File size: 140,481 Bytes
f14e74e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 |
import warnings
from collections import Counter, defaultdict, deque, abc
from collections.abc import Sequence
from functools import cached_property, partial, reduce, wraps
from heapq import heapify, heapreplace, heappop
from itertools import (
chain,
compress,
count,
cycle,
dropwhile,
groupby,
islice,
repeat,
starmap,
takewhile,
tee,
zip_longest,
product,
)
from math import exp, factorial, floor, log
from queue import Empty, Queue
from random import random, randrange, uniform
from operator import itemgetter, mul, sub, gt, lt, ge, le
from sys import hexversion, maxsize
from time import monotonic
from .recipes import (
_marker,
_zip_equal,
UnequalIterablesError,
consume,
flatten,
pairwise,
powerset,
take,
unique_everseen,
all_equal,
batched,
)
__all__ = [
'AbortThread',
'SequenceView',
'UnequalIterablesError',
'adjacent',
'all_unique',
'always_iterable',
'always_reversible',
'bucket',
'callback_iter',
'chunked',
'chunked_even',
'circular_shifts',
'collapse',
'combination_index',
'combination_with_replacement_index',
'consecutive_groups',
'constrained_batches',
'consumer',
'count_cycle',
'countable',
'difference',
'distinct_combinations',
'distinct_permutations',
'distribute',
'divide',
'duplicates_everseen',
'duplicates_justseen',
'exactly_n',
'filter_except',
'first',
'gray_product',
'groupby_transform',
'ichunked',
'iequals',
'ilen',
'interleave',
'interleave_evenly',
'interleave_longest',
'intersperse',
'is_sorted',
'islice_extended',
'iterate',
'last',
'locate',
'longest_common_prefix',
'lstrip',
'make_decorator',
'map_except',
'map_if',
'map_reduce',
'mark_ends',
'minmax',
'nth_or_last',
'nth_permutation',
'nth_product',
'nth_combination_with_replacement',
'numeric_range',
'one',
'only',
'outer_product',
'padded',
'partial_product',
'partitions',
'peekable',
'permutation_index',
'product_index',
'raise_',
'repeat_each',
'repeat_last',
'replace',
'rlocate',
'rstrip',
'run_length',
'sample',
'seekable',
'set_partitions',
'side_effect',
'sliced',
'sort_together',
'split_after',
'split_at',
'split_before',
'split_into',
'split_when',
'spy',
'stagger',
'strip',
'strictly_n',
'substrings',
'substrings_indexes',
'takewhile_inclusive',
'time_limited',
'unique_in_window',
'unique_to_each',
'unzip',
'value_chain',
'windowed',
'windowed_complete',
'with_iter',
'zip_broadcast',
'zip_equal',
'zip_offset',
]
def chunked(iterable, n, strict=False):
"""Break *iterable* into lists of length *n*:
>>> list(chunked([1, 2, 3, 4, 5, 6], 3))
[[1, 2, 3], [4, 5, 6]]
By the default, the last yielded list will have fewer than *n* elements
if the length of *iterable* is not divisible by *n*:
>>> list(chunked([1, 2, 3, 4, 5, 6, 7, 8], 3))
[[1, 2, 3], [4, 5, 6], [7, 8]]
To use a fill-in value instead, see the :func:`grouper` recipe.
If the length of *iterable* is not divisible by *n* and *strict* is
``True``, then ``ValueError`` will be raised before the last
list is yielded.
"""
iterator = iter(partial(take, n, iter(iterable)), [])
if strict:
if n is None:
raise ValueError('n must not be None when using strict mode.')
def ret():
for chunk in iterator:
if len(chunk) != n:
raise ValueError('iterable is not divisible by n.')
yield chunk
return iter(ret())
else:
return iterator
def first(iterable, default=_marker):
"""Return the first item of *iterable*, or *default* if *iterable* is
empty.
>>> first([0, 1, 2, 3])
0
>>> first([], 'some default')
'some default'
If *default* is not provided and there are no items in the iterable,
raise ``ValueError``.
:func:`first` is useful when you have a generator of expensive-to-retrieve
values and want any arbitrary one. It is marginally shorter than
``next(iter(iterable), default)``.
"""
try:
return next(iter(iterable))
except StopIteration as e:
if default is _marker:
raise ValueError(
'first() was called on an empty iterable, and no '
'default value was provided.'
) from e
return default
def last(iterable, default=_marker):
"""Return the last item of *iterable*, or *default* if *iterable* is
empty.
>>> last([0, 1, 2, 3])
3
>>> last([], 'some default')
'some default'
If *default* is not provided and there are no items in the iterable,
raise ``ValueError``.
"""
try:
if isinstance(iterable, Sequence):
return iterable[-1]
# Work around https://bugs.python.org/issue38525
elif hasattr(iterable, '__reversed__') and (hexversion != 0x030800F0):
return next(reversed(iterable))
else:
return deque(iterable, maxlen=1)[-1]
except (IndexError, TypeError, StopIteration):
if default is _marker:
raise ValueError(
'last() was called on an empty iterable, and no default was '
'provided.'
)
return default
def nth_or_last(iterable, n, default=_marker):
"""Return the nth or the last item of *iterable*,
or *default* if *iterable* is empty.
>>> nth_or_last([0, 1, 2, 3], 2)
2
>>> nth_or_last([0, 1], 2)
1
>>> nth_or_last([], 0, 'some default')
'some default'
If *default* is not provided and there are no items in the iterable,
raise ``ValueError``.
"""
return last(islice(iterable, n + 1), default=default)
class peekable:
"""Wrap an iterator to allow lookahead and prepending elements.
Call :meth:`peek` on the result to get the value that will be returned
by :func:`next`. This won't advance the iterator:
>>> p = peekable(['a', 'b'])
>>> p.peek()
'a'
>>> next(p)
'a'
Pass :meth:`peek` a default value to return that instead of raising
``StopIteration`` when the iterator is exhausted.
>>> p = peekable([])
>>> p.peek('hi')
'hi'
peekables also offer a :meth:`prepend` method, which "inserts" items
at the head of the iterable:
>>> p = peekable([1, 2, 3])
>>> p.prepend(10, 11, 12)
>>> next(p)
10
>>> p.peek()
11
>>> list(p)
[11, 12, 1, 2, 3]
peekables can be indexed. Index 0 is the item that will be returned by
:func:`next`, index 1 is the item after that, and so on:
The values up to the given index will be cached.
>>> p = peekable(['a', 'b', 'c', 'd'])
>>> p[0]
'a'
>>> p[1]
'b'
>>> next(p)
'a'
Negative indexes are supported, but be aware that they will cache the
remaining items in the source iterator, which may require significant
storage.
To check whether a peekable is exhausted, check its truth value:
>>> p = peekable(['a', 'b'])
>>> if p: # peekable has items
... list(p)
['a', 'b']
>>> if not p: # peekable is exhausted
... list(p)
[]
"""
def __init__(self, iterable):
self._it = iter(iterable)
self._cache = deque()
def __iter__(self):
return self
def __bool__(self):
try:
self.peek()
except StopIteration:
return False
return True
def peek(self, default=_marker):
"""Return the item that will be next returned from ``next()``.
Return ``default`` if there are no items left. If ``default`` is not
provided, raise ``StopIteration``.
"""
if not self._cache:
try:
self._cache.append(next(self._it))
except StopIteration:
if default is _marker:
raise
return default
return self._cache[0]
def prepend(self, *items):
"""Stack up items to be the next ones returned from ``next()`` or
``self.peek()``. The items will be returned in
first in, first out order::
>>> p = peekable([1, 2, 3])
>>> p.prepend(10, 11, 12)
>>> next(p)
10
>>> list(p)
[11, 12, 1, 2, 3]
It is possible, by prepending items, to "resurrect" a peekable that
previously raised ``StopIteration``.
>>> p = peekable([])
>>> next(p)
Traceback (most recent call last):
...
StopIteration
>>> p.prepend(1)
>>> next(p)
1
>>> next(p)
Traceback (most recent call last):
...
StopIteration
"""
self._cache.extendleft(reversed(items))
def __next__(self):
if self._cache:
return self._cache.popleft()
return next(self._it)
def _get_slice(self, index):
# Normalize the slice's arguments
step = 1 if (index.step is None) else index.step
if step > 0:
start = 0 if (index.start is None) else index.start
stop = maxsize if (index.stop is None) else index.stop
elif step < 0:
start = -1 if (index.start is None) else index.start
stop = (-maxsize - 1) if (index.stop is None) else index.stop
else:
raise ValueError('slice step cannot be zero')
# If either the start or stop index is negative, we'll need to cache
# the rest of the iterable in order to slice from the right side.
if (start < 0) or (stop < 0):
self._cache.extend(self._it)
# Otherwise we'll need to find the rightmost index and cache to that
# point.
else:
n = min(max(start, stop) + 1, maxsize)
cache_len = len(self._cache)
if n >= cache_len:
self._cache.extend(islice(self._it, n - cache_len))
return list(self._cache)[index]
def __getitem__(self, index):
if isinstance(index, slice):
return self._get_slice(index)
cache_len = len(self._cache)
if index < 0:
self._cache.extend(self._it)
elif index >= cache_len:
self._cache.extend(islice(self._it, index + 1 - cache_len))
return self._cache[index]
def consumer(func):
"""Decorator that automatically advances a PEP-342-style "reverse iterator"
to its first yield point so you don't have to call ``next()`` on it
manually.
>>> @consumer
... def tally():
... i = 0
... while True:
... print('Thing number %s is %s.' % (i, (yield)))
... i += 1
...
>>> t = tally()
>>> t.send('red')
Thing number 0 is red.
>>> t.send('fish')
Thing number 1 is fish.
Without the decorator, you would have to call ``next(t)`` before
``t.send()`` could be used.
"""
@wraps(func)
def wrapper(*args, **kwargs):
gen = func(*args, **kwargs)
next(gen)
return gen
return wrapper
def ilen(iterable):
"""Return the number of items in *iterable*.
>>> ilen(x for x in range(1000000) if x % 3 == 0)
333334
This consumes the iterable, so handle with care.
"""
# This approach was selected because benchmarks showed it's likely the
# fastest of the known implementations at the time of writing.
# See GitHub tracker: #236, #230.
counter = count()
deque(zip(iterable, counter), maxlen=0)
return next(counter)
def iterate(func, start):
"""Return ``start``, ``func(start)``, ``func(func(start))``, ...
>>> from itertools import islice
>>> list(islice(iterate(lambda x: 2*x, 1), 10))
[1, 2, 4, 8, 16, 32, 64, 128, 256, 512]
"""
while True:
yield start
try:
start = func(start)
except StopIteration:
break
def with_iter(context_manager):
"""Wrap an iterable in a ``with`` statement, so it closes once exhausted.
For example, this will close the file when the iterator is exhausted::
upper_lines = (line.upper() for line in with_iter(open('foo')))
Any context manager which returns an iterable is a candidate for
``with_iter``.
"""
with context_manager as iterable:
yield from iterable
def one(iterable, too_short=None, too_long=None):
"""Return the first item from *iterable*, which is expected to contain only
that item. Raise an exception if *iterable* is empty or has more than one
item.
:func:`one` is useful for ensuring that an iterable contains only one item.
For example, it can be used to retrieve the result of a database query
that is expected to return a single row.
If *iterable* is empty, ``ValueError`` will be raised. You may specify a
different exception with the *too_short* keyword:
>>> it = []
>>> one(it) # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
ValueError: too many items in iterable (expected 1)'
>>> too_short = IndexError('too few items')
>>> one(it, too_short=too_short) # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
IndexError: too few items
Similarly, if *iterable* contains more than one item, ``ValueError`` will
be raised. You may specify a different exception with the *too_long*
keyword:
>>> it = ['too', 'many']
>>> one(it) # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
ValueError: Expected exactly one item in iterable, but got 'too',
'many', and perhaps more.
>>> too_long = RuntimeError
>>> one(it, too_long=too_long) # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
RuntimeError
Note that :func:`one` attempts to advance *iterable* twice to ensure there
is only one item. See :func:`spy` or :func:`peekable` to check iterable
contents less destructively.
"""
it = iter(iterable)
try:
first_value = next(it)
except StopIteration as e:
raise (
too_short or ValueError('too few items in iterable (expected 1)')
) from e
try:
second_value = next(it)
except StopIteration:
pass
else:
msg = (
'Expected exactly one item in iterable, but got {!r}, {!r}, '
'and perhaps more.'.format(first_value, second_value)
)
raise too_long or ValueError(msg)
return first_value
def raise_(exception, *args):
raise exception(*args)
def strictly_n(iterable, n, too_short=None, too_long=None):
"""Validate that *iterable* has exactly *n* items and return them if
it does. If it has fewer than *n* items, call function *too_short*
with those items. If it has more than *n* items, call function
*too_long* with the first ``n + 1`` items.
>>> iterable = ['a', 'b', 'c', 'd']
>>> n = 4
>>> list(strictly_n(iterable, n))
['a', 'b', 'c', 'd']
By default, *too_short* and *too_long* are functions that raise
``ValueError``.
>>> list(strictly_n('ab', 3)) # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
ValueError: too few items in iterable (got 2)
>>> list(strictly_n('abc', 2)) # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
ValueError: too many items in iterable (got at least 3)
You can instead supply functions that do something else.
*too_short* will be called with the number of items in *iterable*.
*too_long* will be called with `n + 1`.
>>> def too_short(item_count):
... raise RuntimeError
>>> it = strictly_n('abcd', 6, too_short=too_short)
>>> list(it) # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
RuntimeError
>>> def too_long(item_count):
... print('The boss is going to hear about this')
>>> it = strictly_n('abcdef', 4, too_long=too_long)
>>> list(it)
The boss is going to hear about this
['a', 'b', 'c', 'd']
"""
if too_short is None:
too_short = lambda item_count: raise_(
ValueError,
'Too few items in iterable (got {})'.format(item_count),
)
if too_long is None:
too_long = lambda item_count: raise_(
ValueError,
'Too many items in iterable (got at least {})'.format(item_count),
)
it = iter(iterable)
for i in range(n):
try:
item = next(it)
except StopIteration:
too_short(i)
return
else:
yield item
try:
next(it)
except StopIteration:
pass
else:
too_long(n + 1)
def distinct_permutations(iterable, r=None):
"""Yield successive distinct permutations of the elements in *iterable*.
>>> sorted(distinct_permutations([1, 0, 1]))
[(0, 1, 1), (1, 0, 1), (1, 1, 0)]
Equivalent to ``set(permutations(iterable))``, except duplicates are not
generated and thrown away. For larger input sequences this is much more
efficient.
Duplicate permutations arise when there are duplicated elements in the
input iterable. The number of items returned is
`n! / (x_1! * x_2! * ... * x_n!)`, where `n` is the total number of
items input, and each `x_i` is the count of a distinct item in the input
sequence.
If *r* is given, only the *r*-length permutations are yielded.
