/usr/lib/x86_64-linux-gnu/perl5/5.26/Text/CSV_XS.pm is in libtext-csv-xs-perl 1.34-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 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 | package Text::CSV_XS;
# Copyright (c) 2007-2017 H.Merijn Brand. All rights reserved.
# Copyright (c) 1998-2001 Jochen Wiedmann. All rights reserved.
# Copyright (c) 1997 Alan Citterman. All rights reserved.
#
# This program is free software; you can redistribute it and/or
# modify it under the same terms as Perl itself.
# HISTORY
#
# 0.24 -
# H.Merijn Brand (h.m.brand@xs4all.nl)
# 0.10 - 0.23
# Jochen Wiedmann <joe@ispsoft.de>
# Based on (the original) Text::CSV by:
# Alan Citterman <alan@mfgrtl.com>
require 5.006001;
use strict;
use warnings;
require Exporter;
use DynaLoader ();
use Carp;
use vars qw( $VERSION @ISA @EXPORT_OK );
$VERSION = "1.34";
@ISA = qw( DynaLoader Exporter );
@EXPORT_OK = qw( csv );
bootstrap Text::CSV_XS $VERSION;
sub PV { 0 }
sub IV { 1 }
sub NV { 2 }
if ($] < 5.008002) {
no warnings "redefine";
*utf8::decode = sub {};
}
# version
#
# class/object method expecting no arguments and returning the version
# number of Text::CSV. there are no side-effects.
sub version {
return $VERSION;
} # version
# new
#
# class/object method expecting no arguments and returning a reference to
# a newly created Text::CSV object.
my %def_attr = (
eol => '',
sep_char => ',',
quote_char => '"',
escape_char => '"',
binary => 0,
decode_utf8 => 1,
auto_diag => 0,
diag_verbose => 0,
strict => 0,
blank_is_undef => 0,
empty_is_undef => 0,
allow_whitespace => 0,
allow_loose_quotes => 0,
allow_loose_escapes => 0,
allow_unquoted_escape => 0,
always_quote => 0,
quote_empty => 0,
quote_space => 1,
quote_binary => 1,
escape_null => 1,
keep_meta_info => 0,
verbatim => 0,
formula => 0,
types => undef,
callbacks => undef,
_EOF => 0,
_RECNO => 0,
_STATUS => undef,
_FIELDS => undef,
_FFLAGS => undef,
_STRING => undef,
_ERROR_INPUT => undef,
_COLUMN_NAMES => undef,
_BOUND_COLUMNS => undef,
_AHEAD => undef,
);
my %attr_alias = (
quote_always => "always_quote",
verbose_diag => "diag_verbose",
quote_null => "escape_null",
escape => "escape_char",
);
my $last_new_err = Text::CSV_XS->SetDiag (0);
# NOT a method: is also used before bless
sub _unhealthy_whitespace {
my ($self, $aw) = @_;
$aw or return 0; # no checks needed without allow_whitespace
my $quo = $self->{quote};
defined $quo && length ($quo) or $quo = $self->{quote_char};
my $esc = $self->{escape_char};
defined $quo && $quo =~ m/^[ \t]/ and return 1002;
defined $esc && $esc =~ m/^[ \t]/ and return 1002;
return 0;
} # _unhealty_whitespace
sub _check_sanity {
my $self = shift;
my $eol = $self->{eol};
my $sep = $self->{sep};
defined $sep && length ($sep) or $sep = $self->{sep_char};
my $quo = $self->{quote};
defined $quo && length ($quo) or $quo = $self->{quote_char};
my $esc = $self->{escape_char};
# use DP;::diag ("SEP: '", DPeek ($sep),
# "', QUO: '", DPeek ($quo),
# "', ESC: '", DPeek ($esc),"'");
# sep_char should not be undefined
$sep ne "" or return 1008;
length ($sep) > 16 and return 1006;
$sep =~ m/[\r\n]/ and return 1003;
if (defined $quo) {
$quo eq $sep and return 1001;
length ($quo) > 16 and return 1007;
$quo =~ m/[\r\n]/ and return 1003;
}
if (defined $esc) {
$esc eq $sep and return 1001;
$esc =~ m/[\r\n]/ and return 1003;
}
if (defined $eol) {
