defchararray.py 69.5 KB
Newer Older
xuebingbing's avatar
xuebingbing committed
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
"""
This module contains a set of functions for vectorized string
operations and methods.

.. note::
   The `chararray` class exists for backwards compatibility with
   Numarray, it is not recommended for new development. Starting from numpy
   1.4, if one needs arrays of strings, it is recommended to use arrays of
   `dtype` `object_`, `string_` or `unicode_`, and use the free functions
   in the `numpy.char` module for fast vectorized string operations.

Some methods will only be available if the corresponding string method is
available in your version of Python.

The preferred alias for `defchararray` is `numpy.char`.

"""
from __future__ import division, absolute_import, print_function

import functools
import sys
from .numerictypes import string_, unicode_, integer, object_, bool_, character
from .numeric import ndarray, compare_chararrays
from .numeric import array as narray
from numpy.core.multiarray import _vec_string
from numpy.core.overrides import set_module
from numpy.core import overrides
from numpy.compat import asbytes, long
import numpy

__all__ = [
    'chararray', 'equal', 'not_equal', 'greater_equal', 'less_equal',
    'greater', 'less', 'str_len', 'add', 'multiply', 'mod', 'capitalize',
    'center', 'count', 'decode', 'encode', 'endswith', 'expandtabs',
    'find', 'index', 'isalnum', 'isalpha', 'isdigit', 'islower', 'isspace',
    'istitle', 'isupper', 'join', 'ljust', 'lower', 'lstrip', 'partition',
    'replace', 'rfind', 'rindex', 'rjust', 'rpartition', 'rsplit',
    'rstrip', 'split', 'splitlines', 'startswith', 'strip', 'swapcase',
    'title', 'translate', 'upper', 'zfill', 'isnumeric', 'isdecimal',
    'array', 'asarray'
    ]


_globalvar = 0
if sys.version_info[0] >= 3:
    _unicode = str
    _bytes = bytes
else:
    _unicode = unicode
    _bytes = str
_len = len

array_function_dispatch = functools.partial(
    overrides.array_function_dispatch, module='numpy.char')


def _use_unicode(*args):
    """
    Helper function for determining the output type of some string
    operations.

    For an operation on two ndarrays, if at least one is unicode, the
    result should be unicode.
    """
    for x in args:
        if (isinstance(x, _unicode) or
                issubclass(numpy.asarray(x).dtype.type, unicode_)):
            return unicode_
    return string_

def _to_string_or_unicode_array(result):
    """
    Helper function to cast a result back into a string or unicode array
    if an object array must be used as an intermediary.
    """
    return numpy.asarray(result.tolist())

def _clean_args(*args):
    """
    Helper function for delegating arguments to Python string
    functions.

    Many of the Python string operations that have optional arguments
    do not use 'None' to indicate a default value.  In these cases,
    we need to remove all `None` arguments, and those following them.
    """
    newargs = []
    for chk in args:
        if chk is None:
            break
        newargs.append(chk)
    return newargs

def _get_num_chars(a):
    """
    Helper function that returns the number of characters per field in
    a string or unicode array.  This is to abstract out the fact that
    for a unicode array this is itemsize / 4.
    """
    if issubclass(a.dtype.type, unicode_):
        return a.itemsize // 4
    return a.itemsize


def _binary_op_dispatcher(x1, x2):
    return (x1, x2)


@array_function_dispatch(_binary_op_dispatcher)
def equal(x1, x2):
    """
    Return (x1 == x2) element-wise.

    Unlike `numpy.equal`, this comparison is performed by first
    stripping whitespace characters from the end of the string.  This
    behavior is provided for backward-compatibility with numarray.

    Parameters
    ----------
    x1, x2 : array_like of str or unicode
        Input arrays of the same shape.

    Returns
    -------
    out : ndarray or bool
        Output array of bools, or a single bool if x1 and x2 are scalars.

    See Also
    --------
    not_equal, greater_equal, less_equal, greater, less
    """
    return compare_chararrays(x1, x2, '==', True)


@array_function_dispatch(_binary_op_dispatcher)
def not_equal(x1, x2):
    """
    Return (x1 != x2) element-wise.

    Unlike `numpy.not_equal`, this comparison is performed by first
    stripping whitespace characters from the end of the string.  This
    behavior is provided for backward-compatibility with numarray.

    Parameters
    ----------
    x1, x2 : array_like of str or unicode
        Input arrays of the same shape.

    Returns
    -------
    out : ndarray or bool
        Output array of bools, or a single bool if x1 and x2 are scalars.

    See Also
    --------
    equal, greater_equal, less_equal, greater, less
    """
    return compare_chararrays(x1, x2, '!=', True)


@array_function_dispatch(_binary_op_dispatcher)
def greater_equal(x1, x2):
    """
    Return (x1 >= x2) element-wise.

    Unlike `numpy.greater_equal`, this comparison is performed by
    first stripping whitespace characters from the end of the string.
    This behavior is provided for backward-compatibility with
    numarray.

    Parameters
    ----------
    x1, x2 : array_like of str or unicode
        Input arrays of the same shape.

    Returns
    -------
    out : ndarray or bool
        Output array of bools, or a single bool if x1 and x2 are scalars.

    See Also
    --------
    equal, not_equal, less_equal, greater, less
    """
    return compare_chararrays(x1, x2, '>=', True)


@array_function_dispatch(_binary_op_dispatcher)
def less_equal(x1, x2):
    """
    Return (x1 <= x2) element-wise.

    Unlike `numpy.less_equal`, this comparison is performed by first
    stripping whitespace characters from the end of the string.  This
    behavior is provided for backward-compatibility with numarray.

    Parameters
    ----------
    x1, x2 : array_like of str or unicode
        Input arrays of the same shape.

    Returns
    -------
    out : ndarray or bool
        Output array of bools, or a single bool if x1 and x2 are scalars.

    See Also
    --------
    equal, not_equal, greater_equal, greater, less
    """
    return compare_chararrays(x1, x2, '<=', True)


@array_function_dispatch(_binary_op_dispatcher)
def greater(x1, x2):
    """
    Return (x1 > x2) element-wise.

    Unlike `numpy.greater`, this comparison is performed by first
    stripping whitespace characters from the end of the string.  This
    behavior is provided for backward-compatibility with numarray.

    Parameters
    ----------
    x1, x2 : array_like of str or unicode
        Input arrays of the same shape.

    Returns
    -------
    out : ndarray or bool
        Output array of bools, or a single bool if x1 and x2 are scalars.

    See Also
    --------
    equal, not_equal, greater_equal, less_equal, less
    """
    return compare_chararrays(x1, x2, '>', True)


@array_function_dispatch(_binary_op_dispatcher)
def less(x1, x2):
    """
    Return (x1 < x2) element-wise.

    Unlike `numpy.greater`, this comparison is performed by first
    stripping whitespace characters from the end of the string.  This
    behavior is provided for backward-compatibility with numarray.

    Parameters
    ----------
    x1, x2 : array_like of str or unicode
        Input arrays of the same shape.

    Returns
    -------
    out : ndarray or bool
        Output array of bools, or a single bool if x1 and x2 are scalars.

    See Also
    --------
    equal, not_equal, greater_equal, less_equal, greater
    """
    return compare_chararrays(x1, x2, '<', True)


def _unary_op_dispatcher(a):
    return (a,)


@array_function_dispatch(_unary_op_dispatcher)
def str_len(a):
    """
    Return len(a) element-wise.

    Parameters
    ----------
    a : array_like of str or unicode

    Returns
    -------
    out : ndarray
        Output array of integers

    See also
    --------
    __builtin__.len
    """
    return _vec_string(a, integer, '__len__')


@array_function_dispatch(_binary_op_dispatcher)
def add(x1, x2):
    """
    Return element-wise string concatenation for two arrays of str or unicode.

    Arrays `x1` and `x2` must have the same shape.

    Parameters
    ----------
    x1 : array_like of str or unicode
        Input array.
    x2 : array_like of str or unicode
        Input array.