>>> sorted(distinct_permutations([1, 0, 1], r=2))
[(0, 1), (1, 0), (1, 1)]
>>> sorted(distinct_permutations(range(3), r=2))
[(0, 1), (0, 2), (1, 0), (1, 2), (2, 0), (2, 1)]
"""
# Algorithm: https://w.wiki/Qai
def _full(A):
while True:
# Yield the permutation we have
yield tuple(A)
# Find the largest index i such that A[i] < A[i + 1]
for i in range(size - 2, -1, -1):
if A[i] < A[i + 1]:
break
# If no such index exists, this permutation is the last one
else:
return
# Find the largest index j greater than j such that A[i] < A[j]
for j in range(size - 1, i, -1):
if A[i] < A[j]:
break
# Swap the value of A[i] with that of A[j], then reverse the
# sequence from A[i + 1] to form the new permutation
A[i], A[j] = A[j], A[i]
A[i + 1 :] = A[: i - size : -1] # A[i + 1:][::-1]
# Algorithm: modified from the above
def _partial(A, r):
# Split A into the first r items and the last r items
head, tail = A[:r], A[r:]
right_head_indexes = range(r - 1, -1, -1)
left_tail_indexes = range(len(tail))
while True:
# Yield the permutation we have
yield tuple(head)
# Starting from the right, find the first index of the head with
# value smaller than the maximum value of the tail - call it i.
pivot = tail[-1]
for i in right_head_indexes:
if head[i] < pivot:
break
pivot = head[i]
else:
return
# Starting from the left, find the first value of the tail
# with a value greater than head[i] and swap.
for j in left_tail_indexes:
if tail[j] > head[i]:
head[i], tail[j] = tail[j], head[i]
break
# If we didn't find one, start from the right and find the first
# index of the head with a value greater than head[i] and swap.
else:
for j in right_head_indexes:
if head[j] > head[i]:
head[i], head[j] = head[j], head[i]
break
# Reverse head[i + 1:] and swap it with tail[:r - (i + 1)]
tail += head[: i - r : -1] # head[i + 1:][::-1]
i += 1
head[i:], tail[:] = tail[: r - i], tail[r - i :]
items = sorted(iterable)
size = len(items)
if r is None:
r = size
if 0 < r <= size:
return _full(items) if (r == size) else _partial(items, r)
return iter(() if r else ((),))
def intersperse(e, iterable, n=1):
"""Intersperse filler element *e* among the items in *iterable*, leaving
*n* items between each filler element.
>>> list(intersperse('!', [1, 2, 3, 4, 5]))
[1, '!', 2, '!', 3, '!', 4, '!', 5]
>>> list(intersperse(None, [1, 2, 3, 4, 5], n=2))
[1, 2, None, 3, 4, None, 5]
"""
if n == 0:
raise ValueError('n must be > 0')
elif n == 1:
# interleave(repeat(e), iterable) -> e, x_0, e, x_1, e, x_2...
# islice(..., 1, None) -> x_0, e, x_1, e, x_2...
return islice(interleave(repeat(e), iterable), 1, None)
else:
# interleave(filler, chunks) -> [e], [x_0, x_1], [e], [x_2, x_3]...
# islice(..., 1, None) -> [x_0, x_1], [e], [x_2, x_3]...
# flatten(...) -> x_0, x_1, e, x_2, x_3...
filler = repeat([e])
chunks = chunked(iterable, n)
return flatten(islice(interleave(filler, chunks), 1, None))
def unique_to_each(*iterables):
"""Return the elements from each of the input iterables that aren't in the
other input iterables.
For example, suppose you have a set of packages, each with a set of
dependencies::
{'pkg_1': {'A', 'B'}, 'pkg_2': {'B', 'C'}, 'pkg_3': {'B', 'D'}}
If you remove one package, which dependencies can also be removed?
If ``pkg_1`` is removed, then ``A`` is no longer necessary - it is not
associated with ``pkg_2`` or ``pkg_3``. Similarly, ``C`` is only needed for
``pkg_2``, and ``D`` is only needed for ``pkg_3``::
>>> unique_to_each({'A', 'B'}, {'B', 'C'}, {'B', 'D'})
[['A'], ['C'], ['D']]
If there are duplicates in one input iterable that aren't in the others
they will be duplicated in the output. Input order is preserved::
>>> unique_to_each("mississippi", "missouri")
[['p', 'p'], ['o', 'u', 'r']]
It is assumed that the elements of each iterable are hashable.
"""
pool = [list(it) for it in iterables]
counts = Counter(chain.from_iterable(map(set, pool)))
uniques = {element for element in counts if counts[element] == 1}
return [list(filter(uniques.__contains__, it)) for it in pool]
def windowed(seq, n, fillvalue=None, step=1):
"""Return a sliding window of width *n* over the given iterable.
>>> all_windows = windowed([1, 2, 3, 4, 5], 3)
>>> list(all_windows)
[(1, 2, 3), (2, 3, 4), (3, 4, 5)]
When the window is larger than the iterable, *fillvalue* is used in place
of missing values:
>>> list(windowed([1, 2, 3], 4))
[(1, 2, 3, None)]
Each window will advance in increments of *step*:
>>> list(windowed([1, 2, 3, 4, 5, 6], 3, fillvalue='!', step=2))
[(1, 2, 3), (3, 4, 5), (5, 6, '!')]
To slide into the iterable's items, use :func:`chain` to add filler items
to the left:
>>> iterable = [1, 2, 3, 4]
>>> n = 3
>>> padding = [None] * (n - 1)
>>> list(windowed(chain(padding, iterable), 3))
[(None, None, 1), (None, 1, 2), (1, 2, 3), (2, 3, 4)]
"""
if n < 0:
raise ValueError('n must be >= 0')
if n == 0:
yield tuple()
return
if step < 1:
raise ValueError('step must be >= 1')
window = deque(maxlen=n)
i = n
for _ in map(window.append, seq):
i -= 1
if not i:
i = step
yield tuple(window)
size = len(window)
if size == 0:
return
elif size < n:
yield tuple(chain(window, repeat(fillvalue, n - size)))
elif 0 < i < min(step, n):
window += (fillvalue,) * i
yield tuple(window)
def substrings(iterable):
"""Yield all of the substrings of *iterable*.
>>> [''.join(s) for s in substrings('more')]
['m', 'o', 'r', 'e', 'mo', 'or', 're', 'mor', 'ore', 'more']
Note that non-string iterables can also be subdivided.
>>> list(substrings([0, 1, 2]))
[(0,), (1,), (2,), (0, 1), (1, 2), (0, 1, 2)]
"""
# The length-1 substrings
seq = []
for item in iter(iterable):
seq.append(item)
yield (item,)
seq = tuple(seq)
item_count = len(seq)
# And the rest
for n in range(2, item_count + 1):
for i in range(item_count - n + 1):
yield seq[i : i + n]
def substrings_indexes(seq, reverse=False):
"""Yield all substrings and their positions in *seq*
The items yielded will be a tuple of the form ``(substr, i, j)``, where
``substr == seq[i:j]``.
This function only works for iterables that support slicing, such as
``str`` objects.
>>> for item in substrings_indexes('more'):
... print(item)
('m', 0, 1)
('o', 1, 2)
('r', 2, 3)
('e', 3, 4)
('mo', 0, 2)
('or', 1, 3)
('re', 2, 4)
('mor', 0, 3)
('ore', 1, 4)
('more', 0, 4)
Set *reverse* to ``True`` to yield the same items in the opposite order.
"""
r = range(1, len(seq) + 1)
if reverse:
r = reversed(r)
return (
(seq[i : i + L], i, i + L) for L in r for i in range(len(seq) - L + 1)
)
class bucket:
"""Wrap *iterable* and return an object that buckets it iterable into
child iterables based on a *key* function.
>>> iterable = ['a1', 'b1', 'c1', 'a2', 'b2', 'c2', 'b3']
>>> s = bucket(iterable, key=lambda x: x[0]) # Bucket by 1st character
>>> sorted(list(s)) # Get the keys
['a', 'b', 'c']
>>> a_iterable = s['a']
>>> next(a_iterable)
'a1'
>>> next(a_iterable)
'a2'
>>> list(s['b'])
['b1', 'b2', 'b3']
The original iterable will be advanced and its items will be cached until
they are used by the child iterables. This may require significant storage.
By default, attempting to select a bucket to which no items belong will
exhaust the iterable and cache all values.
If you specify a *validator* function, selected buckets will instead be
checked against it.
>>> from itertools import count
>>> it = count(1, 2) # Infinite sequence of odd numbers
>>> key = lambda x: x % 10 # Bucket by last digit
>>> validator = lambda x: x in {1, 3, 5, 7, 9} # Odd digits only
>>> s = bucket(it, key=key, validator=validator)
>>> 2 in s
False
>>> list(s[2])
[]
"""
def __init__(self, iterable, key, validator=None):
self._it = iter(iterable)
self._key = key
self._cache = defaultdict(deque)
self._validator = validator or (lambda x: True)
def __contains__(self, value):
if not self._validator(value):
return False
try:
item = next(self[value])
except StopIteration:
return False
else:
self._cache[value].appendleft(item)
return True
def _get_values(self, value):
"""
Helper to yield items from the parent iterator that match *value*.
Items that don't match are stored in the local cache as they
are encountered.
"""
while True:
# If we've cached some items that match the target value, emit
# the first one and evict it from the cache.
if self._cache[value]:
yield self._cache[value].popleft()
# Otherwise we need to advance the parent iterator to search for
# a matching item, caching the rest.
else:
while True:
try:
item = next(self._it)
except StopIteration:
return
item_value = self._key(item)
if item_value == value:
yield item
break
elif self._validator(item_value):
self._cache[item_value].append(item)
def __iter__(self):
for item in self._it:
item_value = self._key(item)
if self._validator(item_value):
self._cache[item_value].append(item)
yield from self._cache.keys()
def __getitem__(self, value):
if not self._validator(value):
return iter(())
return self._get_values(value)
def spy(iterable, n=1):
"""Return a 2-tuple with a list containing the first *n* elements of
*iterable*, and an iterator with the same items as *iterable*.
This allows you to "look ahead" at the items in the iterable without
advancing it.
There is one item in the list by default:
>>> iterable = 'abcdefg'
>>> head, iterable = spy(iterable)
>>> head
['a']
>>> list(iterable)
['a', 'b', 'c', 'd', 'e', 'f', 'g']
You may use unpacking to retrieve items instead of lists:
>>> (head,), iterable = spy('abcdefg')
>>> head
'a'
>>> (first, second), iterable = spy('abcdefg', 2)
>>> first
'a'
>>> second
'b'
The number of items requested can be larger than the number of items in
the iterable:
>>> iterable = [1, 2, 3, 4, 5]
>>> head, iterable = spy(iterable, 10)
>>> head
[1, 2, 3, 4, 5]
>>> list(iterable)
[1, 2, 3, 4, 5]
"""
it = iter(iterable)
head = take(n, it)
return head.copy(), chain(head, it)
def interleave(*iterables):
"""Return a new iterable yielding from each iterable in turn,
until the shortest is exhausted.
>>> list(interleave([1, 2, 3], [4, 5], [6, 7, 8]))
[1, 4, 6, 2, 5, 7]
For a version that doesn't terminate after the shortest iterable is
exhausted, see :func:`interleave_longest`.
"""
return chain.from_iterable(zip(*iterables))
def interleave_longest(*iterables):
"""Return a new iterable yielding from each iterable in turn,
skipping any that are exhausted.
>>> list(interleave_longest([1, 2, 3], [4, 5], [6, 7, 8]))
[1, 4, 6, 2, 5, 7, 3, 8]
This function produces the same output as :func:`roundrobin`, but may
perform better for some inputs (in particular when the number of iterables
is large).
"""
i = chain.from_iterable(zip_longest(*iterables, fillvalue=_marker))
return (x for x in i if x is not _marker)
def interleave_evenly(iterables, lengths=None):
"""
Interleave multiple iterables so that their elements are evenly distributed
throughout the output sequence.
>>> iterables = [1, 2, 3, 4, 5], ['a', 'b']
>>> list(interleave_evenly(iterables))
[1, 2, 'a', 3, 4, 'b', 5]
>>> iterables = [[1, 2, 3], [4, 5], [6, 7, 8]]
>>> list(interleave_evenly(iterables))
[1, 6, 4, 2, 7, 3, 8, 5]
This function requires iterables of known length. Iterables without
``__len__()`` can be used by manually specifying lengths with *lengths*:
>>> from itertools import combinations, repeat
>>> iterables = [combinations(range(4), 2), ['a', 'b', 'c']]
>>> lengths = [4 * (4 - 1) // 2, 3]
>>> list(interleave_evenly(iterables, lengths=lengths))
[(0, 1), (0, 2), 'a', (0, 3), (1, 2), 'b', (1, 3), (2, 3), 'c']
Based on Bresenham's algorithm.
"""
if lengths is None:
try:
lengths = [len(it) for it in iterables]
except TypeError:
raise ValueError(
'Iterable lengths could not be determined automatically. '
'Specify them with the lengths keyword.'
)
elif len(iterables) != len(lengths):
raise ValueError('Mismatching number of iterables and lengths.')
dims = len(lengths)
# sort iterables by length, descending
lengths_permute = sorted(
range(dims), key=lambda i: lengths[i], reverse=True
)
lengths_desc = [lengths[i] for i in lengths_permute]
iters_desc = [iter(iterables[i]) for i in lengths_permute]
# the longest iterable is the primary one (Bresenham: the longest
# distance along an axis)
delta_primary, deltas_secondary = lengths_desc[0], lengths_desc[1:]
iter_primary, iters_secondary = iters_desc[0], iters_desc[1:]
errors = [delta_primary // dims] * len(deltas_secondary)
to_yield = sum(lengths)
while to_yield:
yield next(iter_primary)
to_yield -= 1
# update errors for each secondary iterable
errors = [e - delta for e, delta in zip(errors, deltas_secondary)]
# those iterables for which the error is negative are yielded
# ("diagonal step" in Bresenham)
for i, e in enumerate(errors):
if e < 0:
yield next(iters_secondary[i])
to_yield -= 1
errors[i] += delta_primary
def collapse(iterable, base_type=None, levels=None):
"""Flatten an iterable with multiple levels of nesting (e.g., a list of
lists of tuples) into non-iterable types.
>>> iterable = [(1, 2), ([3, 4], [[5], [6]])]
>>> list(collapse(iterable))
[1, 2, 3, 4, 5, 6]
Binary and text strings are not considered iterable and
will not be collapsed.
To avoid collapsing other types, specify *base_type*:
>>> iterable = ['ab', ('cd', 'ef'), ['gh', 'ij']]
>>> list(collapse(iterable, base_type=tuple))
['ab', ('cd', 'ef'), 'gh', 'ij']
Specify *levels* to stop flattening after a certain level:
>>> iterable = [('a', ['b']), ('c', ['d'])]
>>> list(collapse(iterable)) # Fully flattened
['a', 'b', 'c', 'd']
>>> list(collapse(iterable, levels=1)) # Only one level flattened
['a', ['b'], 'c', ['d']]
"""
def walk(node, level):
if (
((levels is not None) and (level > levels))
or isinstance(node, (str, bytes))
or ((base_type is not None) and isinstance(node, base_type))
):
yield node
return
try:
tree = iter(node)
except TypeError:
yield node
return
else:
for child in tree:
yield from walk(child, level + 1)
yield from walk(iterable, 0)
def side_effect(func, iterable, chunk_size=None, before=None, after=None):
"""Invoke *func* on each item in *iterable* (or on each *chunk_size* group
of items) before yielding the item.
`func` must be a function that takes a single argument. Its return value
will be discarded.