length ($eol) > 16 and return 1005;
}
return _unhealthy_whitespace ($self, $self->{allow_whitespace});
} # _check_sanity
sub known_attributes {
sort grep !m/^_/ => "sep", "quote", keys %def_attr;
} # known_attributes
sub new {
$last_new_err = Text::CSV_XS->SetDiag (1000,
"usage: my \$csv = Text::CSV_XS->new ([{ option => value, ... }]);");
my $proto = shift;
my $class = ref ($proto) || $proto or return;
@_ > 0 && ref $_[0] ne "HASH" and return;
my $attr = shift || {};
my %attr = map {
my $k = m/^[a-zA-Z]\w+$/ ? lc $_ : $_;
exists $attr_alias{$k} and $k = $attr_alias{$k};
$k => $attr->{$_};
} keys %$attr;
my $sep_aliased = 0;
if (exists $attr{sep}) {
$attr{sep_char} = delete $attr{sep};
$sep_aliased = 1;
}
my $quote_aliased = 0;
if (exists $attr{quote}) {
$attr{quote_char} = delete $attr{quote};
$quote_aliased = 1;
}
exists $attr{formula_handling} and
$attr{formula} = delete $attr{formula_handling};
exists $attr{formula} and
$attr{formula} = _supported_formula (undef, $attr{formula});
for (keys %attr) {
if (m/^[a-z]/ && exists $def_attr{$_}) {
# uncoverable condition false
defined $attr{$_} && m/_char$/ and utf8::decode ($attr{$_});
next;
}
# croak?
$last_new_err = Text::CSV_XS->SetDiag (1000, "INI - Unknown attribute '$_'");
$attr{auto_diag} and error_diag ();
return;
}
if ($sep_aliased) {
my @b = unpack "U0C*", $attr{sep_char};
if (@b > 1) {
$attr{sep} = $attr{sep_char};
$attr{sep_char} = "\0";
}
else {
$attr{sep} = undef;
}
}
if ($quote_aliased and defined $attr{quote_char}) {
my @b = unpack "U0C*", $attr{quote_char};
if (@b > 1) {
$attr{quote} = $attr{quote_char};
$attr{quote_char} = "\0";
}
else {
$attr{quote} = undef;
}
}
my $self = { %def_attr, %attr };
if (my $ec = _check_sanity ($self)) {
$last_new_err = Text::CSV_XS->SetDiag ($ec);
$attr{auto_diag} and error_diag ();
return;
}
if (defined $self->{callbacks} && ref $self->{callbacks} ne "HASH") {
carp "The 'callbacks' attribute is set but is not a hash: ignored\n";
$self->{callbacks} = undef;
}
$last_new_err = Text::CSV_XS->SetDiag (0);
defined $\ && !exists $attr{eol} and $self->{eol} = $\;
bless $self, $class;
defined $self->{types} and $self->types ($self->{types});
$self;
} # new
# Keep in sync with XS!
my %_cache_id = ( # Only expose what is accessed from within PM
quote_char => 0,
escape_char => 1,
sep_char => 2,
sep => 39, # 39 .. 55
binary => 3,
keep_meta_info => 4,
always_quote => 5,
allow_loose_quotes => 6,
allow_loose_escapes => 7,
allow_unquoted_escape => 8,
allow_whitespace => 9,
blank_is_undef => 10,
eol => 11,
quote => 15,
verbatim => 22,
empty_is_undef => 23,
auto_diag => 24,
diag_verbose => 33,
quote_space => 25,
quote_empty => 37,
quote_binary => 32,
escape_null => 31,
decode_utf8 => 35,
_has_ahead => 30,
_has_hooks => 36,
_is_bound => 26, # 26 .. 29
formula => 38,
strict => 42
);
# A `character'
sub _set_attr_C {
my ($self, $name, $val, $ec) = @_;
defined $val or $val = 0;
utf8::decode ($val);
$self->{$name} = $val;
$ec = _check_sanity ($self) and croak ($self->SetDiag ($ec));
$self->_cache_set ($_cache_id{$name}, $val);
} # _set_attr_C
# A flag
sub _set_attr_X {
my ($self, $name, $val) = @_;
defined $val or $val = 0;
$self->{$name} = $val;
$self->_cache_set ($_cache_id{$name}, 0 + $val);
} # _set_attr_X
# A number
sub _set_attr_N {
my ($self, $name, $val) = @_;
$self->{$name} = $val;
$self->_cache_set ($_cache_id{$name}, 0 + $val);