    Returns
    -------
    add : ndarray
        Output array of `string_` or `unicode_`, depending on input types
        of the same shape as `x1` and `x2`.

    """
    arr1 = numpy.asarray(x1)
    arr2 = numpy.asarray(x2)
    out_size = _get_num_chars(arr1) + _get_num_chars(arr2)
    dtype = _use_unicode(arr1, arr2)
    return _vec_string(arr1, (dtype, out_size), '__add__', (arr2,))


def _multiply_dispatcher(a, i):
    return (a,)


@array_function_dispatch(_multiply_dispatcher)
def multiply(a, i):
    """
    Return (a * i), that is string multiple concatenation,
    element-wise.

    Values in `i` of less than 0 are treated as 0 (which yields an
    empty string).

    Parameters
    ----------
    a : array_like of str or unicode

    i : array_like of ints

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input types

    """
    a_arr = numpy.asarray(a)
    i_arr = numpy.asarray(i)
    if not issubclass(i_arr.dtype.type, integer):
        raise ValueError("Can only multiply by integers")
    out_size = _get_num_chars(a_arr) * max(long(i_arr.max()), 0)
    return _vec_string(
        a_arr, (a_arr.dtype.type, out_size), '__mul__', (i_arr,))


def _mod_dispatcher(a, values):
    return (a, values)


@array_function_dispatch(_mod_dispatcher)
def mod(a, values):
    """
    Return (a % i), that is pre-Python 2.6 string formatting
    (iterpolation), element-wise for a pair of array_likes of str
    or unicode.

    Parameters
    ----------
    a : array_like of str or unicode

    values : array_like of values
       These values will be element-wise interpolated into the string.

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input types

    See also
    --------
    str.__mod__

    """
    return _to_string_or_unicode_array(
        _vec_string(a, object_, '__mod__', (values,)))


@array_function_dispatch(_unary_op_dispatcher)
def capitalize(a):
    """
    Return a copy of `a` with only the first character of each element
    capitalized.

    Calls `str.capitalize` element-wise.

    For 8-bit strings, this method is locale-dependent.

    Parameters
    ----------
    a : array_like of str or unicode
        Input array of strings to capitalize.

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input
        types

    See also
    --------
    str.capitalize

    Examples
    --------
    >>> c = np.array(['a1b2','1b2a','b2a1','2a1b'],'S4'); c
    array(['a1b2', '1b2a', 'b2a1', '2a1b'],
        dtype='|S4')
    >>> np.char.capitalize(c)
    array(['A1b2', '1b2a', 'B2a1', '2a1b'],
        dtype='|S4')

    """
    a_arr = numpy.asarray(a)
    return _vec_string(a_arr, a_arr.dtype, 'capitalize')


def _center_dispatcher(a, width, fillchar=None):
    return (a,)


@array_function_dispatch(_center_dispatcher)
def center(a, width, fillchar=' '):
    """
    Return a copy of `a` with its elements centered in a string of
    length `width`.

    Calls `str.center` element-wise.

    Parameters
    ----------
    a : array_like of str or unicode

    width : int
        The length of the resulting strings
    fillchar : str or unicode, optional
        The padding character to use (default is space).

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input
        types

    See also
    --------
    str.center

    """
    a_arr = numpy.asarray(a)
    width_arr = numpy.asarray(width)
    size = long(numpy.max(width_arr.flat))
    if numpy.issubdtype(a_arr.dtype, numpy.string_):
        fillchar = asbytes(fillchar)
    return _vec_string(
        a_arr, (a_arr.dtype.type, size), 'center', (width_arr, fillchar))


def _count_dispatcher(a, sub, start=None, end=None):
    return (a,)


@array_function_dispatch(_count_dispatcher)
def count(a, sub, start=0, end=None):
    """
    Returns an array with the number of non-overlapping occurrences of
    substring `sub` in the range [`start`, `end`].

    Calls `str.count` element-wise.

    Parameters
    ----------
    a : array_like of str or unicode

    sub : str or unicode
       The substring to search for.

    start, end : int, optional
       Optional arguments `start` and `end` are interpreted as slice
       notation to specify the range in which to count.

    Returns
    -------
    out : ndarray
        Output array of ints.

    See also
    --------
    str.count

    Examples
    --------
    >>> c = np.array(['aAaAaA', '  aA  ', 'abBABba'])
    >>> c
    array(['aAaAaA', '  aA  ', 'abBABba'],
        dtype='|S7')
    >>> np.char.count(c, 'A')
    array([3, 1, 1])
    >>> np.char.count(c, 'aA')
    array([3, 1, 0])
    >>> np.char.count(c, 'A', start=1, end=4)
    array([2, 1, 1])
    >>> np.char.count(c, 'A', start=1, end=3)
    array([1, 0, 0])

    """
    return _vec_string(a, integer, 'count', [sub, start] + _clean_args(end))


def _code_dispatcher(a, encoding=None, errors=None):
    return (a,)


@array_function_dispatch(_code_dispatcher)
def decode(a, encoding=None, errors=None):
    """
    Calls `str.decode` element-wise.

    The set of available codecs comes from the Python standard library,
    and may be extended at runtime.  For more information, see the
    :mod:`codecs` module.

    Parameters
    ----------
    a : array_like of str or unicode

    encoding : str, optional
       The name of an encoding

    errors : str, optional
       Specifies how to handle encoding errors

    Returns
    -------
    out : ndarray

    See also
    --------
    str.decode

    Notes
    -----
    The type of the result will depend on the encoding specified.

    Examples
    --------
    >>> c = np.array(['aAaAaA', '  aA  ', 'abBABba'])
    >>> c
    array(['aAaAaA', '  aA  ', 'abBABba'],
        dtype='|S7')
    >>> np.char.encode(c, encoding='cp037')
    array(['\\x81\\xc1\\x81\\xc1\\x81\\xc1', '@@\\x81\\xc1@@',
        '\\x81\\x82\\xc2\\xc1\\xc2\\x82\\x81'],
        dtype='|S7')

    """
    return _to_string_or_unicode_array(
        _vec_string(a, object_, 'decode', _clean_args(encoding, errors)))


@array_function_dispatch(_code_dispatcher)
def encode(a, encoding=None, errors=None):
    """
    Calls `str.encode` element-wise.

    The set of available codecs comes from the Python standard library,
    and may be extended at runtime. For more information, see the codecs
    module.

    Parameters
    ----------
    a : array_like of str or unicode

    encoding : str, optional
       The name of an encoding

    errors : str, optional
       Specifies how to handle encoding errors

    Returns
    -------
    out : ndarray

    See also
    --------
    str.encode

    Notes
    -----
    The type of the result will depend on the encoding specified.

    """
    return _to_string_or_unicode_array(
        _vec_string(a, object_, 'encode', _clean_args(encoding, errors)))


def _endswith_dispatcher(a, suffix, start=None, end=None):
    return (a,)


@array_function_dispatch(_endswith_dispatcher)
def endswith(a, suffix, start=0, end=None):
    """
    Returns a boolean array which is `True` where the string element
    in `a` ends with `suffix`, otherwise `False`.

    Calls `str.endswith` element-wise.

    Parameters
    ----------
    a : array_like of str or unicode

    suffix : str

    start, end : int, optional
        With optional `start`, test beginning at that position. With
        optional `end`, stop comparing at that position.

    Returns
    -------
    out : ndarray
        Outputs an array of bools.

    See also
    --------
    str.endswith

    Examples
    --------
    >>> s = np.array(['foo', 'bar'])
    >>> s[0] = 'foo'
    >>> s[1] = 'bar'
    >>> s
    array(['foo', 'bar'],
        dtype='|S3')
    >>> np.char.endswith(s, 'ar')
    array([False,  True])
    >>> np.char.endswith(s, 'a', start=1, end=2)
    array([False,  True])

    """
    return _vec_string(
        a, bool_, 'endswith', [suffix, start] + _clean_args(end))


def _expandtabs_dispatcher(a, tabsize=None):
    return (a,)


@array_function_dispatch(_expandtabs_dispatcher)
def expandtabs(a, tabsize=8):
    """
    Return a copy of each string element where all tab characters are
    replaced by one or more spaces.