*before* and *after* are optional functions that take no arguments. They
will be executed before iteration starts and after it ends, respectively.
`side_effect` can be used for logging, updating progress bars, or anything
that is not functionally "pure."
Emitting a status message:
>>> from more_itertools import consume
>>> func = lambda item: print('Received {}'.format(item))
>>> consume(side_effect(func, range(2)))
Received 0
Received 1
Operating on chunks of items:
>>> pair_sums = []
>>> func = lambda chunk: pair_sums.append(sum(chunk))
>>> list(side_effect(func, [0, 1, 2, 3, 4, 5], 2))
[0, 1, 2, 3, 4, 5]
>>> list(pair_sums)
[1, 5, 9]
Writing to a file-like object:
>>> from io import StringIO
>>> from more_itertools import consume
>>> f = StringIO()
>>> func = lambda x: print(x, file=f)
>>> before = lambda: print(u'HEADER', file=f)
>>> after = f.close
>>> it = [u'a', u'b', u'c']
>>> consume(side_effect(func, it, before=before, after=after))
>>> f.closed
True
"""
try:
if before is not None:
before()
if chunk_size is None:
for item in iterable:
func(item)
yield item
else:
for chunk in chunked(iterable, chunk_size):
func(chunk)
yield from chunk
finally:
if after is not None:
after()
def sliced(seq, n, strict=False):
"""Yield slices of length *n* from the sequence *seq*.
>>> list(sliced((1, 2, 3, 4, 5, 6), 3))
[(1, 2, 3), (4, 5, 6)]
By the default, the last yielded slice will have fewer than *n* elements
if the length of *seq* is not divisible by *n*:
>>> list(sliced((1, 2, 3, 4, 5, 6, 7, 8), 3))
[(1, 2, 3), (4, 5, 6), (7, 8)]
If the length of *seq* is not divisible by *n* and *strict* is
``True``, then ``ValueError`` will be raised before the last
slice is yielded.
This function will only work for iterables that support slicing.
For non-sliceable iterables, see :func:`chunked`.
"""
iterator = takewhile(len, (seq[i : i + n] for i in count(0, n)))
if strict:
def ret():
for _slice in iterator:
if len(_slice) != n:
raise ValueError("seq is not divisible by n.")
yield _slice
return iter(ret())
else:
return iterator
def split_at(iterable, pred, maxsplit=-1, keep_separator=False):
"""Yield lists of items from *iterable*, where each list is delimited by
an item where callable *pred* returns ``True``.
>>> list(split_at('abcdcba', lambda x: x == 'b'))
[['a'], ['c', 'd', 'c'], ['a']]
>>> list(split_at(range(10), lambda n: n % 2 == 1))
[[0], [2], [4], [6], [8], []]
At most *maxsplit* splits are done. If *maxsplit* is not specified or -1,
then there is no limit on the number of splits:
>>> list(split_at(range(10), lambda n: n % 2 == 1, maxsplit=2))
[[0], [2], [4, 5, 6, 7, 8, 9]]
By default, the delimiting items are not included in the output.
To include them, set *keep_separator* to ``True``.
>>> list(split_at('abcdcba', lambda x: x == 'b', keep_separator=True))
[['a'], ['b'], ['c', 'd', 'c'], ['b'], ['a']]
"""
if maxsplit == 0:
yield list(iterable)
return
buf = []
it = iter(iterable)
for item in it:
if pred(item):
yield buf
if keep_separator:
yield [item]
if maxsplit == 1:
yield list(it)
return
buf = []
maxsplit -= 1
else:
buf.append(item)
yield buf
def split_before(iterable, pred, maxsplit=-1):
"""Yield lists of items from *iterable*, where each list ends just before
an item for which callable *pred* returns ``True``:
>>> list(split_before('OneTwo', lambda s: s.isupper()))
[['O', 'n', 'e'], ['T', 'w', 'o']]
>>> list(split_before(range(10), lambda n: n % 3 == 0))
[[0, 1, 2], [3, 4, 5], [6, 7, 8], [9]]
At most *maxsplit* splits are done. If *maxsplit* is not specified or -1,
then there is no limit on the number of splits:
>>> list(split_before(range(10), lambda n: n % 3 == 0, maxsplit=2))
[[0, 1, 2], [3, 4, 5], [6, 7, 8, 9]]
"""
if maxsplit == 0:
yield list(iterable)
return
buf = []
it = iter(iterable)
for item in it:
if pred(item) and buf:
yield buf
if maxsplit == 1:
yield [item] + list(it)
return
buf = []
maxsplit -= 1
buf.append(item)
if buf:
yield buf
def split_after(iterable, pred, maxsplit=-1):
"""Yield lists of items from *iterable*, where each list ends with an
item where callable *pred* returns ``True``:
>>> list(split_after('one1two2', lambda s: s.isdigit()))
[['o', 'n', 'e', '1'], ['t', 'w', 'o', '2']]
>>> list(split_after(range(10), lambda n: n % 3 == 0))
[[0], [1, 2, 3], [4, 5, 6], [7, 8, 9]]
At most *maxsplit* splits are done. If *maxsplit* is not specified or -1,
then there is no limit on the number of splits:
>>> list(split_after(range(10), lambda n: n % 3 == 0, maxsplit=2))
[[0], [1, 2, 3], [4, 5, 6, 7, 8, 9]]
"""
if maxsplit == 0:
yield list(iterable)
return
buf = []
it = iter(iterable)
for item in it:
buf.append(item)
if pred(item) and buf:
yield buf
if maxsplit == 1:
buf = list(it)
if buf:
yield buf
return
buf = []
maxsplit -= 1
if buf:
yield buf
def split_when(iterable, pred, maxsplit=-1):
"""Split *iterable* into pieces based on the output of *pred*.
*pred* should be a function that takes successive pairs of items and
returns ``True`` if the iterable should be split in between them.
For example, to find runs of increasing numbers, split the iterable when
element ``i`` is larger than element ``i + 1``:
>>> list(split_when([1, 2, 3, 3, 2, 5, 2, 4, 2], lambda x, y: x > y))
[[1, 2, 3, 3], [2, 5], [2, 4], [2]]
At most *maxsplit* splits are done. If *maxsplit* is not specified or -1,
then there is no limit on the number of splits:
>>> list(split_when([1, 2, 3, 3, 2, 5, 2, 4, 2],
... lambda x, y: x > y, maxsplit=2))
[[1, 2, 3, 3], [2, 5], [2, 4, 2]]
"""
if maxsplit == 0:
yield list(iterable)
return
it = iter(iterable)
try:
cur_item = next(it)
except StopIteration:
return
buf = [cur_item]
for next_item in it:
if pred(cur_item, next_item):
yield buf
if maxsplit == 1:
yield [next_item] + list(it)
return
buf = []
maxsplit -= 1
buf.append(next_item)
cur_item = next_item
yield buf
def split_into(iterable, sizes):
"""Yield a list of sequential items from *iterable* of length 'n' for each
integer 'n' in *sizes*.
>>> list(split_into([1,2,3,4,5,6], [1,2,3]))
[[1], [2, 3], [4, 5, 6]]
If the sum of *sizes* is smaller than the length of *iterable*, then the
remaining items of *iterable* will not be returned.
>>> list(split_into([1,2,3,4,5,6], [2,3]))
[[1, 2], [3, 4, 5]]
If the sum of *sizes* is larger than the length of *iterable*, fewer items
will be returned in the iteration that overruns *iterable* and further
lists will be empty:
>>> list(split_into([1,2,3,4], [1,2,3,4]))
[[1], [2, 3], [4], []]
When a ``None`` object is encountered in *sizes*, the returned list will
contain items up to the end of *iterable* the same way that itertools.slice
does:
>>> list(split_into([1,2,3,4,5,6,7,8,9,0], [2,3,None]))
[[1, 2], [3, 4, 5], [6, 7, 8, 9, 0]]
:func:`split_into` can be useful for grouping a series of items where the
sizes of the groups are not uniform. An example would be where in a row
from a table, multiple columns represent elements of the same feature
(e.g. a point represented by x,y,z) but, the format is not the same for
all columns.
"""
# convert the iterable argument into an iterator so its contents can
# be consumed by islice in case it is a generator
it = iter(iterable)
for size in sizes:
if size is None:
yield list(it)
return
else:
yield list(islice(it, size))
def padded(iterable, fillvalue=None, n=None, next_multiple=False):
"""Yield the elements from *iterable*, followed by *fillvalue*, such that
at least *n* items are emitted.
>>> list(padded([1, 2, 3], '?', 5))
[1, 2, 3, '?', '?']
If *next_multiple* is ``True``, *fillvalue* will be emitted until the
number of items emitted is a multiple of *n*::
>>> list(padded([1, 2, 3, 4], n=3, next_multiple=True))
[1, 2, 3, 4, None, None]
If *n* is ``None``, *fillvalue* will be emitted indefinitely.
"""
it = iter(iterable)
if n is None:
yield from chain(it, repeat(fillvalue))
elif n < 1:
raise ValueError('n must be at least 1')
else:
item_count = 0
for item in it:
yield item
item_count += 1
remaining = (n - item_count) % n if next_multiple else n - item_count
for _ in range(remaining):
yield fillvalue
def repeat_each(iterable, n=2):
"""Repeat each element in *iterable* *n* times.
>>> list(repeat_each('ABC', 3))
['A', 'A', 'A', 'B', 'B', 'B', 'C', 'C', 'C']
"""
return chain.from_iterable(map(repeat, iterable, repeat(n)))
def repeat_last(iterable, default=None):
"""After the *iterable* is exhausted, keep yielding its last element.
>>> list(islice(repeat_last(range(3)), 5))
[0, 1, 2, 2, 2]
If the iterable is empty, yield *default* forever::
>>> list(islice(repeat_last(range(0), 42), 5))
[42, 42, 42, 42, 42]
"""
item = _marker
for item in iterable:
yield item
final = default if item is _marker else item
yield from repeat(final)
def distribute(n, iterable):
"""Distribute the items from *iterable* among *n* smaller iterables.
>>> group_1, group_2 = distribute(2, [1, 2, 3, 4, 5, 6])
>>> list(group_1)
[1, 3, 5]
>>> list(group_2)
[2, 4, 6]
If the length of *iterable* is not evenly divisible by *n*, then the
length of the returned iterables will not be identical:
>>> children = distribute(3, [1, 2, 3, 4, 5, 6, 7])
>>> [list(c) for c in children]
[[1, 4, 7], [2, 5], [3, 6]]
If the length of *iterable* is smaller than *n*, then the last returned
iterables will be empty:
>>> children = distribute(5, [1, 2, 3])
>>> [list(c) for c in children]
[[1], [2], [3], [], []]
This function uses :func:`itertools.tee` and may require significant
storage. If you need the order items in the smaller iterables to match the
original iterable, see :func:`divide`.
"""
if n < 1:
raise ValueError('n must be at least 1')
children = tee(iterable, n)
return [islice(it, index, None, n) for index, it in enumerate(children)]
def stagger(iterable, offsets=(-1, 0, 1), longest=False, fillvalue=None):
"""Yield tuples whose elements are offset from *iterable*.
The amount by which the `i`-th item in each tuple is offset is given by
the `i`-th item in *offsets*.
>>> list(stagger([0, 1, 2, 3]))
[(None, 0, 1), (0, 1, 2), (1, 2, 3)]
>>> list(stagger(range(8), offsets=(0, 2, 4)))
[(0, 2, 4), (1, 3, 5), (2, 4, 6), (3, 5, 7)]
By default, the sequence will end when the final element of a tuple is the
last item in the iterable. To continue until the first element of a tuple
is the last item in the iterable, set *longest* to ``True``::
>>> list(stagger([0, 1, 2, 3], longest=True))
[(None, 0, 1), (0, 1, 2), (1, 2, 3), (2, 3, None), (3, None, None)]
By default, ``None`` will be used to replace offsets beyond the end of the
sequence. Specify *fillvalue* to use some other value.
"""
children = tee(iterable, len(offsets))
return zip_offset(
*children, offsets=offsets, longest=longest, fillvalue=fillvalue
)
def zip_equal(*iterables):
"""``zip`` the input *iterables* together, but raise
``UnequalIterablesError`` if they aren't all the same length.
>>> it_1 = range(3)
>>> it_2 = iter('abc')
>>> list(zip_equal(it_1, it_2))
[(0, 'a'), (1, 'b'), (2, 'c')]
>>> it_1 = range(3)
>>> it_2 = iter('abcd')
>>> list(zip_equal(it_1, it_2)) # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
more_itertools.more.UnequalIterablesError: Iterables have different
lengths
"""
if hexversion >= 0x30A00A6:
warnings.warn(
(
'zip_equal will be removed in a future version of '
'more-itertools. Use the builtin zip function with '
'strict=True instead.'
),
DeprecationWarning,
)
return _zip_equal(*iterables)
def zip_offset(*iterables, offsets, longest=False, fillvalue=None):
"""``zip`` the input *iterables* together, but offset the `i`-th iterable
by the `i`-th item in *offsets*.
>>> list(zip_offset('0123', 'abcdef', offsets=(0, 1)))
[('0', 'b'), ('1', 'c'), ('2', 'd'), ('3', 'e')]
This can be used as a lightweight alternative to SciPy or pandas to analyze
data sets in which some series have a lead or lag relationship.
By default, the sequence will end when the shortest iterable is exhausted.
To continue until the longest iterable is exhausted, set *longest* to
``True``.
>>> list(zip_offset('0123', 'abcdef', offsets=(0, 1), longest=True))
[('0', 'b'), ('1', 'c'), ('2', 'd'), ('3', 'e'), (None, 'f')]
By default, ``None`` will be used to replace offsets beyond the end of the
sequence. Specify *fillvalue* to use some other value.
"""
if len(iterables) != len(offsets):
raise ValueError("Number of iterables and offsets didn't match")
staggered = []
for it, n in zip(iterables, offsets):
if n < 0:
staggered.append(chain(repeat(fillvalue, -n), it))
elif n > 0:
staggered.append(islice(it, n, None))
else:
staggered.append(it)
if longest:
return zip_longest(*staggered, fillvalue=fillvalue)
return zip(*staggered)
def sort_together(iterables, key_list=(0,), key=None, reverse=False):
"""Return the input iterables sorted together, with *key_list* as the
priority for sorting. All iterables are trimmed to the length of the
shortest one.
This can be used like the sorting function in a spreadsheet. If each
iterable represents a column of data, the key list determines which
columns are used for sorting.
By default, all iterables are sorted using the ``0``-th iterable::
>>> iterables = [(4, 3, 2, 1), ('a', 'b', 'c', 'd')]
>>> sort_together(iterables)
[(1, 2, 3, 4), ('d', 'c', 'b', 'a')]
Set a different key list to sort according to another iterable.
Specifying multiple keys dictates how ties are broken::
>>> iterables = [(3, 1, 2), (0, 1, 0), ('c', 'b', 'a')]
>>> sort_together(iterables, key_list=(1, 2))
[(2, 3, 1), (0, 0, 1), ('a', 'c', 'b')]
To sort by a function of the elements of the iterable, pass a *key*
function. Its arguments are the elements of the iterables corresponding to
the key list::
>>> names = ('a', 'b', 'c')
>>> lengths = (1, 2, 3)
>>> widths = (5, 2, 1)
>>> def area(length, width):
... return length * width
>>> sort_together([names, lengths, widths], key_list=(1, 2), key=area)
[('c', 'b', 'a'), (3, 2, 1), (1, 2, 5)]
Set *reverse* to ``True`` to sort in descending order.