} # _set_attr_N
# Accessor methods.
# It is unwise to change them halfway through a single file!
sub quote_char {
my $self = shift;
if (@_) {
$self->_set_attr_C ("quote_char", shift);
$self->_cache_set ($_cache_id{quote}, "");
}
$self->{quote_char};
} # quote_char
sub quote {
my $self = shift;
if (@_) {
my $quote = shift;
defined $quote or $quote = "";
utf8::decode ($quote);
my @b = unpack "U0C*", $quote;
if (@b > 1) {
@b > 16 and croak ($self->SetDiag (1007));
$self->quote_char ("\0");
}
else {
$self->quote_char ($quote);
$quote = "";
}
$self->{quote} = $quote;
my $ec = _check_sanity ($self);
$ec and croak ($self->SetDiag ($ec));
$self->_cache_set ($_cache_id{quote}, $quote);
}
my $quote = $self->{quote};
defined $quote && length ($quote) ? $quote : $self->{quote_char};
} # quote
sub escape_char {
my $self = shift;
if (@_) {
my $ec = shift;
$self->_set_attr_C ("escape_char", $ec);
$ec or $self->_set_attr_X ("escape_null", 0);
}
$self->{escape_char};
} # escape_char
sub sep_char {
my $self = shift;
if (@_) {
$self->_set_attr_C ("sep_char", shift);
$self->_cache_set ($_cache_id{sep}, "");
}
$self->{sep_char};
} # sep_char
sub sep {
my $self = shift;
if (@_) {
my $sep = shift;
defined $sep or $sep = "";
utf8::decode ($sep);
my @b = unpack "U0C*", $sep;
if (@b > 1) {
@b > 16 and croak ($self->SetDiag (1006));
$self->sep_char ("\0");
}
else {
$self->sep_char ($sep);
$sep = "";
}
$self->{sep} = $sep;
my $ec = _check_sanity ($self);
$ec and croak ($self->SetDiag ($ec));
$self->_cache_set ($_cache_id{sep}, $sep);
}
my $sep = $self->{sep};
defined $sep && length ($sep) ? $sep : $self->{sep_char};
} # sep
sub eol {
my $self = shift;
if (@_) {
my $eol = shift;
defined $eol or $eol = "";
length ($eol) > 16 and croak ($self->SetDiag (1005));
$self->{eol} = $eol;
$self->_cache_set ($_cache_id{eol}, $eol);
}
$self->{eol};
} # eol
sub always_quote {
my $self = shift;
@_ and $self->_set_attr_X ("always_quote", shift);
$self->{always_quote};
} # always_quote
sub quote_space {
my $self = shift;
@_ and $self->_set_attr_X ("quote_space", shift);
$self->{quote_space};
} # quote_space
sub quote_empty {
my $self = shift;
@_ and $self->_set_attr_X ("quote_empty", shift);
$self->{quote_empty};
} # quote_empty
sub escape_null {
my $self = shift;
@_ and $self->_set_attr_X ("escape_null", shift);
$self->{escape_null};
} # escape_null
sub quote_null { goto &escape_null; }
sub quote_binary {
my $self = shift;
@_ and $self->_set_attr_X ("quote_binary", shift);
$self->{quote_binary};
} # quote_binary
sub binary {
my $self = shift;
@_ and $self->_set_attr_X ("binary", shift);
$self->{binary};
} # binary
sub strict {
my $self = shift;
@_ and $self->_set_attr_X ("strict", shift);
$self->{strict};
} # always_quote
sub _supported_formula {
my ($self, $f) = @_;
defined $f or return 5;
$f =~ m/^(?: 0 | none )$/xi ? 0 :
$f =~ m/^(?: 1 | die )$/xi ? 1 :
$f =~ m/^(?: 2 | croak )$/xi ? 2 :
$f =~ m/^(?: 3 | diag )$/xi ? 3 :
$f =~ m/^(?: 4 | empty | )$/xi ? 4 :
$f =~ m/^(?: 5 | undef )$/xi ? 5 : do {
$self ||= "Text::CSV_XS";
$self->SetDiag (1500);
croak "formula-handling '$f' is not supported\n";
};
} # _supported_formula
sub formula {
my $self = shift;
@_ and $self->_set_attr_N ("formula", _supported_formula ($self, shift));
[qw( none die croak diag empty undef )]->[_supported_formula ($self, $self->{formula})];
} # always_quote
sub formula_handling {
my $self = shift;
$self->formula (@_);
} # formula_handling
sub decode_utf8 {
my $self = shift;