    Calls `str.expandtabs` element-wise.

    Return a copy of each string element where all tab characters are
    replaced by one or more spaces, depending on the current column
    and the given `tabsize`. The column number is reset to zero after
    each newline occurring in the string. This doesn't understand other
    non-printing characters or escape sequences.

    Parameters
    ----------
    a : array_like of str or unicode
        Input array
    tabsize : int, optional
        Replace tabs with `tabsize` number of spaces.  If not given defaults
        to 8 spaces.

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input type

    See also
    --------
    str.expandtabs

    """
    return _to_string_or_unicode_array(
        _vec_string(a, object_, 'expandtabs', (tabsize,)))


@array_function_dispatch(_count_dispatcher)
def find(a, sub, start=0, end=None):
    """
    For each element, return the lowest index in the string where
    substring `sub` is found.

    Calls `str.find` element-wise.

    For each element, return the lowest index in the string where
    substring `sub` is found, such that `sub` is contained in the
    range [`start`, `end`].

    Parameters
    ----------
    a : array_like of str or unicode

    sub : str or unicode

    start, end : int, optional
        Optional arguments `start` and `end` are interpreted as in
        slice notation.

    Returns
    -------
    out : ndarray or int
        Output array of ints.  Returns -1 if `sub` is not found.

    See also
    --------
    str.find

    """
    return _vec_string(
        a, integer, 'find', [sub, start] + _clean_args(end))


@array_function_dispatch(_count_dispatcher)
def index(a, sub, start=0, end=None):
    """
    Like `find`, but raises `ValueError` when the substring is not found.

    Calls `str.index` element-wise.

    Parameters
    ----------
    a : array_like of str or unicode

    sub : str or unicode

    start, end : int, optional

    Returns
    -------
    out : ndarray
        Output array of ints.  Returns -1 if `sub` is not found.

    See also
    --------
    find, str.find

    """
    return _vec_string(
        a, integer, 'index', [sub, start] + _clean_args(end))


@array_function_dispatch(_unary_op_dispatcher)
def isalnum(a):
    """
    Returns true for each element if all characters in the string are
    alphanumeric and there is at least one character, false otherwise.

    Calls `str.isalnum` element-wise.

    For 8-bit strings, this method is locale-dependent.

    Parameters
    ----------
    a : array_like of str or unicode

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input type

    See also
    --------
    str.isalnum
    """
    return _vec_string(a, bool_, 'isalnum')


@array_function_dispatch(_unary_op_dispatcher)
def isalpha(a):
    """
    Returns true for each element if all characters in the string are
    alphabetic and there is at least one character, false otherwise.

    Calls `str.isalpha` element-wise.

    For 8-bit strings, this method is locale-dependent.

    Parameters
    ----------
    a : array_like of str or unicode

    Returns
    -------
    out : ndarray
        Output array of bools

    See also
    --------
    str.isalpha
    """
    return _vec_string(a, bool_, 'isalpha')


@array_function_dispatch(_unary_op_dispatcher)
def isdigit(a):
    """
    Returns true for each element if all characters in the string are
    digits and there is at least one character, false otherwise.

    Calls `str.isdigit` element-wise.

    For 8-bit strings, this method is locale-dependent.

    Parameters
    ----------
    a : array_like of str or unicode

    Returns
    -------
    out : ndarray
        Output array of bools

    See also
    --------
    str.isdigit
    """
    return _vec_string(a, bool_, 'isdigit')


@array_function_dispatch(_unary_op_dispatcher)
def islower(a):
    """
    Returns true for each element if all cased characters in the
    string are lowercase and there is at least one cased character,
    false otherwise.

    Calls `str.islower` element-wise.

    For 8-bit strings, this method is locale-dependent.

    Parameters
    ----------
    a : array_like of str or unicode

    Returns
    -------
    out : ndarray
        Output array of bools

    See also
    --------
    str.islower
    """
    return _vec_string(a, bool_, 'islower')


@array_function_dispatch(_unary_op_dispatcher)
def isspace(a):
    """
    Returns true for each element if there are only whitespace
    characters in the string and there is at least one character,
    false otherwise.

    Calls `str.isspace` element-wise.

    For 8-bit strings, this method is locale-dependent.

    Parameters
    ----------
    a : array_like of str or unicode

    Returns
    -------
    out : ndarray
        Output array of bools

    See also
    --------
    str.isspace
    """
    return _vec_string(a, bool_, 'isspace')


@array_function_dispatch(_unary_op_dispatcher)
def istitle(a):
    """
    Returns true for each element if the element is a titlecased
    string and there is at least one character, false otherwise.

    Call `str.istitle` element-wise.

    For 8-bit strings, this method is locale-dependent.

    Parameters
    ----------
    a : array_like of str or unicode

    Returns
    -------
    out : ndarray
        Output array of bools

    See also
    --------
    str.istitle
    """
    return _vec_string(a, bool_, 'istitle')


@array_function_dispatch(_unary_op_dispatcher)
def isupper(a):
    """
    Returns true for each element if all cased characters in the
    string are uppercase and there is at least one character, false
    otherwise.

    Call `str.isupper` element-wise.

    For 8-bit strings, this method is locale-dependent.

    Parameters
    ----------
    a : array_like of str or unicode

    Returns
    -------
    out : ndarray
        Output array of bools

    See also
    --------
    str.isupper
    """
    return _vec_string(a, bool_, 'isupper')


def _join_dispatcher(sep, seq):
    return (sep, seq)


@array_function_dispatch(_join_dispatcher)
def join(sep, seq):
    """
    Return a string which is the concatenation of the strings in the
    sequence `seq`.

    Calls `str.join` element-wise.

    Parameters
    ----------
    sep : array_like of str or unicode
    seq : array_like of str or unicode

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input types

    See also
    --------
    str.join
    """
    return _to_string_or_unicode_array(
        _vec_string(sep, object_, 'join', (seq,)))



def _just_dispatcher(a, width, fillchar=None):
    return (a,)


@array_function_dispatch(_just_dispatcher)
def ljust(a, width, fillchar=' '):
    """
    Return an array with the elements of `a` left-justified in a
    string of length `width`.

    Calls `str.ljust` element-wise.

    Parameters
    ----------
    a : array_like of str or unicode

    width : int
        The length of the resulting strings
    fillchar : str or unicode, optional
        The character to use for padding

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input type

    See also
    --------
    str.ljust

    """
    a_arr = numpy.asarray(a)
    width_arr = numpy.asarray(width)
    size = long(numpy.max(width_arr.flat))
    if numpy.issubdtype(a_arr.dtype, numpy.string_):
        fillchar = asbytes(fillchar)
    return _vec_string(
        a_arr, (a_arr.dtype.type, size), 'ljust', (width_arr, fillchar))


@array_function_dispatch(_unary_op_dispatcher)
def lower(a):
    """
    Return an array with the elements converted to lowercase.

    Call `str.lower` element-wise.

    For 8-bit strings, this method is locale-dependent.

    Parameters
    ----------
    a : array_like, {str, unicode}
        Input array.

    Returns
    -------
    out : ndarray, {str, unicode}
        Output array of str or unicode, depending on input type

    See also
    --------
    str.lower

    Examples
    --------
    >>> c = np.array(['A1B C', '1BCA', 'BCA1']); c
    array(['A1B C', '1BCA', 'BCA1'],
          dtype='|S5')
    >>> np.char.lower(c)
    array(['a1b c', '1bca', 'bca1'],
          dtype='|S5')

    """
    a_arr = numpy.asarray(a)
    return _vec_string(a_arr, a_arr.dtype, 'lower')


def _strip_dispatcher(a, chars=None):
    return (a,)


@array_function_dispatch(_strip_dispatcher)
def lstrip(a, chars=None):
    """
    For each element in `a`, return a copy with the leading characters
    removed.