>>> sort_together([(1, 2, 3), ('c', 'b', 'a')], reverse=True)
[(3, 2, 1), ('a', 'b', 'c')]
"""
if key is None:
# if there is no key function, the key argument to sorted is an
# itemgetter
key_argument = itemgetter(*key_list)
else:
# if there is a key function, call it with the items at the offsets
# specified by the key function as arguments
key_list = list(key_list)
if len(key_list) == 1:
# if key_list contains a single item, pass the item at that offset
# as the only argument to the key function
key_offset = key_list[0]
key_argument = lambda zipped_items: key(zipped_items[key_offset])
else:
# if key_list contains multiple items, use itemgetter to return a
# tuple of items, which we pass as *args to the key function
get_key_items = itemgetter(*key_list)
key_argument = lambda zipped_items: key(
*get_key_items(zipped_items)
)
return list(
zip(*sorted(zip(*iterables), key=key_argument, reverse=reverse))
)
def unzip(iterable):
"""The inverse of :func:`zip`, this function disaggregates the elements
of the zipped *iterable*.
The ``i``-th iterable contains the ``i``-th element from each element
of the zipped iterable. The first element is used to determine the
length of the remaining elements.
>>> iterable = [('a', 1), ('b', 2), ('c', 3), ('d', 4)]
>>> letters, numbers = unzip(iterable)
>>> list(letters)
['a', 'b', 'c', 'd']
>>> list(numbers)
[1, 2, 3, 4]
This is similar to using ``zip(*iterable)``, but it avoids reading
*iterable* into memory. Note, however, that this function uses
:func:`itertools.tee` and thus may require significant storage.
"""
head, iterable = spy(iter(iterable))
if not head:
# empty iterable, e.g. zip([], [], [])
return ()
# spy returns a one-length iterable as head
head = head[0]
iterables = tee(iterable, len(head))
def itemgetter(i):
def getter(obj):
try:
return obj[i]
except IndexError:
# basically if we have an iterable like
# iter([(1, 2, 3), (4, 5), (6,)])
# the second unzipped iterable would fail at the third tuple
# since it would try to access tup[1]
# same with the third unzipped iterable and the second tuple
# to support these "improperly zipped" iterables,
# we create a custom itemgetter
# which just stops the unzipped iterables
# at first length mismatch
raise StopIteration
return getter
return tuple(map(itemgetter(i), it) for i, it in enumerate(iterables))
def divide(n, iterable):
"""Divide the elements from *iterable* into *n* parts, maintaining
order.
>>> group_1, group_2 = divide(2, [1, 2, 3, 4, 5, 6])
>>> list(group_1)
[1, 2, 3]
>>> list(group_2)
[4, 5, 6]
If the length of *iterable* is not evenly divisible by *n*, then the
length of the returned iterables will not be identical:
>>> children = divide(3, [1, 2, 3, 4, 5, 6, 7])
>>> [list(c) for c in children]
[[1, 2, 3], [4, 5], [6, 7]]
If the length of the iterable is smaller than n, then the last returned
iterables will be empty:
>>> children = divide(5, [1, 2, 3])
>>> [list(c) for c in children]
[[1], [2], [3], [], []]
This function will exhaust the iterable before returning and may require
significant storage. If order is not important, see :func:`distribute`,
which does not first pull the iterable into memory.
"""
if n < 1:
raise ValueError('n must be at least 1')
try:
iterable[:0]
except TypeError:
seq = tuple(iterable)
else:
seq = iterable
q, r = divmod(len(seq), n)
ret = []
stop = 0
for i in range(1, n + 1):
start = stop
stop += q + 1 if i <= r else q
ret.append(iter(seq[start:stop]))
return ret
def always_iterable(obj, base_type=(str, bytes)):
"""If *obj* is iterable, return an iterator over its items::
>>> obj = (1, 2, 3)
>>> list(always_iterable(obj))
[1, 2, 3]
If *obj* is not iterable, return a one-item iterable containing *obj*::
>>> obj = 1
>>> list(always_iterable(obj))
[1]
If *obj* is ``None``, return an empty iterable:
>>> obj = None
>>> list(always_iterable(None))
[]
By default, binary and text strings are not considered iterable::
>>> obj = 'foo'
>>> list(always_iterable(obj))
['foo']
If *base_type* is set, objects for which ``isinstance(obj, base_type)``
returns ``True`` won't be considered iterable.
>>> obj = {'a': 1}
>>> list(always_iterable(obj)) # Iterate over the dict's keys
['a']
>>> list(always_iterable(obj, base_type=dict)) # Treat dicts as a unit
[{'a': 1}]
Set *base_type* to ``None`` to avoid any special handling and treat objects
Python considers iterable as iterable:
>>> obj = 'foo'
>>> list(always_iterable(obj, base_type=None))
['f', 'o', 'o']
"""
if obj is None:
return iter(())
if (base_type is not None) and isinstance(obj, base_type):
return iter((obj,))
try:
return iter(obj)
except TypeError:
return iter((obj,))
def adjacent(predicate, iterable, distance=1):
"""Return an iterable over `(bool, item)` tuples where the `item` is
drawn from *iterable* and the `bool` indicates whether
that item satisfies the *predicate* or is adjacent to an item that does.
For example, to find whether items are adjacent to a ``3``::
>>> list(adjacent(lambda x: x == 3, range(6)))
[(False, 0), (False, 1), (True, 2), (True, 3), (True, 4), (False, 5)]
Set *distance* to change what counts as adjacent. For example, to find
whether items are two places away from a ``3``:
>>> list(adjacent(lambda x: x == 3, range(6), distance=2))
[(False, 0), (True, 1), (True, 2), (True, 3), (True, 4), (True, 5)]
This is useful for contextualizing the results of a search function.
For example, a code comparison tool might want to identify lines that
have changed, but also surrounding lines to give the viewer of the diff
context.
The predicate function will only be called once for each item in the
iterable.
See also :func:`groupby_transform`, which can be used with this function
to group ranges of items with the same `bool` value.
"""
# Allow distance=0 mainly for testing that it reproduces results with map()
if distance < 0:
raise ValueError('distance must be at least 0')
i1, i2 = tee(iterable)
padding = [False] * distance
selected = chain(padding, map(predicate, i1), padding)
adjacent_to_selected = map(any, windowed(selected, 2 * distance + 1))
return zip(adjacent_to_selected, i2)
def groupby_transform(iterable, keyfunc=None, valuefunc=None, reducefunc=None):
"""An extension of :func:`itertools.groupby` that can apply transformations
to the grouped data.
* *keyfunc* is a function computing a key value for each item in *iterable*
* *valuefunc* is a function that transforms the individual items from
*iterable* after grouping
* *reducefunc* is a function that transforms each group of items
>>> iterable = 'aAAbBBcCC'
>>> keyfunc = lambda k: k.upper()
>>> valuefunc = lambda v: v.lower()
>>> reducefunc = lambda g: ''.join(g)
>>> list(groupby_transform(iterable, keyfunc, valuefunc, reducefunc))
[('A', 'aaa'), ('B', 'bbb'), ('C', 'ccc')]
Each optional argument defaults to an identity function if not specified.
:func:`groupby_transform` is useful when grouping elements of an iterable
using a separate iterable as the key. To do this, :func:`zip` the iterables
and pass a *keyfunc* that extracts the first element and a *valuefunc*
that extracts the second element::
>>> from operator import itemgetter
>>> keys = [0, 0, 1, 1, 1, 2, 2, 2, 3]
>>> values = 'abcdefghi'
>>> iterable = zip(keys, values)
>>> grouper = groupby_transform(iterable, itemgetter(0), itemgetter(1))
>>> [(k, ''.join(g)) for k, g in grouper]
[(0, 'ab'), (1, 'cde'), (2, 'fgh'), (3, 'i')]
Note that the order of items in the iterable is significant.
Only adjacent items are grouped together, so if you don't want any
duplicate groups, you should sort the iterable by the key function.
"""
ret = groupby(iterable, keyfunc)
if valuefunc:
ret = ((k, map(valuefunc, g)) for k, g in ret)
if reducefunc:
ret = ((k, reducefunc(g)) for k, g in ret)
return ret
class numeric_range(abc.Sequence, abc.Hashable):
"""An extension of the built-in ``range()`` function whose arguments can
be any orderable numeric type.
With only *stop* specified, *start* defaults to ``0`` and *step*
defaults to ``1``. The output items will match the type of *stop*:
>>> list(numeric_range(3.5))
[0.0, 1.0, 2.0, 3.0]
With only *start* and *stop* specified, *step* defaults to ``1``. The
output items will match the type of *start*:
>>> from decimal import Decimal
>>> start = Decimal('2.1')
>>> stop = Decimal('5.1')
>>> list(numeric_range(start, stop))
[Decimal('2.1'), Decimal('3.1'), Decimal('4.1')]
With *start*, *stop*, and *step* specified the output items will match
the type of ``start + step``:
>>> from fractions import Fraction
>>> start = Fraction(1, 2) # Start at 1/2
>>> stop = Fraction(5, 2) # End at 5/2
>>> step = Fraction(1, 2) # Count by 1/2
>>> list(numeric_range(start, stop, step))
[Fraction(1, 2), Fraction(1, 1), Fraction(3, 2), Fraction(2, 1)]
If *step* is zero, ``ValueError`` is raised. Negative steps are supported:
>>> list(numeric_range(3, -1, -1.0))
[3.0, 2.0, 1.0, 0.0]
Be aware of the limitations of floating point numbers; the representation
of the yielded numbers may be surprising.
``datetime.datetime`` objects can be used for *start* and *stop*, if *step*
is a ``datetime.timedelta`` object:
>>> import datetime
>>> start = datetime.datetime(2019, 1, 1)
>>> stop = datetime.datetime(2019, 1, 3)
>>> step = datetime.timedelta(days=1)
>>> items = iter(numeric_range(start, stop, step))
>>> next(items)
datetime.datetime(2019, 1, 1, 0, 0)
>>> next(items)
datetime.datetime(2019, 1, 2, 0, 0)
"""
_EMPTY_HASH = hash(range(0, 0))
def __init__(self, *args):
argc = len(args)
if argc == 1:
(self._stop,) = args
self._start = type(self._stop)(0)
self._step = type(self._stop - self._start)(1)
elif argc == 2:
self._start, self._stop = args
self._step = type(self._stop - self._start)(1)
elif argc == 3:
self._start, self._stop, self._step = args
elif argc == 0:
raise TypeError(
'numeric_range expected at least '
'1 argument, got {}'.format(argc)
)
else:
raise TypeError(
'numeric_range expected at most '
'3 arguments, got {}'.format(argc)
)
self._zero = type(self._step)(0)
if self._step == self._zero:
raise ValueError('numeric_range() arg 3 must not be zero')
self._growing = self._step > self._zero
def __bool__(self):
if self._growing:
return self._start < self._stop
else:
return self._start > self._stop
def __contains__(self, elem):
if self._growing:
if self._start <= elem < self._stop:
return (elem - self._start) % self._step == self._zero
else:
if self._start >= elem > self._stop:
return (self._start - elem) % (-self._step) == self._zero
return False
def __eq__(self, other):
if isinstance(other, numeric_range):
empty_self = not bool(self)
empty_other = not bool(other)
if empty_self or empty_other:
return empty_self and empty_other # True if both empty
else:
return (
self._start == other._start
and self._step == other._step
and self._get_by_index(-1) == other._get_by_index(-1)
)
else:
return False
def __getitem__(self, key):
if isinstance(key, int):
return self._get_by_index(key)
elif isinstance(key, slice):
step = self._step if key.step is None else key.step * self._step
if key.start is None or key.start <= -self._len:
start = self._start
elif key.start >= self._len:
start = self._stop
else: # -self._len < key.start < self._len
start = self._get_by_index(key.start)
if key.stop is None or key.stop >= self._len:
stop = self._stop
elif key.stop <= -self._len:
stop = self._start
else: # -self._len < key.stop < self._len
stop = self._get_by_index(key.stop)
return numeric_range(start, stop, step)
else:
raise TypeError(
'numeric range indices must be '
'integers or slices, not {}'.format(type(key).__name__)
)
def __hash__(self):
if self:
return hash((self._start, self._get_by_index(-1), self._step))
else:
return self._EMPTY_HASH
def __iter__(self):
values = (self._start + (n * self._step) for n in count())
if self._growing:
return takewhile(partial(gt, self._stop), values)
else:
return takewhile(partial(lt, self._stop), values)
def __len__(self):
return self._len
@cached_property
def _len(self):
if self._growing:
start = self._start
stop = self._stop
step = self._step
else:
start = self._stop
stop = self._start
step = -self._step
distance = stop - start
if distance <= self._zero:
return 0
else: # distance > 0 and step > 0: regular euclidean division
q, r = divmod(distance, step)
return int(q) + int(r != self._zero)
def __reduce__(self):
return numeric_range, (self._start, self._stop, self._step)
def __repr__(self):
if self._step == 1:
return "numeric_range({}, {})".format(
repr(self._start), repr(self._stop)
)
else:
return "numeric_range({}, {}, {})".format(
repr(self._start), repr(self._stop), repr(self._step)
)
def __reversed__(self):
return iter(
numeric_range(
self._get_by_index(-1), self._start - self._step, -self._step
)
)
def count(self, value):
return int(value in self)
def index(self, value):
if self._growing:
if self._start <= value < self._stop:
q, r = divmod(value - self._start, self._step)
if r == self._zero:
return int(q)
else:
if self._start >= value > self._stop:
q, r = divmod(self._start - value, -self._step)
if r == self._zero:
return int(q)
raise ValueError("{} is not in numeric range".format(value))
def _get_by_index(self, i):
if i < 0:
i += self._len
if i < 0 or i >= self._len:
raise IndexError("numeric range object index out of range")
return self._start + i * self._step
def count_cycle(iterable, n=None):
"""Cycle through the items from *iterable* up to *n* times, yielding
the number of completed cycles along with each item. If *n* is omitted the
process repeats indefinitely.
>>> list(count_cycle('AB', 3))
[(0, 'A'), (0, 'B'), (1, 'A'), (1, 'B'), (2, 'A'), (2, 'B')]
"""
iterable = tuple(iterable)
if not iterable:
return iter(())
counter = count() if n is None else range(n)
return ((i, item) for i in counter for item in iterable)
def mark_ends(iterable):
"""Yield 3-tuples of the form ``(is_first, is_last, item)``.
>>> list(mark_ends('ABC'))
[(True, False, 'A'), (False, False, 'B'), (False, True, 'C')]
Use this when looping over an iterable to take special action on its first
and/or last items:
>>> iterable = ['Header', 100, 200, 'Footer']
>>> total = 0
>>> for is_first, is_last, item in mark_ends(iterable):
... if is_first:
... continue # Skip the header
... if is_last:
... continue # Skip the footer
... total += item
>>> print(total)
300
"""
it = iter(iterable)
try:
b = next(it)
except StopIteration:
return
try:
for i in count():
a = b
b = next(it)
yield i == 0, False, a
except StopIteration:
yield i == 0, True, a
def locate(iterable, pred=bool, window_size=None):
"""Yield the index of each item in *iterable* for which *pred* returns
``True``.