@_ and $self->_set_attr_X ("decode_utf8", shift);
$self->{decode_utf8};
} # decode_utf8
sub keep_meta_info {
my $self = shift;
if (@_) {
my $v = shift;
!defined $v || $v eq "" and $v = 0;
$v =~ m/^[0-9]/ or $v = lc $v eq "false" ? 0 : 1; # true/truth = 1
$self->_set_attr_X ("keep_meta_info", $v);
}
$self->{keep_meta_info};
} # keep_meta_info
sub allow_loose_quotes {
my $self = shift;
@_ and $self->_set_attr_X ("allow_loose_quotes", shift);
$self->{allow_loose_quotes};
} # allow_loose_quotes
sub allow_loose_escapes {
my $self = shift;
@_ and $self->_set_attr_X ("allow_loose_escapes", shift);
$self->{allow_loose_escapes};
} # allow_loose_escapes
sub allow_whitespace {
my $self = shift;
if (@_) {
my $aw = shift;
_unhealthy_whitespace ($self, $aw) and
croak ($self->SetDiag (1002));
$self->_set_attr_X ("allow_whitespace", $aw);
}
$self->{allow_whitespace};
} # allow_whitespace
sub allow_unquoted_escape {
my $self = shift;
@_ and $self->_set_attr_X ("allow_unquoted_escape", shift);
$self->{allow_unquoted_escape};
} # allow_unquoted_escape
sub blank_is_undef {
my $self = shift;
@_ and $self->_set_attr_X ("blank_is_undef", shift);
$self->{blank_is_undef};
} # blank_is_undef
sub empty_is_undef {
my $self = shift;
@_ and $self->_set_attr_X ("empty_is_undef", shift);
$self->{empty_is_undef};
} # empty_is_undef
sub verbatim {
my $self = shift;
@_ and $self->_set_attr_X ("verbatim", shift);
$self->{verbatim};
} # verbatim
sub auto_diag {
my $self = shift;
if (@_) {
my $v = shift;
!defined $v || $v eq "" and $v = 0;
$v =~ m/^[0-9]/ or $v = lc $v eq "false" ? 0 : 1; # true/truth = 1
$self->_set_attr_X ("auto_diag", $v);
}
$self->{auto_diag};
} # auto_diag
sub diag_verbose {
my $self = shift;
if (@_) {
my $v = shift;
!defined $v || $v eq "" and $v = 0;
$v =~ m/^[0-9]/ or $v = lc $v eq "false" ? 0 : 1; # true/truth = 1
$self->_set_attr_X ("diag_verbose", $v);
}
$self->{diag_verbose};
} # diag_verbose
# status
#
# object method returning the success or failure of the most recent
# combine () or parse (). there are no side-effects.
sub status {
my $self = shift;
return $self->{_STATUS};
} # status
sub eof {
my $self = shift;
return $self->{_EOF};
} # status
sub types {
my $self = shift;
if (@_) {
if (my $types = shift) {
$self->{_types} = join "", map { chr } @{$types};
$self->{types} = $types;
}
else {
delete $self->{types};
delete $self->{_types};
undef;
}
}
else {
$self->{types};
}
} # types
sub callbacks {
my $self = shift;
if (@_) {
my $cb;
my $hf = 0x00;
if (defined $_[0]) {
grep { !defined } @_ and croak ($self->SetDiag (1004));
$cb = @_ == 1 && ref $_[0] eq "HASH" ? shift
: @_ % 2 == 0 ? { @_ }
: croak ($self->SetDiag (1004));
foreach my $cbk (keys %$cb) {
# A key cannot be a ref. That would be stored as the *string
# 'SCALAR(0x1f3e710)' or 'ARRAY(0x1a5ae18)'
$cbk =~ m/^[\w.]+$/ && ref $cb->{$cbk} eq "CODE" or
croak ($self->SetDiag (1004));
}
exists $cb->{error} and $hf |= 0x01;
exists $cb->{after_parse} and $hf |= 0x02;
exists $cb->{before_print} and $hf |= 0x04;
}
elsif (@_ > 1) {
# (undef, whatever)
croak ($self->SetDiag (1004));
}
$self->_set_attr_X ("_has_hooks", $hf);
$self->{callbacks} = $cb;
}
$self->{callbacks};
} # callbacks
# error_diag
#
# If (and only if) an error occurred, this function returns a code that
# indicates the reason of failure
sub error_diag {
my $self = shift;
my @diag = (0 + $last_new_err, $last_new_err, 0, 0, 0);
if ($self && ref $self && # Not a class method or direct call
$self->isa (__PACKAGE__) && exists $self->{_ERROR_DIAG}) {