    Calls `str.lstrip` element-wise.

    Parameters
    ----------
    a : array-like, {str, unicode}
        Input array.

    chars : {str, unicode}, optional
        The `chars` argument is a string specifying the set of
        characters to be removed. If omitted or None, the `chars`
        argument defaults to removing whitespace. The `chars` argument
        is not a prefix; rather, all combinations of its values are
        stripped.

    Returns
    -------
    out : ndarray, {str, unicode}
        Output array of str or unicode, depending on input type

    See also
    --------
    str.lstrip

    Examples
    --------
    >>> c = np.array(['aAaAaA', '  aA  ', 'abBABba'])
    >>> c
    array(['aAaAaA', '  aA  ', 'abBABba'],
        dtype='|S7')

    The 'a' variable is unstripped from c[1] because whitespace leading.

    >>> np.char.lstrip(c, 'a')
    array(['AaAaA', '  aA  ', 'bBABba'],
        dtype='|S7')


    >>> np.char.lstrip(c, 'A') # leaves c unchanged
    array(['aAaAaA', '  aA  ', 'abBABba'],
        dtype='|S7')
    >>> (np.char.lstrip(c, ' ') == np.char.lstrip(c, '')).all()
    ... # XXX: is this a regression? this line now returns False
    ... # np.char.lstrip(c,'') does not modify c at all.
    True
    >>> (np.char.lstrip(c, ' ') == np.char.lstrip(c, None)).all()
    True

    """
    a_arr = numpy.asarray(a)
    return _vec_string(a_arr, a_arr.dtype, 'lstrip', (chars,))


def _partition_dispatcher(a, sep):
    return (a,)


@array_function_dispatch(_partition_dispatcher)
def partition(a, sep):
    """
    Partition each element in `a` around `sep`.

    Calls `str.partition` element-wise.

    For each element in `a`, split the element as the first
    occurrence of `sep`, and return 3 strings containing the part
    before the separator, the separator itself, and the part after
    the separator. If the separator is not found, return 3 strings
    containing the string itself, followed by two empty strings.

    Parameters
    ----------
    a : array_like, {str, unicode}
        Input array
    sep : {str, unicode}
        Separator to split each string element in `a`.

    Returns
    -------
    out : ndarray, {str, unicode}
        Output array of str or unicode, depending on input type.
        The output array will have an extra dimension with 3
        elements per input element.

    See also
    --------
    str.partition

    """
    return _to_string_or_unicode_array(
        _vec_string(a, object_, 'partition', (sep,)))


def _replace_dispatcher(a, old, new, count=None):
    return (a,)


@array_function_dispatch(_replace_dispatcher)
def replace(a, old, new, count=None):
    """
    For each element in `a`, return a copy of the string with all
    occurrences of substring `old` replaced by `new`.

    Calls `str.replace` element-wise.

    Parameters
    ----------
    a : array-like of str or unicode

    old, new : str or unicode

    count : int, optional
        If the optional argument `count` is given, only the first
        `count` occurrences are replaced.

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input type

    See also
    --------
    str.replace

    """
    return _to_string_or_unicode_array(
        _vec_string(
            a, object_, 'replace', [old, new] + _clean_args(count)))


@array_function_dispatch(_count_dispatcher)
def rfind(a, sub, start=0, end=None):
    """
    For each element in `a`, return the highest index in the string
    where substring `sub` is found, such that `sub` is contained
    within [`start`, `end`].

    Calls `str.rfind` element-wise.

    Parameters
    ----------
    a : array-like of str or unicode

    sub : str or unicode

    start, end : int, optional
        Optional arguments `start` and `end` are interpreted as in
        slice notation.

    Returns
    -------
    out : ndarray
       Output array of ints.  Return -1 on failure.

    See also
    --------
    str.rfind

    """
    return _vec_string(
        a, integer, 'rfind', [sub, start] + _clean_args(end))


@array_function_dispatch(_count_dispatcher)
def rindex(a, sub, start=0, end=None):
    """
    Like `rfind`, but raises `ValueError` when the substring `sub` is
    not found.

    Calls `str.rindex` element-wise.

    Parameters
    ----------
    a : array-like of str or unicode

    sub : str or unicode

    start, end : int, optional

    Returns
    -------
    out : ndarray
       Output array of ints.

    See also
    --------
    rfind, str.rindex

    """
    return _vec_string(
        a, integer, 'rindex', [sub, start] + _clean_args(end))


@array_function_dispatch(_just_dispatcher)
def rjust(a, width, fillchar=' '):
    """
    Return an array with the elements of `a` right-justified in a
    string of length `width`.

    Calls `str.rjust` element-wise.

    Parameters
    ----------
    a : array_like of str or unicode

    width : int
        The length of the resulting strings
    fillchar : str or unicode, optional
        The character to use for padding

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input type

    See also
    --------
    str.rjust

    """
    a_arr = numpy.asarray(a)
    width_arr = numpy.asarray(width)
    size = long(numpy.max(width_arr.flat))
    if numpy.issubdtype(a_arr.dtype, numpy.string_):
        fillchar = asbytes(fillchar)
    return _vec_string(
        a_arr, (a_arr.dtype.type, size), 'rjust', (width_arr, fillchar))


@array_function_dispatch(_partition_dispatcher)
def rpartition(a, sep):
    """
    Partition (split) each element around the right-most separator.

    Calls `str.rpartition` element-wise.

    For each element in `a`, split the element as the last
    occurrence of `sep`, and return 3 strings containing the part
    before the separator, the separator itself, and the part after
    the separator. If the separator is not found, return 3 strings
    containing the string itself, followed by two empty strings.

    Parameters
    ----------
    a : array_like of str or unicode
        Input array
    sep : str or unicode
        Right-most separator to split each element in array.

    Returns
    -------
    out : ndarray
        Output array of string or unicode, depending on input
        type.  The output array will have an extra dimension with
        3 elements per input element.

    See also
    --------
    str.rpartition

    """
    return _to_string_or_unicode_array(
        _vec_string(a, object_, 'rpartition', (sep,)))


def _split_dispatcher(a, sep=None, maxsplit=None):
    return (a,)


@array_function_dispatch(_split_dispatcher)
def rsplit(a, sep=None, maxsplit=None):
    """
    For each element in `a`, return a list of the words in the
    string, using `sep` as the delimiter string.

    Calls `str.rsplit` element-wise.

    Except for splitting from the right, `rsplit`
    behaves like `split`.

    Parameters
    ----------
    a : array_like of str or unicode

    sep : str or unicode, optional
        If `sep` is not specified or `None`, any whitespace string
        is a separator.
    maxsplit : int, optional
        If `maxsplit` is given, at most `maxsplit` splits are done,
        the rightmost ones.

    Returns
    -------
    out : ndarray
       Array of list objects

    See also
    --------
    str.rsplit, split

    """
    # This will return an array of lists of different sizes, so we
    # leave it as an object array
    return _vec_string(
        a, object_, 'rsplit', [sep] + _clean_args(maxsplit))


def _strip_dispatcher(a, chars=None):
    return (a,)


@array_function_dispatch(_strip_dispatcher)
def rstrip(a, chars=None):
    """
    For each element in `a`, return a copy with the trailing
    characters removed.

    Calls `str.rstrip` element-wise.

    Parameters
    ----------
    a : array-like of str or unicode

    chars : str or unicode, optional
       The `chars` argument is a string specifying the set of
       characters to be removed. If omitted or None, the `chars`
       argument defaults to removing whitespace. The `chars` argument
       is not a suffix; rather, all combinations of its values are
       stripped.