*pred* defaults to :func:`bool`, which will select truthy items:
>>> list(locate([0, 1, 1, 0, 1, 0, 0]))
[1, 2, 4]
Set *pred* to a custom function to, e.g., find the indexes for a particular
item.
>>> list(locate(['a', 'b', 'c', 'b'], lambda x: x == 'b'))
[1, 3]
If *window_size* is given, then the *pred* function will be called with
that many items. This enables searching for sub-sequences:
>>> iterable = [0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3]
>>> pred = lambda *args: args == (1, 2, 3)
>>> list(locate(iterable, pred=pred, window_size=3))
[1, 5, 9]
Use with :func:`seekable` to find indexes and then retrieve the associated
items:
>>> from itertools import count
>>> from more_itertools import seekable
>>> source = (3 * n + 1 if (n % 2) else n // 2 for n in count())
>>> it = seekable(source)
>>> pred = lambda x: x > 100
>>> indexes = locate(it, pred=pred)
>>> i = next(indexes)
>>> it.seek(i)
>>> next(it)
106
"""
if window_size is None:
return compress(count(), map(pred, iterable))
if window_size < 1:
raise ValueError('window size must be at least 1')
it = windowed(iterable, window_size, fillvalue=_marker)
return compress(count(), starmap(pred, it))
def longest_common_prefix(iterables):
"""Yield elements of the longest common prefix amongst given *iterables*.
>>> ''.join(longest_common_prefix(['abcd', 'abc', 'abf']))
'ab'
"""
return (c[0] for c in takewhile(all_equal, zip(*iterables)))
def lstrip(iterable, pred):
"""Yield the items from *iterable*, but strip any from the beginning
for which *pred* returns ``True``.
For example, to remove a set of items from the start of an iterable:
>>> iterable = (None, False, None, 1, 2, None, 3, False, None)
>>> pred = lambda x: x in {None, False, ''}
>>> list(lstrip(iterable, pred))
[1, 2, None, 3, False, None]
This function is analogous to to :func:`str.lstrip`, and is essentially
an wrapper for :func:`itertools.dropwhile`.
"""
return dropwhile(pred, iterable)
def rstrip(iterable, pred):
"""Yield the items from *iterable*, but strip any from the end
for which *pred* returns ``True``.
For example, to remove a set of items from the end of an iterable:
>>> iterable = (None, False, None, 1, 2, None, 3, False, None)
>>> pred = lambda x: x in {None, False, ''}
>>> list(rstrip(iterable, pred))
[None, False, None, 1, 2, None, 3]
This function is analogous to :func:`str.rstrip`.
"""
cache = []
cache_append = cache.append
cache_clear = cache.clear
for x in iterable:
if pred(x):
cache_append(x)
else:
yield from cache
cache_clear()
yield x
def strip(iterable, pred):
"""Yield the items from *iterable*, but strip any from the
beginning and end for which *pred* returns ``True``.
For example, to remove a set of items from both ends of an iterable:
>>> iterable = (None, False, None, 1, 2, None, 3, False, None)
>>> pred = lambda x: x in {None, False, ''}
>>> list(strip(iterable, pred))
[1, 2, None, 3]
This function is analogous to :func:`str.strip`.
"""
return rstrip(lstrip(iterable, pred), pred)
class islice_extended:
"""An extension of :func:`itertools.islice` that supports negative values
for *stop*, *start*, and *step*.
>>> iterable = iter('abcdefgh')
>>> list(islice_extended(iterable, -4, -1))
['e', 'f', 'g']
Slices with negative values require some caching of *iterable*, but this
function takes care to minimize the amount of memory required.
For example, you can use a negative step with an infinite iterator:
>>> from itertools import count
>>> list(islice_extended(count(), 110, 99, -2))
[110, 108, 106, 104, 102, 100]
You can also use slice notation directly:
>>> iterable = map(str, count())
>>> it = islice_extended(iterable)[10:20:2]
>>> list(it)
['10', '12', '14', '16', '18']
"""
def __init__(self, iterable, *args):
it = iter(iterable)
if args:
self._iterable = _islice_helper(it, slice(*args))
else:
self._iterable = it
def __iter__(self):
return self
def __next__(self):
return next(self._iterable)
def __getitem__(self, key):
if isinstance(key, slice):
return islice_extended(_islice_helper(self._iterable, key))
raise TypeError('islice_extended.__getitem__ argument must be a slice')
def _islice_helper(it, s):
start = s.start
stop = s.stop
if s.step == 0:
raise ValueError('step argument must be a non-zero integer or None.')
step = s.step or 1
if step > 0:
start = 0 if (start is None) else start
if start < 0:
# Consume all but the last -start items
cache = deque(enumerate(it, 1), maxlen=-start)
len_iter = cache[-1][0] if cache else 0
# Adjust start to be positive
i = max(len_iter + start, 0)
# Adjust stop to be positive
if stop is None:
j = len_iter
elif stop >= 0:
j = min(stop, len_iter)
else:
j = max(len_iter + stop, 0)
# Slice the cache
n = j - i
if n <= 0:
return
for index, item in islice(cache, 0, n, step):
yield item
elif (stop is not None) and (stop < 0):
# Advance to the start position
next(islice(it, start, start), None)
# When stop is negative, we have to carry -stop items while
# iterating
cache = deque(islice(it, -stop), maxlen=-stop)
for index, item in enumerate(it):
cached_item = cache.popleft()
if index % step == 0:
yield cached_item
cache.append(item)
else:
# When both start and stop are positive we have the normal case
yield from islice(it, start, stop, step)
else:
start = -1 if (start is None) else start
if (stop is not None) and (stop < 0):
# Consume all but the last items
n = -stop - 1
cache = deque(enumerate(it, 1), maxlen=n)
len_iter = cache[-1][0] if cache else 0
# If start and stop are both negative they are comparable and
# we can just slice. Otherwise we can adjust start to be negative
# and then slice.
if start < 0:
i, j = start, stop
else:
i, j = min(start - len_iter, -1), None
for index, item in list(cache)[i:j:step]:
yield item
else:
# Advance to the stop position
if stop is not None:
m = stop + 1
next(islice(it, m, m), None)
# stop is positive, so if start is negative they are not comparable
# and we need the rest of the items.
if start < 0:
i = start
n = None
# stop is None and start is positive, so we just need items up to
# the start index.
elif stop is None:
i = None
n = start + 1
# Both stop and start are positive, so they are comparable.
else:
i = None
n = start - stop
if n <= 0:
return
cache = list(islice(it, n))
yield from cache[i::step]
def always_reversible(iterable):
"""An extension of :func:`reversed` that supports all iterables, not
just those which implement the ``Reversible`` or ``Sequence`` protocols.
>>> print(*always_reversible(x for x in range(3)))
2 1 0
If the iterable is already reversible, this function returns the
result of :func:`reversed()`. If the iterable is not reversible,
this function will cache the remaining items in the iterable and
yield them in reverse order, which may require significant storage.
"""
try:
return reversed(iterable)
except TypeError:
return reversed(list(iterable))
def consecutive_groups(iterable, ordering=lambda x: x):
"""Yield groups of consecutive items using :func:`itertools.groupby`.
The *ordering* function determines whether two items are adjacent by
returning their position.
By default, the ordering function is the identity function. This is
suitable for finding runs of numbers:
>>> iterable = [1, 10, 11, 12, 20, 30, 31, 32, 33, 40]
>>> for group in consecutive_groups(iterable):
... print(list(group))
[1]
[10, 11, 12]
[20]
[30, 31, 32, 33]
[40]
For finding runs of adjacent letters, try using the :meth:`index` method
of a string of letters:
>>> from string import ascii_lowercase
>>> iterable = 'abcdfgilmnop'
>>> ordering = ascii_lowercase.index
>>> for group in consecutive_groups(iterable, ordering):
... print(list(group))
['a', 'b', 'c', 'd']
['f', 'g']
['i']
['l', 'm', 'n', 'o', 'p']
Each group of consecutive items is an iterator that shares it source with
*iterable*. When an an output group is advanced, the previous group is
no longer available unless its elements are copied (e.g., into a ``list``).
>>> iterable = [1, 2, 11, 12, 21, 22]
>>> saved_groups = []
>>> for group in consecutive_groups(iterable):
... saved_groups.append(list(group)) # Copy group elements
>>> saved_groups
[[1, 2], [11, 12], [21, 22]]
"""
for k, g in groupby(
enumerate(iterable), key=lambda x: x[0] - ordering(x[1])
):
yield map(itemgetter(1), g)
def difference(iterable, func=sub, *, initial=None):
"""This function is the inverse of :func:`itertools.accumulate`. By default
it will compute the first difference of *iterable* using
:func:`operator.sub`:
>>> from itertools import accumulate
>>> iterable = accumulate([0, 1, 2, 3, 4]) # produces 0, 1, 3, 6, 10
>>> list(difference(iterable))
[0, 1, 2, 3, 4]
*func* defaults to :func:`operator.sub`, but other functions can be
specified. They will be applied as follows::
A, B, C, D, ... --> A, func(B, A), func(C, B), func(D, C), ...
For example, to do progressive division:
>>> iterable = [1, 2, 6, 24, 120]
>>> func = lambda x, y: x // y
>>> list(difference(iterable, func))
[1, 2, 3, 4, 5]
If the *initial* keyword is set, the first element will be skipped when
computing successive differences.
>>> it = [10, 11, 13, 16] # from accumulate([1, 2, 3], initial=10)
>>> list(difference(it, initial=10))
[1, 2, 3]
"""
a, b = tee(iterable)
try:
first = [next(b)]
except StopIteration:
return iter([])
if initial is not None:
first = []
return chain(first, map(func, b, a))
class SequenceView(Sequence):
"""Return a read-only view of the sequence object *target*.
:class:`SequenceView` objects are analogous to Python's built-in
"dictionary view" types. They provide a dynamic view of a sequence's items,
meaning that when the sequence updates, so does the view.
>>> seq = ['0', '1', '2']
>>> view = SequenceView(seq)
>>> view
SequenceView(['0', '1', '2'])
>>> seq.append('3')
>>> view
SequenceView(['0', '1', '2', '3'])
Sequence views support indexing, slicing, and length queries. They act
like the underlying sequence, except they don't allow assignment:
>>> view[1]
'1'
>>> view[1:-1]
['1', '2']
>>> len(view)
4
Sequence views are useful as an alternative to copying, as they don't
require (much) extra storage.
"""
def __init__(self, target):
if not isinstance(target, Sequence):
raise TypeError
self._target = target
def __getitem__(self, index):
return self._target[index]
def __len__(self):
return len(self._target)
def __repr__(self):
return '{}({})'.format(self.__class__.__name__, repr(self._target))
class seekable:
"""Wrap an iterator to allow for seeking backward and forward. This
progressively caches the items in the source iterable so they can be
re-visited.
Call :meth:`seek` with an index to seek to that position in the source
iterable.
To "reset" an iterator, seek to ``0``:
>>> from itertools import count
>>> it = seekable((str(n) for n in count()))
>>> next(it), next(it), next(it)
('0', '1', '2')
>>> it.seek(0)
>>> next(it), next(it), next(it)
('0', '1', '2')
>>> next(it)
'3'
You can also seek forward:
>>> it = seekable((str(n) for n in range(20)))
>>> it.seek(10)
>>> next(it)
'10'
>>> it.relative_seek(-2) # Seeking relative to the current position
>>> next(it)
'9'
>>> it.seek(20) # Seeking past the end of the source isn't a problem
>>> list(it)
[]
>>> it.seek(0) # Resetting works even after hitting the end
>>> next(it), next(it), next(it)
('0', '1', '2')
Call :meth:`peek` to look ahead one item without advancing the iterator:
>>> it = seekable('1234')
>>> it.peek()
'1'
>>> list(it)
['1', '2', '3', '4']
>>> it.peek(default='empty')
'empty'
Before the iterator is at its end, calling :func:`bool` on it will return
``True``. After it will return ``False``:
>>> it = seekable('5678')
>>> bool(it)
True
>>> list(it)
['5', '6', '7', '8']
>>> bool(it)
False
You may view the contents of the cache with the :meth:`elements` method.
That returns a :class:`SequenceView`, a view that updates automatically:
>>> it = seekable((str(n) for n in range(10)))
>>> next(it), next(it), next(it)
('0', '1', '2')
>>> elements = it.elements()
>>> elements
SequenceView(['0', '1', '2'])
>>> next(it)
'3'
>>> elements
SequenceView(['0', '1', '2', '3'])
By default, the cache grows as the source iterable progresses, so beware of
wrapping very large or infinite iterables. Supply *maxlen* to limit the
size of the cache (this of course limits how far back you can seek).
>>> from itertools import count
>>> it = seekable((str(n) for n in count()), maxlen=2)
>>> next(it), next(it), next(it), next(it)
('0', '1', '2', '3')
>>> list(it.elements())
['2', '3']
>>> it.seek(0)
>>> next(it), next(it), next(it), next(it)
('2', '3', '4', '5')
>>> next(it)
'6'
"""
def __init__(self, iterable, maxlen=None):
self._source = iter(iterable)
if maxlen is None:
self._cache = []
else:
self._cache = deque([], maxlen)
self._index = None
def __iter__(self):
return self
def __next__(self):
if self._index is not None:
try:
item = self._cache[self._index]
except IndexError:
self._index = None
else:
self._index += 1
return item
item = next(self._source)
self._cache.append(item)
return item
def __bool__(self):
try:
self.peek()
except StopIteration:
return False
return True
def peek(self, default=_marker):
try:
peeked = next(self)
except StopIteration:
if default is _marker:
raise
return default
if self._index is None:
self._index = len(self._cache)
self._index -= 1
return peeked
def elements(self):
return SequenceView(self._cache)
def seek(self, index):
self._index = index
remainder = index - len(self._cache)
if remainder > 0:
consume(self, remainder)
def relative_seek(self, count):
index = len(self._cache)
self.seek(max(index + count, 0))
class run_length:
"""
:func:`run_length.encode` compresses an iterable with run-length encoding.
It yields groups of repeated items with the count of how many times they
were repeated:
>>> uncompressed = 'abbcccdddd'
>>> list(run_length.encode(uncompressed))
[('a', 1), ('b', 2), ('c', 3), ('d', 4)]
:func:`run_length.decode` decompresses an iterable that was previously
compressed with run-length encoding. It yields the items of the
decompressed iterable:
>>> compressed = [('a', 1), ('b', 2), ('c', 3), ('d', 4)]
>>> list(run_length.decode(compressed))
['a', 'b', 'b', 'c', 'c', 'c', 'd', 'd', 'd', 'd']
"""
@staticmethod
def encode(iterable):
return ((k, ilen(g)) for k, g in groupby(iterable))
@staticmethod
def decode(iterable):
return chain.from_iterable(repeat(k, n) for k, n in iterable)
def exactly_n(iterable, n, predicate=bool):
"""Return ``True`` if exactly ``n`` items in the iterable are ``True``
according to the *predicate* function.
