    for line in mount_locs:
        m = re.search(regex, line)
        if not m:
            continue
        devpth = m.group(1)
        mount_point = m.group(2)
        # above regex will either fill the fs_type in group(3)
        # or group(4) depending on the format we have.
        fs_type = m.group(3)
        if fs_type is None:
            fs_type = m.group(4)
        LOG.debug('found line in mount -> devpth: %s, mount_point: %s, '
                  'fs_type: %s', devpth, mount_point, fs_type)
        # check whether the dev refers to a label on FreeBSD
        # for example, if dev is '/dev/label/rootfs', we should
        # continue finding the real device like '/dev/da0'.
        # this is only valid for non zfs file systems as a zpool
        # can have gpt labels as disk.
        devm = re.search('^(/dev/.+)p([0-9])$', devpth)
        if not devm and is_FreeBSD() and fs_type != 'zfs':
            return get_mount_info_freebsd(path)
        elif mount_point == path:
            return devpth, fs_type, mount_point
    return None


def get_mount_info(path, log=LOG, get_mnt_opts=False):
    # Use /proc/$$/mountinfo to find the device where path is mounted.
    # This is done because with a btrfs filesystem using os.stat(path)
    # does not return the ID of the device.
    #
    # Here, / has a device of 18 (decimal).
    #
    # $ stat /
    #   File: '/'
    #   Size: 234               Blocks: 0          IO Block: 4096   directory
    # Device: 12h/18d   Inode: 256         Links: 1
    # Access: (0755/drwxr-xr-x)  Uid: (    0/    root)   Gid: (    0/    root)
    # Access: 2013-01-13 07:31:04.358011255 +0000
    # Modify: 2013-01-13 18:48:25.930011255 +0000
    # Change: 2013-01-13 18:48:25.930011255 +0000
    #  Birth: -
    #
    # Find where / is mounted:
    #
    # $ mount | grep ' / '
    # /dev/vda1 on / type btrfs (rw,subvol=@,compress=lzo)
    #
    # And the device ID for /dev/vda1 is not 18:
    #
    # $ ls -l /dev/vda1
    # brw-rw---- 1 root disk 253, 1 Jan 13 08:29 /dev/vda1
    #
    # So use /proc/$$/mountinfo to find the device underlying the
    # input path.
    mountinfo_path = '/proc/%s/mountinfo' % os.getpid()
    if os.path.exists(mountinfo_path):
        lines = load_file(mountinfo_path).splitlines()
        return parse_mount_info(path, lines, log, get_mnt_opts)
    elif os.path.exists("/etc/mtab"):
        return parse_mtab(path)
    else:
        return parse_mount(path)


def is_exe(fpath):
    # return boolean indicating if fpath exists and is executable.
    return os.path.isfile(fpath) and os.access(fpath, os.X_OK)


def which(program, search=None, target=None):
    target = target_path(target)

    if os.path.sep in program:
        # if program had a '/' in it, then do not search PATH
        # 'which' does consider cwd here. (cd / && which bin/ls) = bin/ls
        # so effectively we set cwd to / (or target)
        if is_exe(target_path(target, program)):
            return program

    if search is None:
        paths = [p.strip('"') for p in
                 os.environ.get("PATH", "").split(os.pathsep)]
        if target == "/":
            search = paths
        else:
            search = [p for p in paths if p.startswith("/")]

    # normalize path input
    search = [os.path.abspath(p) for p in search]

    for path in search:
        ppath = os.path.sep.join((path, program))
        if is_exe(target_path(target, ppath)):
            return ppath

    return None


def log_time(logfunc, msg, func, args=None, kwargs=None, get_uptime=False):
    if args is None:
        args = []
    if kwargs is None:
        kwargs = {}

    start = time.time()

    ustart = None
    if get_uptime:
        try:
            ustart = float(uptime())
        except ValueError:
            pass

    try:
        ret = func(*args, **kwargs)
    finally:
        delta = time.time() - start
        udelta = None
        if ustart is not None:
            try:
                udelta = float(uptime()) - ustart
            except ValueError:
                pass

        tmsg = " took %0.3f seconds" % delta
        if get_uptime:
            if isinstance(udelta, (float)):
                tmsg += " (%0.2f)" % udelta
            else:
                tmsg += " (N/A)"
        try:
            logfunc(msg + tmsg)
        except Exception:
            pass
    return ret


def expand_dotted_devname(dotted):
    toks = dotted.rsplit(".", 1)
    if len(toks) > 1:
        return toks
    else:
        return (dotted, None)