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input type

    See also
    --------
    str.rstrip

    Examples
    --------
    >>> c = np.array(['aAaAaA', 'abBABba'], dtype='S7'); c
    array(['aAaAaA', 'abBABba'],
        dtype='|S7')
    >>> np.char.rstrip(c, 'a')
    array(['aAaAaA', 'abBABb'],
        dtype='|S7')
    >>> np.char.rstrip(c, 'A')
    array(['aAaAa', 'abBABba'],
        dtype='|S7')

    """
    a_arr = numpy.asarray(a)
    return _vec_string(a_arr, a_arr.dtype, 'rstrip', (chars,))


@array_function_dispatch(_split_dispatcher)
def split(a, sep=None, maxsplit=None):
    """
    For each element in `a`, return a list of the words in the
    string, using `sep` as the delimiter string.

    Calls `str.split` element-wise.

    Parameters
    ----------
    a : array_like of str or unicode

    sep : str or unicode, optional
       If `sep` is not specified or `None`, any whitespace string is a
       separator.

    maxsplit : int, optional
        If `maxsplit` is given, at most `maxsplit` splits are done.

    Returns
    -------
    out : ndarray
        Array of list objects

    See also
    --------
    str.split, rsplit

    """
    # This will return an array of lists of different sizes, so we
    # leave it as an object array
    return _vec_string(
        a, object_, 'split', [sep] + _clean_args(maxsplit))


def _splitlines_dispatcher(a, keepends=None):
    return (a,)


@array_function_dispatch(_splitlines_dispatcher)
def splitlines(a, keepends=None):
    """
    For each element in `a`, return a list of the lines in the
    element, breaking at line boundaries.

    Calls `str.splitlines` element-wise.

    Parameters
    ----------
    a : array_like of str or unicode

    keepends : bool, optional
        Line breaks are not included in the resulting list unless
        keepends is given and true.

    Returns
    -------
    out : ndarray
        Array of list objects

    See also
    --------
    str.splitlines

    """
    return _vec_string(
        a, object_, 'splitlines', _clean_args(keepends))


def _startswith_dispatcher(a, prefix, start=None, end=None):
    return (a,)


@array_function_dispatch(_startswith_dispatcher)
def startswith(a, prefix, start=0, end=None):
    """
    Returns a boolean array which is `True` where the string element
    in `a` starts with `prefix`, otherwise `False`.

    Calls `str.startswith` element-wise.

    Parameters
    ----------
    a : array_like of str or unicode

    prefix : str

    start, end : int, optional
        With optional `start`, test beginning at that position. With
        optional `end`, stop comparing at that position.

    Returns
    -------
    out : ndarray
        Array of booleans

    See also
    --------
    str.startswith

    """
    return _vec_string(
        a, bool_, 'startswith', [prefix, start] + _clean_args(end))


@array_function_dispatch(_strip_dispatcher)
def strip(a, chars=None):
    """
    For each element in `a`, return a copy with the leading and
    trailing characters removed.

    Calls `str.strip` element-wise.

    Parameters
    ----------
    a : array-like of str or unicode

    chars : str or unicode, optional
       The `chars` argument is a string specifying the set of
       characters to be removed. If omitted or None, the `chars`
       argument defaults to removing whitespace. The `chars` argument
       is not a prefix or suffix; rather, all combinations of its
       values are stripped.

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input type

    See also
    --------
    str.strip

    Examples
    --------
    >>> c = np.array(['aAaAaA', '  aA  ', 'abBABba'])
    >>> c
    array(['aAaAaA', '  aA  ', 'abBABba'],
        dtype='|S7')
    >>> np.char.strip(c)
    array(['aAaAaA', 'aA', 'abBABba'],
        dtype='|S7')
    >>> np.char.strip(c, 'a') # 'a' unstripped from c[1] because whitespace leads
    array(['AaAaA', '  aA  ', 'bBABb'],
        dtype='|S7')
    >>> np.char.strip(c, 'A') # 'A' unstripped from c[1] because (unprinted) ws trails
    array(['aAaAa', '  aA  ', 'abBABba'],
        dtype='|S7')

    """
    a_arr = numpy.asarray(a)
    return _vec_string(a_arr, a_arr.dtype, 'strip', _clean_args(chars))


@array_function_dispatch(_unary_op_dispatcher)
def swapcase(a):
    """
    Return element-wise a copy of the string with
    uppercase characters converted to lowercase and vice versa.

    Calls `str.swapcase` element-wise.

    For 8-bit strings, this method is locale-dependent.

    Parameters
    ----------
    a : array_like, {str, unicode}
        Input array.

    Returns
    -------
    out : ndarray, {str, unicode}
        Output array of str or unicode, depending on input type

    See also
    --------
    str.swapcase

    Examples
    --------
    >>> c=np.array(['a1B c','1b Ca','b Ca1','cA1b'],'S5'); c
    array(['a1B c', '1b Ca', 'b Ca1', 'cA1b'],
        dtype='|S5')
    >>> np.char.swapcase(c)
    array(['A1b C', '1B cA', 'B cA1', 'Ca1B'],
        dtype='|S5')

    """
    a_arr = numpy.asarray(a)
    return _vec_string(a_arr, a_arr.dtype, 'swapcase')


@array_function_dispatch(_unary_op_dispatcher)
def title(a):
    """
    Return element-wise title cased version of string or unicode.

    Title case words start with uppercase characters, all remaining cased
    characters are lowercase.

    Calls `str.title` element-wise.

    For 8-bit strings, this method is locale-dependent.

    Parameters
    ----------
    a : array_like, {str, unicode}
        Input array.

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input type

    See also
    --------
    str.title

    Examples
    --------
    >>> c=np.array(['a1b c','1b ca','b ca1','ca1b'],'S5'); c
    array(['a1b c', '1b ca', 'b ca1', 'ca1b'],
        dtype='|S5')
    >>> np.char.title(c)
    array(['A1B C', '1B Ca', 'B Ca1', 'Ca1B'],
        dtype='|S5')

    """
    a_arr = numpy.asarray(a)
    return _vec_string(a_arr, a_arr.dtype, 'title')


def _translate_dispatcher(a, table, deletechars=None):
    return (a,)


@array_function_dispatch(_translate_dispatcher)
def translate(a, table, deletechars=None):
    """
    For each element in `a`, return a copy of the string where all
    characters occurring in the optional argument `deletechars` are
    removed, and the remaining characters have been mapped through the
    given translation table.

    Calls `str.translate` element-wise.

    Parameters
    ----------
    a : array-like of str or unicode

    table : str of length 256

    deletechars : str

    Returns
    -------
    out : ndarray
        Output array of str or unicode, depending on input type

    See also
    --------
    str.translate

    """
    a_arr = numpy.asarray(a)
    if issubclass(a_arr.dtype.type, unicode_):
        return _vec_string(
            a_arr, a_arr.dtype, 'translate', (table,))
    else:
        return _vec_string(
            a_arr, a_arr.dtype, 'translate', [table] + _clean_args(deletechars))


@array_function_dispatch(_unary_op_dispatcher)
def upper(a):
    """
    Return an array with the elements converted to uppercase.

    Calls `str.upper` element-wise.

    For 8-bit strings, this method is locale-dependent.

    Parameters
    ----------
    a : array_like, {str, unicode}
        Input array.

    Returns
    -------
    out : ndarray, {str, unicode}
        Output array of str or unicode, depending on input type

    See also
    --------
    str.upper

    Examples
    --------
    >>> c = np.array(['a1b c', '1bca', 'bca1']); c
    array(['a1b c', '1bca', 'bca1'],
        dtype='|S5')
    >>> np.char.upper(c)
    array(['A1B C', '1BCA', 'BCA1'],
        dtype='|S5')

    """
    a_arr = numpy.asarray(a)
    return _vec_string(a_arr, a_arr.dtype, 'upper')


def _zfill_dispatcher(a, width):
    return (a,)


@array_function_dispatch(_zfill_dispatcher)
def zfill(a, width):
    """
    Return the numeric string left-filled with zeros

    Calls `str.zfill` element-wise.

    Parameters
    ----------
    a : array_like, {str, unicode}
        Input array.
    width : int
        Width of string to left-fill elements in `a`.