>>> exactly_n([True, True, False], 2)
True
>>> exactly_n([True, True, False], 1)
False
>>> exactly_n([0, 1, 2, 3, 4, 5], 3, lambda x: x < 3)
True
The iterable will be advanced until ``n + 1`` truthy items are encountered,
so avoid calling it on infinite iterables.
"""
return len(take(n + 1, filter(predicate, iterable))) == n
def circular_shifts(iterable):
"""Return a list of circular shifts of *iterable*.
>>> circular_shifts(range(4))
[(0, 1, 2, 3), (1, 2, 3, 0), (2, 3, 0, 1), (3, 0, 1, 2)]
"""
lst = list(iterable)
return take(len(lst), windowed(cycle(lst), len(lst)))
def make_decorator(wrapping_func, result_index=0):
"""Return a decorator version of *wrapping_func*, which is a function that
modifies an iterable. *result_index* is the position in that function's
signature where the iterable goes.
This lets you use itertools on the "production end," i.e. at function
definition. This can augment what the function returns without changing the
function's code.
For example, to produce a decorator version of :func:`chunked`:
>>> from more_itertools import chunked
>>> chunker = make_decorator(chunked, result_index=0)
>>> @chunker(3)
... def iter_range(n):
... return iter(range(n))
...
>>> list(iter_range(9))
[[0, 1, 2], [3, 4, 5], [6, 7, 8]]
To only allow truthy items to be returned:
>>> truth_serum = make_decorator(filter, result_index=1)
>>> @truth_serum(bool)
... def boolean_test():
... return [0, 1, '', ' ', False, True]
...
>>> list(boolean_test())
[1, ' ', True]
The :func:`peekable` and :func:`seekable` wrappers make for practical
decorators:
>>> from more_itertools import peekable
>>> peekable_function = make_decorator(peekable)
>>> @peekable_function()
... def str_range(*args):
... return (str(x) for x in range(*args))
...
>>> it = str_range(1, 20, 2)
>>> next(it), next(it), next(it)
('1', '3', '5')
>>> it.peek()
'7'
>>> next(it)
'7'
"""
# See https://sites.google.com/site/bbayles/index/decorator_factory for
# notes on how this works.
def decorator(*wrapping_args, **wrapping_kwargs):
def outer_wrapper(f):
def inner_wrapper(*args, **kwargs):
result = f(*args, **kwargs)
wrapping_args_ = list(wrapping_args)
wrapping_args_.insert(result_index, result)
return wrapping_func(*wrapping_args_, **wrapping_kwargs)
return inner_wrapper
return outer_wrapper
return decorator
def map_reduce(iterable, keyfunc, valuefunc=None, reducefunc=None):
"""Return a dictionary that maps the items in *iterable* to categories
defined by *keyfunc*, transforms them with *valuefunc*, and
then summarizes them by category with *reducefunc*.
*valuefunc* defaults to the identity function if it is unspecified.
If *reducefunc* is unspecified, no summarization takes place:
>>> keyfunc = lambda x: x.upper()
>>> result = map_reduce('abbccc', keyfunc)
>>> sorted(result.items())
[('A', ['a']), ('B', ['b', 'b']), ('C', ['c', 'c', 'c'])]
Specifying *valuefunc* transforms the categorized items:
>>> keyfunc = lambda x: x.upper()
>>> valuefunc = lambda x: 1
>>> result = map_reduce('abbccc', keyfunc, valuefunc)
>>> sorted(result.items())
[('A', [1]), ('B', [1, 1]), ('C', [1, 1, 1])]
Specifying *reducefunc* summarizes the categorized items:
>>> keyfunc = lambda x: x.upper()
>>> valuefunc = lambda x: 1
>>> reducefunc = sum
>>> result = map_reduce('abbccc', keyfunc, valuefunc, reducefunc)
>>> sorted(result.items())
[('A', 1), ('B', 2), ('C', 3)]
You may want to filter the input iterable before applying the map/reduce
procedure:
>>> all_items = range(30)
>>> items = [x for x in all_items if 10 <= x <= 20] # Filter
>>> keyfunc = lambda x: x % 2 # Evens map to 0; odds to 1
>>> categories = map_reduce(items, keyfunc=keyfunc)
>>> sorted(categories.items())
[(0, [10, 12, 14, 16, 18, 20]), (1, [11, 13, 15, 17, 19])]
>>> summaries = map_reduce(items, keyfunc=keyfunc, reducefunc=sum)
>>> sorted(summaries.items())
[(0, 90), (1, 75)]
Note that all items in the iterable are gathered into a list before the
summarization step, which may require significant storage.
The returned object is a :obj:`collections.defaultdict` with the
``default_factory`` set to ``None``, such that it behaves like a normal
dictionary.
"""
valuefunc = (lambda x: x) if (valuefunc is None) else valuefunc
ret = defaultdict(list)
for item in iterable:
key = keyfunc(item)
value = valuefunc(item)
ret[key].append(value)
if reducefunc is not None:
for key, value_list in ret.items():
ret[key] = reducefunc(value_list)
ret.default_factory = None
return ret
def rlocate(iterable, pred=bool, window_size=None):
"""Yield the index of each item in *iterable* for which *pred* returns
``True``, starting from the right and moving left.
*pred* defaults to :func:`bool`, which will select truthy items:
>>> list(rlocate([0, 1, 1, 0, 1, 0, 0])) # Truthy at 1, 2, and 4
[4, 2, 1]
Set *pred* to a custom function to, e.g., find the indexes for a particular
item:
>>> iterable = iter('abcb')
>>> pred = lambda x: x == 'b'
>>> list(rlocate(iterable, pred))
[3, 1]
If *window_size* is given, then the *pred* function will be called with
that many items. This enables searching for sub-sequences:
>>> iterable = [0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3]
>>> pred = lambda *args: args == (1, 2, 3)
>>> list(rlocate(iterable, pred=pred, window_size=3))
[9, 5, 1]
Beware, this function won't return anything for infinite iterables.
If *iterable* is reversible, ``rlocate`` will reverse it and search from
the right. Otherwise, it will search from the left and return the results
in reverse order.
See :func:`locate` to for other example applications.
"""
if window_size is None:
try:
len_iter = len(iterable)
return (len_iter - i - 1 for i in locate(reversed(iterable), pred))
except TypeError:
pass
return reversed(list(locate(iterable, pred, window_size)))
def replace(iterable, pred, substitutes, count=None, window_size=1):
"""Yield the items from *iterable*, replacing the items for which *pred*
returns ``True`` with the items from the iterable *substitutes*.
>>> iterable = [1, 1, 0, 1, 1, 0, 1, 1]
>>> pred = lambda x: x == 0
>>> substitutes = (2, 3)
>>> list(replace(iterable, pred, substitutes))
[1, 1, 2, 3, 1, 1, 2, 3, 1, 1]
If *count* is given, the number of replacements will be limited:
>>> iterable = [1, 1, 0, 1, 1, 0, 1, 1, 0]
>>> pred = lambda x: x == 0
>>> substitutes = [None]
>>> list(replace(iterable, pred, substitutes, count=2))
[1, 1, None, 1, 1, None, 1, 1, 0]
Use *window_size* to control the number of items passed as arguments to
*pred*. This allows for locating and replacing subsequences.
>>> iterable = [0, 1, 2, 5, 0, 1, 2, 5]
>>> window_size = 3
>>> pred = lambda *args: args == (0, 1, 2) # 3 items passed to pred
>>> substitutes = [3, 4] # Splice in these items
>>> list(replace(iterable, pred, substitutes, window_size=window_size))
[3, 4, 5, 3, 4, 5]
"""
if window_size < 1:
raise ValueError('window_size must be at least 1')
# Save the substitutes iterable, since it's used more than once
substitutes = tuple(substitutes)
# Add padding such that the number of windows matches the length of the
# iterable
it = chain(iterable, [_marker] * (window_size - 1))
windows = windowed(it, window_size)
n = 0
for w in windows:
# If the current window matches our predicate (and we haven't hit
# our maximum number of replacements), splice in the substitutes
# and then consume the following windows that overlap with this one.
# For example, if the iterable is (0, 1, 2, 3, 4...)
# and the window size is 2, we have (0, 1), (1, 2), (2, 3)...
# If the predicate matches on (0, 1), we need to zap (0, 1) and (1, 2)
if pred(*w):
if (count is None) or (n < count):
n += 1
yield from substitutes
consume(windows, window_size - 1)
continue
# If there was no match (or we've reached the replacement limit),
# yield the first item from the window.
if w and (w[0] is not _marker):
yield w[0]
def partitions(iterable):
"""Yield all possible order-preserving partitions of *iterable*.
>>> iterable = 'abc'
>>> for part in partitions(iterable):
... print([''.join(p) for p in part])
['abc']
['a', 'bc']
['ab', 'c']
['a', 'b', 'c']
This is unrelated to :func:`partition`.
"""
sequence = list(iterable)
n = len(sequence)
for i in powerset(range(1, n)):
yield [sequence[i:j] for i, j in zip((0,) + i, i + (n,))]
def set_partitions(iterable, k=None):
"""
Yield the set partitions of *iterable* into *k* parts. Set partitions are
not order-preserving.
>>> iterable = 'abc'
>>> for part in set_partitions(iterable, 2):
... print([''.join(p) for p in part])
['a', 'bc']
['ab', 'c']
['b', 'ac']
If *k* is not given, every set partition is generated.
>>> iterable = 'abc'
>>> for part in set_partitions(iterable):
... print([''.join(p) for p in part])
['abc']
['a', 'bc']
['ab', 'c']
['b', 'ac']
['a', 'b', 'c']
"""
L = list(iterable)
n = len(L)
if k is not None:
if k < 1:
raise ValueError(
"Can't partition in a negative or zero number of groups"
)
elif k > n:
return
def set_partitions_helper(L, k):
n = len(L)
if k == 1:
yield [L]
elif n == k:
yield [[s] for s in L]
else:
e, *M = L
for p in set_partitions_helper(M, k - 1):
yield [[e], *p]
for p in set_partitions_helper(M, k):
for i in range(len(p)):
yield p[:i] + [[e] + p[i]] + p[i + 1 :]
if k is None:
for k in range(1, n + 1):
yield from set_partitions_helper(L, k)
else:
yield from set_partitions_helper(L, k)
class time_limited:
"""
Yield items from *iterable* until *limit_seconds* have passed.
If the time limit expires before all items have been yielded, the
``timed_out`` parameter will be set to ``True``.
>>> from time import sleep
>>> def generator():
... yield 1
... yield 2
... sleep(0.2)
... yield 3
>>> iterable = time_limited(0.1, generator())
>>> list(iterable)
[1, 2]
>>> iterable.timed_out
True
Note that the time is checked before each item is yielded, and iteration
stops if the time elapsed is greater than *limit_seconds*. If your time
limit is 1 second, but it takes 2 seconds to generate the first item from
the iterable, the function will run for 2 seconds and not yield anything.
"""
def __init__(self, limit_seconds, iterable):
if limit_seconds < 0:
raise ValueError('limit_seconds must be positive')
self.limit_seconds = limit_seconds
self._iterable = iter(iterable)
self._start_time = monotonic()
self.timed_out = False
def __iter__(self):
return self
def __next__(self):
item = next(self._iterable)
if monotonic() - self._start_time > self.limit_seconds:
self.timed_out = True
raise StopIteration
return item
def only(iterable, default=None, too_long=None):
"""If *iterable* has only one item, return it.
If it has zero items, return *default*.
If it has more than one item, raise the exception given by *too_long*,
which is ``ValueError`` by default.
>>> only([], default='missing')
'missing'
>>> only([1])
1
>>> only([1, 2]) # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
ValueError: Expected exactly one item in iterable, but got 1, 2,
and perhaps more.'
>>> only([1, 2], too_long=TypeError) # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
TypeError
Note that :func:`only` attempts to advance *iterable* twice to ensure there
is only one item. See :func:`spy` or :func:`peekable` to check
iterable contents less destructively.
"""
it = iter(iterable)
first_value = next(it, default)
try:
second_value = next(it)
except StopIteration:
pass
else:
msg = (
'Expected exactly one item in iterable, but got {!r}, {!r}, '
'and perhaps more.'.format(first_value, second_value)
)
raise too_long or ValueError(msg)
return first_value
class _IChunk:
def __init__(self, iterable, n):
self._it = islice(iterable, n)
self._cache = deque()
def fill_cache(self):
self._cache.extend(self._it)
def __iter__(self):
return self
def __next__(self):
try:
return next(self._it)
except StopIteration:
if self._cache:
return self._cache.popleft()
else:
raise
def ichunked(iterable, n):
"""Break *iterable* into sub-iterables with *n* elements each.
:func:`ichunked` is like :func:`chunked`, but it yields iterables
instead of lists.
If the sub-iterables are read in order, the elements of *iterable*
won't be stored in memory.
If they are read out of order, :func:`itertools.tee` is used to cache
elements as necessary.
>>> from itertools import count
>>> all_chunks = ichunked(count(), 4)
>>> c_1, c_2, c_3 = next(all_chunks), next(all_chunks), next(all_chunks)
>>> list(c_2) # c_1's elements have been cached; c_3's haven't been
[4, 5, 6, 7]
>>> list(c_1)
[0, 1, 2, 3]
>>> list(c_3)
[8, 9, 10, 11]
"""
source = peekable(iter(iterable))
ichunk_marker = object()
while True:
# Check to see whether we're at the end of the source iterable
item = source.peek(ichunk_marker)
if item is ichunk_marker:
return
chunk = _IChunk(source, n)
yield chunk
# Advance the source iterable and fill previous chunk's cache
chunk.fill_cache()
def iequals(*iterables):
"""Return ``True`` if all given *iterables* are equal to each other,
which means that they contain the same elements in the same order.
The function is useful for comparing iterables of different data types
or iterables that do not support equality checks.
>>> iequals("abc", ['a', 'b', 'c'], ('a', 'b', 'c'), iter("abc"))
True
>>> iequals("abc", "acb")
False
Not to be confused with :func:`all_equals`, which checks whether all
elements of iterable are equal to each other.
"""
return all(map(all_equal, zip_longest(*iterables, fillvalue=object())))
def distinct_combinations(iterable, r):
"""Yield the distinct combinations of *r* items taken from *iterable*.
>>> list(distinct_combinations([0, 0, 1], 2))
[(0, 0), (0, 1)]
Equivalent to ``set(combinations(iterable))``, except duplicates are not
generated and thrown away. For larger input sequences this is much more
efficient.
"""
if r < 0:
raise ValueError('r must be non-negative')
elif r == 0:
yield ()
return
pool = tuple(iterable)
generators = [unique_everseen(enumerate(pool), key=itemgetter(1))]
current_combo = [None] * r
level = 0
while generators:
try:
cur_idx, p = next(generators[-1])
except StopIteration:
generators.pop()
level -= 1
continue
current_combo[level] = p
if level + 1 == r:
yield tuple(current_combo)
else:
generators.append(
unique_everseen(
enumerate(pool[cur_idx + 1 :], cur_idx + 1),
key=itemgetter(1),
)
)
level += 1
def filter_except(validator, iterable, *exceptions):
"""Yield the items from *iterable* for which the *validator* function does
not raise one of the specified *exceptions*.
*validator* is called for each item in *iterable*.
It should be a function that accepts one argument and raises an exception
if that item is not valid.