def pathprefix2dict(base, required=None, optional=None, delim=os.path.sep):
    # return a dictionary populated with keys in 'required' and 'optional'
    # by reading files in prefix + delim + entry
    if required is None:
        required = []
    if optional is None:
        optional = []

    missing = []
    ret = {}
    for f in required + optional:
        try:
            ret[f] = load_file(base + delim + f, quiet=False, decode=False)
        except IOError as e:
            if e.errno != ENOENT:
                raise
            if f in required:
                missing.append(f)

    if len(missing):
        raise ValueError(
            'Missing required files: {files}'.format(files=','.join(missing)))

    return ret


def read_meminfo(meminfo="/proc/meminfo", raw=False):
    # read a /proc/meminfo style file and return
    # a dict with 'total', 'free', and 'available'
    mpliers = {'kB': 2 ** 10, 'mB': 2 ** 20, 'B': 1, 'gB': 2 ** 30}
    kmap = {'MemTotal:': 'total', 'MemFree:': 'free',
            'MemAvailable:': 'available'}
    ret = {}
    for line in load_file(meminfo).splitlines():
        try:
            key, value, unit = line.split()
        except ValueError:
            key, value = line.split()
            unit = 'B'
        if raw:
            ret[key] = int(value) * mpliers[unit]
        elif key in kmap:
            ret[kmap[key]] = int(value) * mpliers[unit]

    return ret


def human2bytes(size):
    """Convert human string or integer to size in bytes
      10M => 10485760
      .5G => 536870912
    """
    size_in = size
    if size.endswith("B"):
        size = size[:-1]

    mpliers = {'B': 1, 'K': 2 ** 10, 'M': 2 ** 20, 'G': 2 ** 30, 'T': 2 ** 40}

    num = size
    mplier = 'B'
    for m in mpliers:
        if size.endswith(m):
            mplier = m
            num = size[0:-len(m)]

    try:
        num = float(num)
    except ValueError:
        raise ValueError("'%s' is not valid input." % size_in)

    if num < 0:
        raise ValueError("'%s': cannot be negative" % size_in)

    return int(num * mpliers[mplier])


def _read_dmi_syspath(key):
    """
    Reads dmi data with from /sys/class/dmi/id
    """
    if key not in DMIDECODE_TO_DMI_SYS_MAPPING:
        return None
    mapped_key = DMIDECODE_TO_DMI_SYS_MAPPING[key]
    dmi_key_path = "{0}/{1}".format(DMI_SYS_PATH, mapped_key)
    LOG.debug("querying dmi data %s", dmi_key_path)
    try:
        if not os.path.exists(dmi_key_path):
            LOG.debug("did not find %s", dmi_key_path)
            return None

        key_data = load_file(dmi_key_path, decode=False)
        if not key_data:
            LOG.debug("%s did not return any data", dmi_key_path)
            return None

        # uninitialized dmi values show as all \xff and /sys appends a '\n'.
        # in that event, return a string of '.' in the same length.
        if key_data == b'\xff' * (len(key_data) - 1) + b'\n':
            key_data = b""

        str_data = key_data.decode('utf8').strip()
        LOG.debug("dmi data %s returned %s", dmi_key_path, str_data)
        return str_data

    except Exception:
        logexc(LOG, "failed read of %s", dmi_key_path)
        return None


def _call_dmidecode(key, dmidecode_path):
    """
    Calls out to dmidecode to get the data out. This is mostly for supporting
    OS's without /sys/class/dmi/id support.
    """
    try:
        cmd = [dmidecode_path, "--string", key]
        (result, _err) = subp(cmd)
        LOG.debug("dmidecode returned '%s' for '%s'", result, key)
        result = result.strip()
        if result.replace(".", "") == "":
            return ""
        return result
    except (IOError, OSError) as _err:
        LOG.debug('failed dmidecode cmd: %s\n%s', cmd, _err)
        return None


def read_dmi_data(key):
    """
    Wrapper for reading DMI data.

    If running in a container return None.  This is because DMI data is
    assumed to be not useful in a container as it does not represent the
    container but rather the host.

    This will do the following (returning the first that produces a
    result):
        1) Use a mapping to translate `key` from dmidecode naming to
           sysfs naming and look in /sys/class/dmi/... for a value.
        2) Use `key` as a sysfs key directly and look in /sys/class/dmi/...
        3) Fall-back to passing `key` to `dmidecode --string`.