    Returns
    -------
    out : ndarray, {str, unicode}
        Output array of str or unicode, depending on input type

    See also
    --------
    str.zfill

    """
    a_arr = numpy.asarray(a)
    width_arr = numpy.asarray(width)
    size = long(numpy.max(width_arr.flat))
    return _vec_string(
        a_arr, (a_arr.dtype.type, size), 'zfill', (width_arr,))


@array_function_dispatch(_unary_op_dispatcher)
def isnumeric(a):
    """
    For each element, return True if there are only numeric
    characters in the element.

    Calls `unicode.isnumeric` element-wise.

    Numeric characters include digit characters, and all characters
    that have the Unicode numeric value property, e.g. ``U+2155,
    VULGAR FRACTION ONE FIFTH``.

    Parameters
    ----------
    a : array_like, unicode
        Input array.

    Returns
    -------
    out : ndarray, bool
        Array of booleans of same shape as `a`.

    See also
    --------
    unicode.isnumeric

    """
    if _use_unicode(a) != unicode_:
        raise TypeError("isnumeric is only available for Unicode strings and arrays")
    return _vec_string(a, bool_, 'isnumeric')


@array_function_dispatch(_unary_op_dispatcher)
def isdecimal(a):
    """
    For each element, return True if there are only decimal
    characters in the element.

    Calls `unicode.isdecimal` element-wise.

    Decimal characters include digit characters, and all characters
    that that can be used to form decimal-radix numbers,
    e.g. ``U+0660, ARABIC-INDIC DIGIT ZERO``.

    Parameters
    ----------
    a : array_like, unicode
        Input array.

    Returns
    -------
    out : ndarray, bool
        Array of booleans identical in shape to `a`.

    See also
    --------
    unicode.isdecimal

    """
    if _use_unicode(a) != unicode_:
        raise TypeError("isnumeric is only available for Unicode strings and arrays")
    return _vec_string(a, bool_, 'isdecimal')


@set_module('numpy')
class chararray(ndarray):
    """
    chararray(shape, itemsize=1, unicode=False, buffer=None, offset=0,
              strides=None, order=None)

    Provides a convenient view on arrays of string and unicode values.

    .. note::
       The `chararray` class exists for backwards compatibility with
       Numarray, it is not recommended for new development. Starting from numpy
       1.4, if one needs arrays of strings, it is recommended to use arrays of
       `dtype` `object_`, `string_` or `unicode_`, and use the free functions
       in the `numpy.char` module for fast vectorized string operations.

    Versus a regular NumPy array of type `str` or `unicode`, this
    class adds the following functionality:

      1) values automatically have whitespace removed from the end
         when indexed

      2) comparison operators automatically remove whitespace from the
         end when comparing values

      3) vectorized string operations are provided as methods
         (e.g. `.endswith`) and infix operators (e.g. ``"+", "*", "%"``)

    chararrays should be created using `numpy.char.array` or
    `numpy.char.asarray`, rather than this constructor directly.

    This constructor creates the array, using `buffer` (with `offset`
    and `strides`) if it is not ``None``. If `buffer` is ``None``, then
    constructs a new array with `strides` in "C order", unless both
    ``len(shape) >= 2`` and ``order='Fortran'``, in which case `strides`
    is in "Fortran order".

    Methods
    -------
    astype
    argsort
    copy
    count
    decode
    dump
    dumps
    encode
    endswith
    expandtabs
    fill
    find
    flatten
    getfield
    index
    isalnum
    isalpha
    isdecimal
    isdigit
    islower
    isnumeric
    isspace
    istitle
    isupper
    item
    join
    ljust
    lower
    lstrip
    nonzero
    put
    ravel
    repeat
    replace
    reshape
    resize
    rfind
    rindex
    rjust
    rsplit
    rstrip
    searchsorted
    setfield
    setflags
    sort
    split
    splitlines
    squeeze
    startswith
    strip
    swapaxes
    swapcase
    take
    title
    tofile
    tolist
    tostring
    translate
    transpose
    upper
    view
    zfill

    Parameters
    ----------
    shape : tuple
        Shape of the array.
    itemsize : int, optional
        Length of each array element, in number of characters. Default is 1.
    unicode : bool, optional
        Are the array elements of type unicode (True) or string (False).
        Default is False.
    buffer : int, optional
        Memory address of the start of the array data.  Default is None,
        in which case a new array is created.
    offset : int, optional
        Fixed stride displacement from the beginning of an axis?
        Default is 0. Needs to be >=0.
    strides : array_like of ints, optional
        Strides for the array (see `ndarray.strides` for full description).
        Default is None.
    order : {'C', 'F'}, optional
        The order in which the array data is stored in memory: 'C' ->
        "row major" order (the default), 'F' -> "column major"
        (Fortran) order.

    Examples
    --------
    >>> charar = np.chararray((3, 3))
    >>> charar[:] = 'a'
    >>> charar
    chararray([['a', 'a', 'a'],
           ['a', 'a', 'a'],
           ['a', 'a', 'a']],
          dtype='|S1')

    >>> charar = np.chararray(charar.shape, itemsize=5)
    >>> charar[:] = 'abc'
    >>> charar
    chararray([['abc', 'abc', 'abc'],
           ['abc', 'abc', 'abc'],
           ['abc', 'abc', 'abc']],
          dtype='|S5')

    """
    def __new__(subtype, shape, itemsize=1, unicode=False, buffer=None,
                offset=0, strides=None, order='C'):
        global _globalvar

        if unicode:
            dtype = unicode_
        else:
            dtype = string_

        # force itemsize to be a Python long, since using NumPy integer
        # types results in itemsize.itemsize being used as the size of
        # strings in the new array.
        itemsize = long(itemsize)

        if sys.version_info[0] >= 3 and isinstance(buffer, _unicode):
            # On Py3, unicode objects do not have the buffer interface
            filler = buffer
            buffer = None
        else:
            filler = None

        _globalvar = 1
        if buffer is None:
            self = ndarray.__new__(subtype, shape, (dtype, itemsize),
                                   order=order)
        else:
            self = ndarray.__new__(subtype, shape, (dtype, itemsize),
                                   buffer=buffer,
                                   offset=offset, strides=strides,
                                   order=order)
        if filler is not None:
            self[...] = filler
        _globalvar = 0
        return self

    def __array_finalize__(self, obj):
        # The b is a special case because it is used for reconstructing.
        if not _globalvar and self.dtype.char not in 'SUbc':
            raise ValueError("Can only create a chararray from string data.")

    def __getitem__(self, obj):
        val = ndarray.__getitem__(self, obj)

        if isinstance(val, character):
            temp = val.rstrip()
            if _len(temp) == 0:
                val = ''
            else:
                val = temp

        return val

    # IMPLEMENTATION NOTE: Most of the methods of this class are
    # direct delegations to the free functions in this module.
    # However, those that return an array of strings should instead
    # return a chararray, so some extra wrapping is required.

    def __eq__(self, other):
        """
        Return (self == other) element-wise.

        See also
        --------
        equal
        """
        return equal(self, other)

    def __ne__(self, other):
        """
        Return (self != other) element-wise.

        See also
        --------
        not_equal
        """
        return not_equal(self, other)

    def __ge__(self, other):
        """
        Return (self >= other) element-wise.

        See also
        --------
        greater_equal
        """
        return greater_equal(self, other)

    def __le__(self, other):
        """
        Return (self <= other) element-wise.

        See also
        --------
        less_equal
        """
        return less_equal(self, other)

    def __gt__(self, other):
        """
        Return (self > other) element-wise.

        See also
        --------
        greater
        """
        return greater(self, other)

    def __lt__(self, other):
        """
        Return (self < other) element-wise.

        See also
        --------
        less
        """
        return less(self, other)

    def __add__(self, other):
        """
        Return (self + other), that is string concatenation,
        element-wise for a pair of array_likes of str or unicode.

        See also
        --------
        add
        """
        return asarray(add(self, other))

    def __radd__(self, other):
        """
        Return (other + self), that is string concatenation,
        element-wise for a pair of array_likes of `string_` or `unicode_`.