>>> iterable = ['1', '2', 'three', '4', None]
>>> list(filter_except(int, iterable, ValueError, TypeError))
['1', '2', '4']
If an exception other than one given by *exceptions* is raised by
*validator*, it is raised like normal.
"""
for item in iterable:
try:
validator(item)
except exceptions:
pass
else:
yield item
def map_except(function, iterable, *exceptions):
"""Transform each item from *iterable* with *function* and yield the
result, unless *function* raises one of the specified *exceptions*.
*function* is called to transform each item in *iterable*.
It should accept one argument.
>>> iterable = ['1', '2', 'three', '4', None]
>>> list(map_except(int, iterable, ValueError, TypeError))
[1, 2, 4]
If an exception other than one given by *exceptions* is raised by
*function*, it is raised like normal.
"""
for item in iterable:
try:
yield function(item)
except exceptions:
pass
def map_if(iterable, pred, func, func_else=lambda x: x):
"""Evaluate each item from *iterable* using *pred*. If the result is
equivalent to ``True``, transform the item with *func* and yield it.
Otherwise, transform the item with *func_else* and yield it.
*pred*, *func*, and *func_else* should each be functions that accept
one argument. By default, *func_else* is the identity function.
>>> from math import sqrt
>>> iterable = list(range(-5, 5))
>>> iterable
[-5, -4, -3, -2, -1, 0, 1, 2, 3, 4]
>>> list(map_if(iterable, lambda x: x > 3, lambda x: 'toobig'))
[-5, -4, -3, -2, -1, 0, 1, 2, 3, 'toobig']
>>> list(map_if(iterable, lambda x: x >= 0,
... lambda x: f'{sqrt(x):.2f}', lambda x: None))
[None, None, None, None, None, '0.00', '1.00', '1.41', '1.73', '2.00']
"""
for item in iterable:
yield func(item) if pred(item) else func_else(item)
def _sample_unweighted(iterable, k):
# Implementation of "Algorithm L" from the 1994 paper by Kim-Hung Li:
# "Reservoir-Sampling Algorithms of Time Complexity O(n(1+log(N/n)))".
# Fill up the reservoir (collection of samples) with the first `k` samples
reservoir = take(k, iterable)
# Generate random number that's the largest in a sample of k U(0,1) numbers
# Largest order statistic: https://en.wikipedia.org/wiki/Order_statistic
W = exp(log(random()) / k)
# The number of elements to skip before changing the reservoir is a random
# number with a geometric distribution. Sample it using random() and logs.
next_index = k + floor(log(random()) / log(1 - W))
for index, element in enumerate(iterable, k):
if index == next_index:
reservoir[randrange(k)] = element
# The new W is the largest in a sample of k U(0, `old_W`) numbers
W *= exp(log(random()) / k)
next_index += floor(log(random()) / log(1 - W)) + 1
return reservoir
def _sample_weighted(iterable, k, weights):
# Implementation of "A-ExpJ" from the 2006 paper by Efraimidis et al. :
# "Weighted random sampling with a reservoir".
# Log-transform for numerical stability for weights that are small/large
weight_keys = (log(random()) / weight for weight in weights)
# Fill up the reservoir (collection of samples) with the first `k`
# weight-keys and elements, then heapify the list.
reservoir = take(k, zip(weight_keys, iterable))
heapify(reservoir)
# The number of jumps before changing the reservoir is a random variable
# with an exponential distribution. Sample it using random() and logs.
smallest_weight_key, _ = reservoir[0]
weights_to_skip = log(random()) / smallest_weight_key
for weight, element in zip(weights, iterable):
if weight >= weights_to_skip:
# The notation here is consistent with the paper, but we store
# the weight-keys in log-space for better numerical stability.
smallest_weight_key, _ = reservoir[0]
t_w = exp(weight * smallest_weight_key)
r_2 = uniform(t_w, 1) # generate U(t_w, 1)
weight_key = log(r_2) / weight
heapreplace(reservoir, (weight_key, element))
smallest_weight_key, _ = reservoir[0]
weights_to_skip = log(random()) / smallest_weight_key
else:
weights_to_skip -= weight
# Equivalent to [element for weight_key, element in sorted(reservoir)]
return [heappop(reservoir)[1] for _ in range(k)]
def sample(iterable, k, weights=None):
"""Return a *k*-length list of elements chosen (without replacement)
from the *iterable*. Like :func:`random.sample`, but works on iterables
of unknown length.
>>> iterable = range(100)
>>> sample(iterable, 5) # doctest: +SKIP
[81, 60, 96, 16, 4]
An iterable with *weights* may also be given:
>>> iterable = range(100)
>>> weights = (i * i + 1 for i in range(100))
>>> sampled = sample(iterable, 5, weights=weights) # doctest: +SKIP
[79, 67, 74, 66, 78]
The algorithm can also be used to generate weighted random permutations.
The relative weight of each item determines the probability that it
appears late in the permutation.
>>> data = "abcdefgh"
>>> weights = range(1, len(data) + 1)
>>> sample(data, k=len(data), weights=weights) # doctest: +SKIP
['c', 'a', 'b', 'e', 'g', 'd', 'h', 'f']
"""
if k == 0:
return []
iterable = iter(iterable)
if weights is None:
return _sample_unweighted(iterable, k)
else:
weights = iter(weights)
return _sample_weighted(iterable, k, weights)
def is_sorted(iterable, key=None, reverse=False, strict=False):
"""Returns ``True`` if the items of iterable are in sorted order, and
``False`` otherwise. *key* and *reverse* have the same meaning that they do
in the built-in :func:`sorted` function.
>>> is_sorted(['1', '2', '3', '4', '5'], key=int)
True
>>> is_sorted([5, 4, 3, 1, 2], reverse=True)
False
If *strict*, tests for strict sorting, that is, returns ``False`` if equal
elements are found:
>>> is_sorted([1, 2, 2])
True
>>> is_sorted([1, 2, 2], strict=True)
False
The function returns ``False`` after encountering the first out-of-order
item. If there are no out-of-order items, the iterable is exhausted.
"""
compare = (le if reverse else ge) if strict else (lt if reverse else gt)
it = iterable if key is None else map(key, iterable)
return not any(starmap(compare, pairwise(it)))
class AbortThread(BaseException):
pass
class callback_iter:
"""Convert a function that uses callbacks to an iterator.
Let *func* be a function that takes a `callback` keyword argument.
For example:
>>> def func(callback=None):
... for i, c in [(1, 'a'), (2, 'b'), (3, 'c')]:
... if callback:
... callback(i, c)
... return 4
Use ``with callback_iter(func)`` to get an iterator over the parameters
that are delivered to the callback.
>>> with callback_iter(func) as it:
... for args, kwargs in it:
... print(args)
(1, 'a')
(2, 'b')
(3, 'c')
The function will be called in a background thread. The ``done`` property
indicates whether it has completed execution.
>>> it.done
True
If it completes successfully, its return value will be available
in the ``result`` property.
>>> it.result
4
Notes:
* If the function uses some keyword argument besides ``callback``, supply
*callback_kwd*.
* If it finished executing, but raised an exception, accessing the
``result`` property will raise the same exception.
* If it hasn't finished executing, accessing the ``result``
property from within the ``with`` block will raise ``RuntimeError``.
* If it hasn't finished executing, accessing the ``result`` property from
outside the ``with`` block will raise a
``more_itertools.AbortThread`` exception.
* Provide *wait_seconds* to adjust how frequently the it is polled for
output.
"""
def __init__(self, func, callback_kwd='callback', wait_seconds=0.1):
self._func = func
self._callback_kwd = callback_kwd
self._aborted = False
self._future = None
self._wait_seconds = wait_seconds
# Lazily import concurrent.future
self._executor = __import__(
'concurrent.futures'
).futures.ThreadPoolExecutor(max_workers=1)
self._iterator = self._reader()
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, traceback):
self._aborted = True
self._executor.shutdown()
def __iter__(self):
return self
def __next__(self):
return next(self._iterator)
@property
def done(self):
if self._future is None:
return False
return self._future.done()
@property
def result(self):
if not self.done:
raise RuntimeError('Function has not yet completed')
return self._future.result()
def _reader(self):
q = Queue()
def callback(*args, **kwargs):
if self._aborted:
raise AbortThread('canceled by user')
q.put((args, kwargs))
self._future = self._executor.submit(
self._func, **{self._callback_kwd: callback}
)
while True:
try:
item = q.get(timeout=self._wait_seconds)
except Empty:
pass
else:
q.task_done()
yield item
if self._future.done():
break
remaining = []
while True:
try:
item = q.get_nowait()
except Empty:
break
else:
q.task_done()
remaining.append(item)
q.join()
yield from remaining
def windowed_complete(iterable, n):
"""
Yield ``(beginning, middle, end)`` tuples, where:
* Each ``middle`` has *n* items from *iterable*
* Each ``beginning`` has the items before the ones in ``middle``
* Each ``end`` has the items after the ones in ``middle``
>>> iterable = range(7)
>>> n = 3
>>> for beginning, middle, end in windowed_complete(iterable, n):
... print(beginning, middle, end)
() (0, 1, 2) (3, 4, 5, 6)
(0,) (1, 2, 3) (4, 5, 6)
(0, 1) (2, 3, 4) (5, 6)
(0, 1, 2) (3, 4, 5) (6,)
(0, 1, 2, 3) (4, 5, 6) ()
Note that *n* must be at least 0 and most equal to the length of
*iterable*.
This function will exhaust the iterable and may require significant
storage.
"""
if n < 0:
raise ValueError('n must be >= 0')
seq = tuple(iterable)
size = len(seq)
if n > size:
raise ValueError('n must be <= len(seq)')
for i in range(size - n + 1):
beginning = seq[:i]
middle = seq[i : i + n]
end = seq[i + n :]
yield beginning, middle, end
def all_unique(iterable, key=None):
"""
Returns ``True`` if all the elements of *iterable* are unique (no two
elements are equal).
>>> all_unique('ABCB')
False
If a *key* function is specified, it will be used to make comparisons.
>>> all_unique('ABCb')
True
>>> all_unique('ABCb', str.lower)
False
The function returns as soon as the first non-unique element is
encountered. Iterables with a mix of hashable and unhashable items can
be used, but the function will be slower for unhashable items.
"""
seenset = set()
seenset_add = seenset.add
seenlist = []
seenlist_add = seenlist.append
for element in map(key, iterable) if key else iterable:
try:
if element in seenset:
return False
seenset_add(element)
except TypeError:
if element in seenlist:
return False
seenlist_add(element)
return True
def nth_product(index, *args):
"""Equivalent to ``list(product(*args))[index]``.
The products of *args* can be ordered lexicographically.
:func:`nth_product` computes the product at sort position *index* without
computing the previous products.
>>> nth_product(8, range(2), range(2), range(2), range(2))
(1, 0, 0, 0)
``IndexError`` will be raised if the given *index* is invalid.
"""
pools = list(map(tuple, reversed(args)))
ns = list(map(len, pools))
c = reduce(mul, ns)
if index < 0:
index += c
if not 0 <= index < c:
raise IndexError
result = []
for pool, n in zip(pools, ns):
result.append(pool[index % n])
index //= n
return tuple(reversed(result))
def nth_permutation(iterable, r, index):
"""Equivalent to ``list(permutations(iterable, r))[index]```
The subsequences of *iterable* that are of length *r* where order is
important can be ordered lexicographically. :func:`nth_permutation`
computes the subsequence at sort position *index* directly, without
computing the previous subsequences.
>>> nth_permutation('ghijk', 2, 5)
('h', 'i')
``ValueError`` will be raised If *r* is negative or greater than the length
of *iterable*.
``IndexError`` will be raised if the given *index* is invalid.
"""
pool = list(iterable)
n = len(pool)
if r is None or r == n:
r, c = n, factorial(n)
elif not 0 <= r < n:
raise ValueError
else:
c = factorial(n) // factorial(n - r)
if index < 0:
index += c
if not 0 <= index < c:
raise IndexError
if c == 0:
return tuple()
result = [0] * r
q = index * factorial(n) // c if r < n else index
for d in range(1, n + 1):
q, i = divmod(q, d)
if 0 <= n - d < r:
result[n - d] = i
if q == 0:
break
return tuple(map(pool.pop, result))
def nth_combination_with_replacement(iterable, r, index):
"""Equivalent to
``list(combinations_with_replacement(iterable, r))[index]``.
The subsequences with repetition of *iterable* that are of length *r* can
be ordered lexicographically. :func:`nth_combination_with_replacement`
computes the subsequence at sort position *index* directly, without
computing the previous subsequences with replacement.
>>> nth_combination_with_replacement(range(5), 3, 5)
(0, 1, 1)
``ValueError`` will be raised If *r* is negative or greater than the length
of *iterable*.
``IndexError`` will be raised if the given *index* is invalid.
"""
pool = tuple(iterable)
n = len(pool)
if (r < 0) or (r > n):
raise ValueError
c = factorial(n + r - 1) // (factorial(r) * factorial(n - 1))
if index < 0:
index += c
if (index < 0) or (index >= c):
raise IndexError
result = []
i = 0
while r:
r -= 1
while n >= 0:
num_combs = factorial(n + r - 1) // (
factorial(r) * factorial(n - 1)
)
if index < num_combs:
break
n -= 1
i += 1
index -= num_combs
result.append(pool[i])
return tuple(result)
def value_chain(*args):
"""Yield all arguments passed to the function in the same order in which
they were passed. If an argument itself is iterable then iterate over its
values.
>>> list(value_chain(1, 2, 3, [4, 5, 6]))
[1, 2, 3, 4, 5, 6]
Binary and text strings are not considered iterable and are emitted
as-is:
>>> list(value_chain('12', '34', ['56', '78']))
['12', '34', '56', '78']
Multiple levels of nesting are not flattened.
"""
for value in args:
if isinstance(value, (str, bytes)):
yield value
continue
try:
yield from value
except TypeError:
yield value
def product_index(element, *args):
"""Equivalent to ``list(product(*args)).index(element)``
The products of *args* can be ordered lexicographically.
:func:`product_index` computes the first index of *element* without
computing the previous products.
>>> product_index([8, 2], range(10), range(5))
42
``ValueError`` will be raised if the given *element* isn't in the product
of *args*.
"""
index = 0
for x, pool in zip_longest(element, args, fillvalue=_marker):
if x is _marker or pool is _marker:
raise ValueError('element is not a product of args')
pool = tuple(pool)
index = index * len(pool) + pool.index(x)
return index
def combination_index(element, iterable):
"""Equivalent to ``list(combinations(iterable, r)).index(element)``
The subsequences of *iterable* that are of length *r* can be ordered
lexicographically. :func:`combination_index` computes the index of the
first *element*, without computing the previous combinations.
>>> combination_index('adf', 'abcdefg')
10
``ValueError`` will be raised if the given *element* isn't one of the
combinations of *iterable*.
"""
element = enumerate(element)
k, y = next(element, (None, None))
if k is None:
return 0
indexes = []
pool = enumerate(iterable)
for n, x in pool:
if x == y:
indexes.append(n)
tmp, y = next(element, (None, None))
if tmp is None:
break
else:
k = tmp
else:
raise ValueError('element is not a combination of iterable')
n, _ = last(pool, default=(n, None))
# Python versions below 3.8 don't have math.comb
index = 1
for i, j in enumerate(reversed(indexes), start=1):
j = n - j
if i <= j:
index += factorial(j) // (factorial(i) * factorial(j - i))
return factorial(n + 1) // (factorial(k + 1) * factorial(n - k)) - index
def combination_with_replacement_index(element, iterable):
"""Equivalent to
``list(combinations_with_replacement(iterable, r)).index(element)``
The subsequences with repetition of *iterable* that are of length *r* can
be ordered lexicographically. :func:`combination_with_replacement_index`
computes the index of the first *element*, without computing the previous
combinations with replacement.