    If all of the above fail to find a value, None will be returned.
    """

    if is_container():
        return None

    syspath_value = _read_dmi_syspath(key)
    if syspath_value is not None:
        return syspath_value

    # running dmidecode can be problematic on some arches (LP: #1243287)
    uname_arch = os.uname()[4]
    if not (uname_arch == "x86_64" or
            (uname_arch.startswith("i") and uname_arch[2:] == "86") or
            uname_arch == 'aarch64' or
            uname_arch == 'amd64'):
        LOG.debug("dmidata is not supported on %s", uname_arch)
        return None

    dmidecode_path = which('dmidecode')
    if dmidecode_path:
        return _call_dmidecode(key, dmidecode_path)

    LOG.warning("did not find either path %s or dmidecode command",
                DMI_SYS_PATH)
    return None


def message_from_string(string):
    if sys.version_info[:2] < (2, 7):
        return email.message_from_file(six.StringIO(string))
    return email.message_from_string(string)


def get_installed_packages(target=None):
    (out, _) = subp(['dpkg-query', '--list'], target=target, capture=True)

    pkgs_inst = set()
    for line in out.splitlines():
        try:
            (state, pkg, _) = line.split(None, 2)
        except ValueError:
            continue
        if state.startswith("hi") or state.startswith("ii"):
            pkgs_inst.add(re.sub(":.*", "", pkg))

    return pkgs_inst


def system_is_snappy():
    # channel.ini is configparser loadable.
    # snappy will move to using /etc/system-image/config.d/*.ini
    # this is certainly not a perfect test, but good enough for now.
    orpath = "/etc/os-release"
    try:
        orinfo = load_shell_content(load_file(orpath, quiet=True))
        if orinfo.get('ID', '').lower() == "ubuntu-core":
            return True
    except ValueError as e:
        LOG.warning("Unexpected error loading '%s': %s", orpath, e)

    cmdline = get_cmdline()
    if 'snap_core=' in cmdline:
        return True

    content = load_file("/etc/system-image/channel.ini", quiet=True)
    if 'ubuntu-core' in content.lower():
        return True
    if os.path.isdir("/etc/system-image/config.d/"):
        return True
    return False


def indent(text, prefix):
    """replacement for indent from textwrap that is not available in 2.7."""
    lines = []
    for line in text.splitlines(True):
        lines.append(prefix + line)
    return ''.join(lines)


def rootdev_from_cmdline(cmdline):
    found = None
    for tok in cmdline.split():
        if tok.startswith("root="):
            found = tok[5:]
            break
    if found is None:
        return None

    if found.startswith("/dev/"):
        return found
    if found.startswith("LABEL="):
        return "/dev/disk/by-label/" + found[len("LABEL="):]
    if found.startswith("UUID="):
        return "/dev/disk/by-uuid/" + found[len("UUID="):].lower()
    if found.startswith("PARTUUID="):
        disks_path = ("/dev/disk/by-partuuid/" +
                      found[len("PARTUUID="):].lower())
        if os.path.exists(disks_path):
            return disks_path
        results = find_devs_with(found)
        if results:
            return results[0]
        # we know this doesn't exist, but for consistency return the path as
        # it /would/ exist
        return disks_path

    return "/dev/" + found


def load_shell_content(content, add_empty=False, empty_val=None):
    """Given shell like syntax (key=value\nkey2=value2\n) in content
       return the data in dictionary form.  If 'add_empty' is True
       then add entries in to the returned dictionary for 'VAR='
       variables.  Set their value to empty_val."""

    def _shlex_split(blob):
        if PY26 and isinstance(blob, six.text_type):
            # Older versions don't support unicode input
            blob = blob.encode("utf8")
        return shlex.split(blob, comments=True)

    data = {}
    for line in _shlex_split(content):
        key, value = line.split("=", 1)
        if not value:
            value = empty_val
        if add_empty or value:
            data[key] = value

    return data


def wait_for_files(flist, maxwait, naplen=.5, log_pre=""):
    need = set(flist)
    waited = 0
    while True:
        need -= set([f for f in need if os.path.exists(f)])
        if len(need) == 0:
            LOG.debug("%sAll files appeared after %s seconds: %s",
                      log_pre, waited, flist)
            return []
        if waited == 0:
            LOG.debug("%sWaiting up to %s seconds for the following files: %s",
                      log_pre, maxwait, flist)
        if waited + naplen > maxwait:
            break
        time.sleep(naplen)
        waited += naplen

    LOG.debug("%sStill missing files after %s seconds: %s",
              log_pre, maxwait, need)
    return need


def mount_is_read_write(mount_point):
    """Check whether the given mount point is mounted rw"""
    result = get_mount_info(mount_point, get_mnt_opts=True)
    mount_opts = result[-1].split(',')
    return mount_opts[0] == 'rw'

# vi: ts=4 expandtab