        See also
        --------
        add
        """
        return asarray(add(numpy.asarray(other), self))

    def __mul__(self, i):
        """
        Return (self * i), that is string multiple concatenation,
        element-wise.

        See also
        --------
        multiply
        """
        return asarray(multiply(self, i))

    def __rmul__(self, i):
        """
        Return (self * i), that is string multiple concatenation,
        element-wise.

        See also
        --------
        multiply
        """
        return asarray(multiply(self, i))

    def __mod__(self, i):
        """
        Return (self % i), that is pre-Python 2.6 string formatting
        (iterpolation), element-wise for a pair of array_likes of `string_`
        or `unicode_`.

        See also
        --------
        mod
        """
        return asarray(mod(self, i))

    def __rmod__(self, other):
        return NotImplemented

    def argsort(self, axis=-1, kind='quicksort', order=None):
        """
        Return the indices that sort the array lexicographically.

        For full documentation see `numpy.argsort`, for which this method is
        in fact merely a "thin wrapper."

        Examples
        --------
        >>> c = np.array(['a1b c', '1b ca', 'b ca1', 'Ca1b'], 'S5')
        >>> c = c.view(np.chararray); c
        chararray(['a1b c', '1b ca', 'b ca1', 'Ca1b'],
              dtype='|S5')
        >>> c[c.argsort()]
        chararray(['1b ca', 'Ca1b', 'a1b c', 'b ca1'],
              dtype='|S5')

        """
        return self.__array__().argsort(axis, kind, order)
    argsort.__doc__ = ndarray.argsort.__doc__

    def capitalize(self):
        """
        Return a copy of `self` with only the first character of each element
        capitalized.

        See also
        --------
        char.capitalize

        """
        return asarray(capitalize(self))

    def center(self, width, fillchar=' '):
        """
        Return a copy of `self` with its elements centered in a
        string of length `width`.

        See also
        --------
        center
        """
        return asarray(center(self, width, fillchar))

    def count(self, sub, start=0, end=None):
        """
        Returns an array with the number of non-overlapping occurrences of
        substring `sub` in the range [`start`, `end`].

        See also
        --------
        char.count

        """
        return count(self, sub, start, end)

    def decode(self, encoding=None, errors=None):
        """
        Calls `str.decode` element-wise.

        See also
        --------
        char.decode

        """
        return decode(self, encoding, errors)

    def encode(self, encoding=None, errors=None):
        """
        Calls `str.encode` element-wise.

        See also
        --------
        char.encode

        """
        return encode(self, encoding, errors)

    def endswith(self, suffix, start=0, end=None):
        """
        Returns a boolean array which is `True` where the string element
        in `self` ends with `suffix`, otherwise `False`.

        See also
        --------
        char.endswith

        """
        return endswith(self, suffix, start, end)

    def expandtabs(self, tabsize=8):
        """
        Return a copy of each string element where all tab characters are
        replaced by one or more spaces.

        See also
        --------
        char.expandtabs

        """
        return asarray(expandtabs(self, tabsize))

    def find(self, sub, start=0, end=None):
        """
        For each element, return the lowest index in the string where
        substring `sub` is found.

        See also
        --------
        char.find

        """
        return find(self, sub, start, end)

    def index(self, sub, start=0, end=None):
        """
        Like `find`, but raises `ValueError` when the substring is not found.

        See also
        --------
        char.index

        """
        return index(self, sub, start, end)

    def isalnum(self):
        """
        Returns true for each element if all characters in the string
        are alphanumeric and there is at least one character, false
        otherwise.

        See also
        --------
        char.isalnum

        """
        return isalnum(self)

    def isalpha(self):
        """
        Returns true for each element if all characters in the string
        are alphabetic and there is at least one character, false
        otherwise.

        See also
        --------
        char.isalpha

        """
        return isalpha(self)

    def isdigit(self):
        """
        Returns true for each element if all characters in the string are
        digits and there is at least one character, false otherwise.

        See also
        --------
        char.isdigit

        """
        return isdigit(self)

    def islower(self):
        """
        Returns true for each element if all cased characters in the
        string are lowercase and there is at least one cased character,
        false otherwise.

        See also
        --------
        char.islower

        """
        return islower(self)

    def isspace(self):
        """
        Returns true for each element if there are only whitespace
        characters in the string and there is at least one character,
        false otherwise.

        See also
        --------
        char.isspace

        """
        return isspace(self)

    def istitle(self):
        """
        Returns true for each element if the element is a titlecased
        string and there is at least one character, false otherwise.

        See also
        --------
        char.istitle

        """
        return istitle(self)

    def isupper(self):
        """
        Returns true for each element if all cased characters in the
        string are uppercase and there is at least one character, false
        otherwise.

        See also
        --------
        char.isupper

        """
        return isupper(self)

    def join(self, seq):
        """
        Return a string which is the concatenation of the strings in the
        sequence `seq`.

        See also
        --------
        char.join

        """
        return join(self, seq)

    def ljust(self, width, fillchar=' '):
        """
        Return an array with the elements of `self` left-justified in a
        string of length `width`.

        See also
        --------
        char.ljust

        """
        return asarray(ljust(self, width, fillchar))

    def lower(self):
        """
        Return an array with the elements of `self` converted to
        lowercase.

        See also
        --------
        char.lower

        """
        return asarray(lower(self))

    def lstrip(self, chars=None):
        """
        For each element in `self`, return a copy with the leading characters
        removed.

        See also
        --------
        char.lstrip

        """
        return asarray(lstrip(self, chars))

    def partition(self, sep):
        """
        Partition each element in `self` around `sep`.

        See also
        --------
        partition
        """
        return asarray(partition(self, sep))

    def replace(self, old, new, count=None):
        """
        For each element in `self`, return a copy of the string with all
        occurrences of substring `old` replaced by `new`.

        See also
        --------
        char.replace

        """
        return asarray(replace(self, old, new, count))

    def rfind(self, sub, start=0, end=None):
        """
        For each element in `self`, return the highest index in the string
        where substring `sub` is found, such that `sub` is contained
        within [`start`, `end`].

        See also
        --------
        char.rfind

        """
        return rfind(self, sub, start, end)

    def rindex(self, sub, start=0, end=None):
        """
        Like `rfind`, but raises `ValueError` when the substring `sub` is
        not found.

        See also
        --------
        char.rindex

        """
        return rindex(self, sub, start, end)

    def rjust(self, width, fillchar=' '):
        """
        Return an array with the elements of `self`
        right-justified in a string of length `width`.

        See also
        --------
        char.rjust

        """
        return asarray(rjust(self, width, fillchar))

    def rpartition(self, sep):
        """
        Partition each element in `self` around `sep`.

        See also
        --------
        rpartition
        """
        return asarray(rpartition(self, sep))

    def rsplit(self, sep=None, maxsplit=None):
        """
        For each element in `self`, return a list of the words in
        the string, using `sep` as the delimiter string.

        See also
        --------
        char.rsplit

        """
        return rsplit(self, sep, maxsplit)

    def rstrip(self, chars=None):
        """
        For each element in `self`, return a copy with the trailing
        characters removed.

        See also
        --------
        char.rstrip

        """
        return asarray(rstrip(self, chars))

    def split(self, sep=None, maxsplit=None):
        """
        For each element in `self`, return a list of the words in the
        string, using `sep` as the delimiter string.

        See also
        --------
        char.split

        """
        return split(self, sep, maxsplit)

    def splitlines(self, keepends=None):
        """
        For each element in `self`, return a list of the lines in the
        element, breaking at line boundaries.

        See also
        --------
        char.splitlines

        """
        return splitlines(self, keepends)

    def startswith(self, prefix, start=0, end=None):
        """
        Returns a boolean array which is `True` where the string element
        in `self` starts with `prefix`, otherwise `False`.

        See also
        --------
        char.startswith

        """
        return startswith(self, prefix, start, end)

    def strip(self, chars=None):
        """
        For each element in `self`, return a copy with the leading and
        trailing characters removed.