>>> combination_with_replacement_index('adf', 'abcdefg')
20
``ValueError`` will be raised if the given *element* isn't one of the
combinations with replacement of *iterable*.
"""
element = tuple(element)
l = len(element)
element = enumerate(element)
k, y = next(element, (None, None))
if k is None:
return 0
indexes = []
pool = tuple(iterable)
for n, x in enumerate(pool):
while x == y:
indexes.append(n)
tmp, y = next(element, (None, None))
if tmp is None:
break
else:
k = tmp
if y is None:
break
else:
raise ValueError(
'element is not a combination with replacment of iterable'
)
n = len(pool)
occupations = [0] * n
for p in indexes:
occupations[p] += 1
index = 0
for k in range(1, n):
j = l + n - 1 - k - sum(occupations[:k])
i = n - k
if i <= j:
index += factorial(j) // (factorial(i) * factorial(j - i))
return index
def permutation_index(element, iterable):
"""Equivalent to ``list(permutations(iterable, r)).index(element)```
The subsequences of *iterable* that are of length *r* where order is
important can be ordered lexicographically. :func:`permutation_index`
computes the index of the first *element* directly, without computing
the previous permutations.
>>> permutation_index([1, 3, 2], range(5))
19
``ValueError`` will be raised if the given *element* isn't one of the
permutations of *iterable*.
"""
index = 0
pool = list(iterable)
for i, x in zip(range(len(pool), -1, -1), element):
r = pool.index(x)
index = index * i + r
del pool[r]
return index
class countable:
"""Wrap *iterable* and keep a count of how many items have been consumed.
The ``items_seen`` attribute starts at ``0`` and increments as the iterable
is consumed:
>>> iterable = map(str, range(10))
>>> it = countable(iterable)
>>> it.items_seen
0
>>> next(it), next(it)
('0', '1')
>>> list(it)
['2', '3', '4', '5', '6', '7', '8', '9']
>>> it.items_seen
10
"""
def __init__(self, iterable):
self._it = iter(iterable)
self.items_seen = 0
def __iter__(self):
return self
def __next__(self):
item = next(self._it)
self.items_seen += 1
return item
def chunked_even(iterable, n):
"""Break *iterable* into lists of approximately length *n*.
Items are distributed such the lengths of the lists differ by at most
1 item.
>>> iterable = [1, 2, 3, 4, 5, 6, 7]
>>> n = 3
>>> list(chunked_even(iterable, n)) # List lengths: 3, 2, 2
[[1, 2, 3], [4, 5], [6, 7]]
>>> list(chunked(iterable, n)) # List lengths: 3, 3, 1
[[1, 2, 3], [4, 5, 6], [7]]
"""
len_method = getattr(iterable, '__len__', None)
if len_method is None:
return _chunked_even_online(iterable, n)
else:
return _chunked_even_finite(iterable, len_method(), n)
def _chunked_even_online(iterable, n):
buffer = []
maxbuf = n + (n - 2) * (n - 1)
for x in iterable:
buffer.append(x)
if len(buffer) == maxbuf:
yield buffer[:n]
buffer = buffer[n:]
yield from _chunked_even_finite(buffer, len(buffer), n)
def _chunked_even_finite(iterable, N, n):
if N < 1:
return
# Lists are either size `full_size <= n` or `partial_size = full_size - 1`
q, r = divmod(N, n)
num_lists = q + (1 if r > 0 else 0)
q, r = divmod(N, num_lists)
full_size = q + (1 if r > 0 else 0)
partial_size = full_size - 1
num_full = N - partial_size * num_lists
num_partial = num_lists - num_full
# Yield num_full lists of full_size
partial_start_idx = num_full * full_size
if full_size > 0:
for i in range(0, partial_start_idx, full_size):
yield list(islice(iterable, i, i + full_size))
# Yield num_partial lists of partial_size
if partial_size > 0:
for i in range(
partial_start_idx,
partial_start_idx + (num_partial * partial_size),
partial_size,
):
yield list(islice(iterable, i, i + partial_size))
def zip_broadcast(*objects, scalar_types=(str, bytes), strict=False):
"""A version of :func:`zip` that "broadcasts" any scalar
(i.e., non-iterable) items into output tuples.
>>> iterable_1 = [1, 2, 3]
>>> iterable_2 = ['a', 'b', 'c']
>>> scalar = '_'
>>> list(zip_broadcast(iterable_1, iterable_2, scalar))
[(1, 'a', '_'), (2, 'b', '_'), (3, 'c', '_')]
The *scalar_types* keyword argument determines what types are considered
scalar. It is set to ``(str, bytes)`` by default. Set it to ``None`` to
treat strings and byte strings as iterable:
>>> list(zip_broadcast('abc', 0, 'xyz', scalar_types=None))
[('a', 0, 'x'), ('b', 0, 'y'), ('c', 0, 'z')]
If the *strict* keyword argument is ``True``, then
``UnequalIterablesError`` will be raised if any of the iterables have
different lengths.
"""
def is_scalar(obj):
if scalar_types and isinstance(obj, scalar_types):
return True
try:
iter(obj)
except TypeError:
return True
else:
return False
size = len(objects)
if not size:
return
new_item = [None] * size
iterables, iterable_positions = [], []
for i, obj in enumerate(objects):
if is_scalar(obj):
new_item[i] = obj
else:
iterables.append(iter(obj))
iterable_positions.append(i)
if not iterables:
yield tuple(objects)
return
zipper = _zip_equal if strict else zip
for item in zipper(*iterables):
for i, new_item[i] in zip(iterable_positions, item):
pass
yield tuple(new_item)
def unique_in_window(iterable, n, key=None):
"""Yield the items from *iterable* that haven't been seen recently.
*n* is the size of the lookback window.
>>> iterable = [0, 1, 0, 2, 3, 0]
>>> n = 3
>>> list(unique_in_window(iterable, n))
[0, 1, 2, 3, 0]
The *key* function, if provided, will be used to determine uniqueness:
>>> list(unique_in_window('abAcda', 3, key=lambda x: x.lower()))
['a', 'b', 'c', 'd', 'a']
The items in *iterable* must be hashable.
"""
if n <= 0:
raise ValueError('n must be greater than 0')
window = deque(maxlen=n)
counts = defaultdict(int)
use_key = key is not None
for item in iterable:
if len(window) == n:
to_discard = window[0]
if counts[to_discard] == 1:
del counts[to_discard]
else:
counts[to_discard] -= 1
k = key(item) if use_key else item
if k not in counts:
yield item
counts[k] += 1
window.append(k)
def duplicates_everseen(iterable, key=None):
"""Yield duplicate elements after their first appearance.
>>> list(duplicates_everseen('mississippi'))
['s', 'i', 's', 's', 'i', 'p', 'i']
>>> list(duplicates_everseen('AaaBbbCccAaa', str.lower))
['a', 'a', 'b', 'b', 'c', 'c', 'A', 'a', 'a']
This function is analagous to :func:`unique_everseen` and is subject to
the same performance considerations.
"""
seen_set = set()
seen_list = []
use_key = key is not None
for element in iterable:
k = key(element) if use_key else element
try:
if k not in seen_set:
seen_set.add(k)
else:
yield element
except TypeError:
if k not in seen_list:
seen_list.append(k)
else:
yield element
def duplicates_justseen(iterable, key=None):
"""Yields serially-duplicate elements after their first appearance.
>>> list(duplicates_justseen('mississippi'))
['s', 's', 'p']
>>> list(duplicates_justseen('AaaBbbCccAaa', str.lower))
['a', 'a', 'b', 'b', 'c', 'c', 'a', 'a']
This function is analagous to :func:`unique_justseen`.
"""
return flatten(g for _, g in groupby(iterable, key) for _ in g)
def minmax(iterable_or_value, *others, key=None, default=_marker):
"""Returns both the smallest and largest items in an iterable
or the largest of two or more arguments.
>>> minmax([3, 1, 5])
(1, 5)
>>> minmax(4, 2, 6)
(2, 6)
If a *key* function is provided, it will be used to transform the input
items for comparison.
>>> minmax([5, 30], key=str) # '30' sorts before '5'
(30, 5)
If a *default* value is provided, it will be returned if there are no
input items.
>>> minmax([], default=(0, 0))
(0, 0)
Otherwise ``ValueError`` is raised.
This function is based on the
`recipe <http://code.activestate.com/recipes/577916/>`__ by
Raymond Hettinger and takes care to minimize the number of comparisons
performed.
"""
iterable = (iterable_or_value, *others) if others else iterable_or_value
it = iter(iterable)
try:
lo = hi = next(it)
except StopIteration as e:
if default is _marker:
raise ValueError(
'`minmax()` argument is an empty iterable. '
'Provide a `default` value to suppress this error.'
) from e
return default
# Different branches depending on the presence of key. This saves a lot
# of unimportant copies which would slow the "key=None" branch
# significantly down.
if key is None:
for x, y in zip_longest(it, it, fillvalue=lo):
if y < x:
x, y = y, x
if x < lo:
lo = x
if hi < y:
hi = y
else:
lo_key = hi_key = key(lo)
for x, y in zip_longest(it, it, fillvalue=lo):
x_key, y_key = key(x), key(y)
if y_key < x_key:
x, y, x_key, y_key = y, x, y_key, x_key
if x_key < lo_key:
lo, lo_key = x, x_key
if hi_key < y_key:
hi, hi_key = y, y_key
return lo, hi
def constrained_batches(
iterable, max_size, max_count=None, get_len=len, strict=True
):
"""Yield batches of items from *iterable* with a combined size limited by
*max_size*.
>>> iterable = [b'12345', b'123', b'12345678', b'1', b'1', b'12', b'1']
>>> list(constrained_batches(iterable, 10))
[(b'12345', b'123'), (b'12345678', b'1', b'1'), (b'12', b'1')]
If a *max_count* is supplied, the number of items per batch is also
limited:
>>> iterable = [b'12345', b'123', b'12345678', b'1', b'1', b'12', b'1']
>>> list(constrained_batches(iterable, 10, max_count = 2))
[(b'12345', b'123'), (b'12345678', b'1'), (b'1', b'12'), (b'1',)]
If a *get_len* function is supplied, use that instead of :func:`len` to
determine item size.
If *strict* is ``True``, raise ``ValueError`` if any single item is bigger
than *max_size*. Otherwise, allow single items to exceed *max_size*.
"""
if max_size <= 0:
raise ValueError('maximum size must be greater than zero')
batch = []
batch_size = 0
batch_count = 0
for item in iterable:
item_len = get_len(item)
if strict and item_len > max_size:
raise ValueError('item size exceeds maximum size')
reached_count = batch_count == max_count
reached_size = item_len + batch_size > max_size
if batch_count and (reached_size or reached_count):
yield tuple(batch)
batch.clear()
batch_size = 0
batch_count = 0
batch.append(item)
batch_size += item_len
batch_count += 1
if batch:
yield tuple(batch)
def gray_product(*iterables):
"""Like :func:`itertools.product`, but return tuples in an order such
that only one element in the generated tuple changes from one iteration
to the next.
>>> list(gray_product('AB','CD'))
[('A', 'C'), ('B', 'C'), ('B', 'D'), ('A', 'D')]
This function consumes all of the input iterables before producing output.
If any of the input iterables have fewer than two items, ``ValueError``
is raised.
For information on the algorithm, see
`this section <https://www-cs-faculty.stanford.edu/~knuth/fasc2a.ps.gz>`__
of Donald Knuth's *The Art of Computer Programming*.
"""
all_iterables = tuple(tuple(x) for x in iterables)
iterable_count = len(all_iterables)
for iterable in all_iterables:
if len(iterable) < 2:
raise ValueError("each iterable must have two or more items")
# This is based on "Algorithm H" from section 7.2.1.1, page 20.
# a holds the indexes of the source iterables for the n-tuple to be yielded
# f is the array of "focus pointers"
# o is the array of "directions"
a = [0] * iterable_count
f = list(range(iterable_count + 1))
o = [1] * iterable_count
while True:
yield tuple(all_iterables[i][a[i]] for i in range(iterable_count))
j = f[0]
f[0] = 0
if j == iterable_count:
break
a[j] = a[j] + o[j]
if a[j] == 0 or a[j] == len(all_iterables[j]) - 1:
o[j] = -o[j]
f[j] = f[j + 1]
f[j + 1] = j + 1
def partial_product(*iterables):
"""Yields tuples containing one item from each iterator, with subsequent
tuples changing a single item at a time by advancing each iterator until it
is exhausted. This sequence guarantees every value in each iterable is
output at least once without generating all possible combinations.
This may be useful, for example, when testing an expensive function.
>>> list(partial_product('AB', 'C', 'DEF'))
[('A', 'C', 'D'), ('B', 'C', 'D'), ('B', 'C', 'E'), ('B', 'C', 'F')]
"""
iterators = list(map(iter, iterables))
try:
prod = [next(it) for it in iterators]
except StopIteration:
return
yield tuple(prod)
for i, it in enumerate(iterators):
for prod[i] in it:
yield tuple(prod)
def takewhile_inclusive(predicate, iterable):
"""A variant of :func:`takewhile` that yields one additional element.
>>> list(takewhile_inclusive(lambda x: x < 5, [1, 4, 6, 4, 1]))
[1, 4, 6]
:func:`takewhile` would return ``[1, 4]``.
"""
for x in iterable:
if predicate(x):
yield x
else:
yield x
break
def outer_product(func, xs, ys, *args, **kwargs):
"""A generalized outer product that applies a binary function to all
pairs of items. Returns a 2D matrix with ``len(xs)`` rows and ``len(ys)``
columns.
Also accepts ``*args`` and ``**kwargs`` that are passed to ``func``.
Multiplication table:
>>> list(outer_product(mul, range(1, 4), range(1, 6)))
[(1, 2, 3, 4, 5), (2, 4, 6, 8, 10), (3, 6, 9, 12, 15)]
Cross tabulation:
>>> xs = ['A', 'B', 'A', 'A', 'B', 'B', 'A', 'A', 'B', 'B']
>>> ys = ['X', 'X', 'X', 'Y', 'Z', 'Z', 'Y', 'Y', 'Z', 'Z']
>>> rows = list(zip(xs, ys))
>>> count_rows = lambda x, y: rows.count((x, y))
>>> list(outer_product(count_rows, sorted(set(xs)), sorted(set(ys))))
[(2, 3, 0), (1, 0, 4)]
Usage with ``*args`` and ``**kwargs``:
>>> animals = ['cat', 'wolf', 'mouse']
>>> list(outer_product(min, animals, animals, key=len))
[('cat', 'cat', 'cat'), ('cat', 'wolf', 'wolf'), ('cat', 'wolf', 'mouse')]
"""
ys = tuple(ys)
return batched(
starmap(lambda x, y: func(x, y, *args, **kwargs), product(xs, ys)),
n=len(ys),
)
|