        See also
        --------
        char.strip

        """
        return asarray(strip(self, chars))

    def swapcase(self):
        """
        For each element in `self`, return a copy of the string with
        uppercase characters converted to lowercase and vice versa.

        See also
        --------
        char.swapcase

        """
        return asarray(swapcase(self))

    def title(self):
        """
        For each element in `self`, return a titlecased version of the
        string: words start with uppercase characters, all remaining cased
        characters are lowercase.

        See also
        --------
        char.title

        """
        return asarray(title(self))

    def translate(self, table, deletechars=None):
        """
        For each element in `self`, return a copy of the string where
        all characters occurring in the optional argument
        `deletechars` are removed, and the remaining characters have
        been mapped through the given translation table.

        See also
        --------
        char.translate

        """
        return asarray(translate(self, table, deletechars))

    def upper(self):
        """
        Return an array with the elements of `self` converted to
        uppercase.

        See also
        --------
        char.upper

        """
        return asarray(upper(self))

    def zfill(self, width):
        """
        Return the numeric string left-filled with zeros in a string of
        length `width`.

        See also
        --------
        char.zfill

        """
        return asarray(zfill(self, width))

    def isnumeric(self):
        """
        For each element in `self`, return True if there are only
        numeric characters in the element.

        See also
        --------
        char.isnumeric

        """
        return isnumeric(self)

    def isdecimal(self):
        """
        For each element in `self`, return True if there are only
        decimal characters in the element.

        See also
        --------
        char.isdecimal

        """
        return isdecimal(self)


def array(obj, itemsize=None, copy=True, unicode=None, order=None):
    """
    Create a `chararray`.

    .. note::
       This class is provided for numarray backward-compatibility.
       New code (not concerned with numarray compatibility) should use
       arrays of type `string_` or `unicode_` and use the free functions
       in :mod:`numpy.char <numpy.core.defchararray>` for fast
       vectorized string operations instead.

    Versus a regular NumPy array of type `str` or `unicode`, this
    class adds the following functionality:

      1) values automatically have whitespace removed from the end
         when indexed

      2) comparison operators automatically remove whitespace from the
         end when comparing values

      3) vectorized string operations are provided as methods
         (e.g. `str.endswith`) and infix operators (e.g. ``+, *, %``)

    Parameters
    ----------
    obj : array of str or unicode-like

    itemsize : int, optional
        `itemsize` is the number of characters per scalar in the
        resulting array.  If `itemsize` is None, and `obj` is an
        object array or a Python list, the `itemsize` will be
        automatically determined.  If `itemsize` is provided and `obj`
        is of type str or unicode, then the `obj` string will be
        chunked into `itemsize` pieces.

    copy : bool, optional
        If true (default), then the object is copied.  Otherwise, a copy
        will only be made if __array__ returns a copy, if obj is a
        nested sequence, or if a copy is needed to satisfy any of the other
        requirements (`itemsize`, unicode, `order`, etc.).

    unicode : bool, optional
        When true, the resulting `chararray` can contain Unicode
        characters, when false only 8-bit characters.  If unicode is
        `None` and `obj` is one of the following:

          - a `chararray`,
          - an ndarray of type `str` or `unicode`
          - a Python str or unicode object,

        then the unicode setting of the output array will be
        automatically determined.

    order : {'C', 'F', 'A'}, optional
        Specify the order of the array.  If order is 'C' (default), then the
        array will be in C-contiguous order (last-index varies the
        fastest).  If order is 'F', then the returned array
        will be in Fortran-contiguous order (first-index varies the
        fastest).  If order is 'A', then the returned array may
        be in any order (either C-, Fortran-contiguous, or even
        discontiguous).
    """
    if isinstance(obj, (_bytes, _unicode)):
        if unicode is None:
            if isinstance(obj, _unicode):
                unicode = True
            else:
                unicode = False

        if itemsize is None:
            itemsize = _len(obj)
        shape = _len(obj) // itemsize

        if unicode:
            if sys.maxunicode == 0xffff:
                # On a narrow Python build, the buffer for Unicode
                # strings is UCS2, which doesn't match the buffer for
                # NumPy Unicode types, which is ALWAYS UCS4.
                # Therefore, we need to convert the buffer.  On Python
                # 2.6 and later, we can use the utf_32 codec.  Earlier
                # versions don't have that codec, so we convert to a
                # numerical array that matches the input buffer, and
                # then use NumPy to convert it to UCS4.  All of this
                # should happen in native endianness.
                obj = obj.encode('utf_32')
            else:
                obj = _unicode(obj)
        else:
            # Let the default Unicode -> string encoding (if any) take
            # precedence.
            obj = _bytes(obj)

        return chararray(shape, itemsize=itemsize, unicode=unicode,
                         buffer=obj, order=order)

    if isinstance(obj, (list, tuple)):
        obj = numpy.asarray(obj)

    if isinstance(obj, ndarray) and issubclass(obj.dtype.type, character):
        # If we just have a vanilla chararray, create a chararray
        # view around it.
        if not isinstance(obj, chararray):
            obj = obj.view(chararray)

        if itemsize is None:
            itemsize = obj.itemsize
            # itemsize is in 8-bit chars, so for Unicode, we need
            # to divide by the size of a single Unicode character,
            # which for NumPy is always 4
            if issubclass(obj.dtype.type, unicode_):
                itemsize //= 4

        if unicode is None:
            if issubclass(obj.dtype.type, unicode_):
                unicode = True
            else:
                unicode = False

        if unicode:
            dtype = unicode_
        else:
            dtype = string_

        if order is not None:
            obj = numpy.asarray(obj, order=order)
        if (copy or
                (itemsize != obj.itemsize) or
                (not unicode and isinstance(obj, unicode_)) or
                (unicode and isinstance(obj, string_))):
            obj = obj.astype((dtype, long(itemsize)))
        return obj

    if isinstance(obj, ndarray) and issubclass(obj.dtype.type, object):
        if itemsize is None:
            # Since no itemsize was specified, convert the input array to
            # a list so the ndarray constructor will automatically
            # determine the itemsize for us.
            obj = obj.tolist()
            # Fall through to the default case

    if unicode:
        dtype = unicode_
    else:
        dtype = string_

    if itemsize is None:
        val = narray(obj, dtype=dtype, order=order, subok=True)
    else:
        val = narray(obj, dtype=(dtype, itemsize), order=order, subok=True)
    return val.view(chararray)


def asarray(obj, itemsize=None, unicode=None, order=None):
    """
    Convert the input to a `chararray`, copying the data only if
    necessary.

    Versus a regular NumPy array of type `str` or `unicode`, this
    class adds the following functionality:

      1) values automatically have whitespace removed from the end
         when indexed

      2) comparison operators automatically remove whitespace from the
         end when comparing values

      3) vectorized string operations are provided as methods
         (e.g. `str.endswith`) and infix operators (e.g. ``+``, ``*``,``%``)

    Parameters
    ----------
    obj : array of str or unicode-like

    itemsize : int, optional
        `itemsize` is the number of characters per scalar in the
        resulting array.  If `itemsize` is None, and `obj` is an
        object array or a Python list, the `itemsize` will be
        automatically determined.  If `itemsize` is provided and `obj`
        is of type str or unicode, then the `obj` string will be
        chunked into `itemsize` pieces.

    unicode : bool, optional
        When true, the resulting `chararray` can contain Unicode
        characters, when false only 8-bit characters.  If unicode is
        `None` and `obj` is one of the following:

          - a `chararray`,
          - an ndarray of type `str` or 'unicode`
          - a Python str or unicode object,

        then the unicode setting of the output array will be
        automatically determined.

    order : {'C', 'F'}, optional
        Specify the order of the array.  If order is 'C' (default), then the
        array will be in C-contiguous order (last-index varies the
        fastest).  If order is 'F', then the returned array
        will be in Fortran-contiguous order (first-index varies the
        fastest).
    """
    return array(obj, itemsize, copy=False,
                 unicode=unicode, order=order)