$diag[0] = 0 + $self->{_ERROR_DIAG};
$diag[1] = $self->{_ERROR_DIAG};
$diag[2] = 1 + $self->{_ERROR_POS} if exists $self->{_ERROR_POS};
$diag[3] = $self->{_RECNO};
$diag[4] = $self->{_ERROR_FLD} if exists $self->{_ERROR_FLD};
$diag[0] && $self->{callbacks} && $self->{callbacks}{error} and
return $self->{callbacks}{error}->(@diag);
}
my $context = wantarray;
unless (defined $context) { # Void context, auto-diag
if ($diag[0] && $diag[0] != 2012) {
my $msg = "# CSV_XS ERROR: $diag[0] - $diag[1] \@ rec $diag[3] pos $diag[2]\n";
$diag[4] and $msg =~ s/$/ field $diag[4]/;
unless ($self && ref $self) { # auto_diag
# called without args in void context
warn $msg;
return;
}
if ($self->{diag_verbose} and $self->{_ERROR_INPUT}) {
$msg .= "$self->{_ERROR_INPUT}'\n";
$msg .= " " x ($diag[2] - 1);
$msg .= "^\n";
}
my $lvl = $self->{auto_diag};
if ($lvl < 2) {
my @c = caller (2);
if (@c >= 11 && $c[10] && ref $c[10] eq "HASH") {
my $hints = $c[10];
(exists $hints->{autodie} && $hints->{autodie} or
exists $hints->{"guard Fatal"} &&
!exists $hints->{"no Fatal"}) and
$lvl++;
# Future releases of autodie will probably set $^H{autodie}
# to "autodie @args", like "autodie :all" or "autodie open"
# so we can/should check for "open" or "new"
}
}
$lvl > 1 ? die $msg : warn $msg;
}
return;
}
return $context ? @diag : $diag[1];
} # error_diag
sub record_number {
my $self = shift;
return $self->{_RECNO};
} # record_number
# string
#
# object method returning the result of the most recent combine () or the
# input to the most recent parse (), whichever is more recent. there are
# no side-effects.
sub string {
my $self = shift;
return ref $self->{_STRING} ? ${$self->{_STRING}} : undef;
} # string
# fields
#
# object method returning the result of the most recent parse () or the
# input to the most recent combine (), whichever is more recent. there
# are no side-effects.
sub fields {
my $self = shift;
return ref $self->{_FIELDS} ? @{$self->{_FIELDS}} : undef;
} # fields
# meta_info
#
# object method returning the result of the most recent parse () or the
# input to the most recent combine (), whichever is more recent. there
# are no side-effects. meta_info () returns (if available) some of the
# field's properties
sub meta_info {
my $self = shift;
return ref $self->{_FFLAGS} ? @{$self->{_FFLAGS}} : undef;
} # meta_info
sub is_quoted {
my ($self, $idx) = @_;
ref $self->{_FFLAGS} &&
$idx >= 0 && $idx < @{$self->{_FFLAGS}} or return;
$self->{_FFLAGS}[$idx] & 0x0001 ? 1 : 0;
} # is_quoted
sub is_binary {
my ($self, $idx) = @_;
ref $self->{_FFLAGS} &&
$idx >= 0 && $idx < @{$self->{_FFLAGS}} or return;
$self->{_FFLAGS}[$idx] & 0x0002 ? 1 : 0;
} # is_binary
sub is_missing {
my ($self, $idx) = @_;
$idx < 0 || !ref $self->{_FFLAGS} and return;
$idx >= @{$self->{_FFLAGS}} and return 1;
$self->{_FFLAGS}[$idx] & 0x0010 ? 1 : 0;
} # is_missing
# combine
#
# Object method returning success or failure. The given arguments are
# combined into a single comma-separated value. Failure can be the
# result of no arguments or an argument containing an invalid character.
# side-effects include:
# setting status ()
# setting fields ()
# setting string ()
# setting error_input ()
sub combine {
my $self = shift;
my $str = "";
$self->{_FIELDS} = \@_;
$self->{_STATUS} = (@_ > 0) && $self->Combine (\$str, \@_, 0);
$self->{_STRING} = \$str;
$self->{_STATUS};
} # combine
# parse
#
# Object method returning success or failure. The given argument is
# expected to be a valid comma-separated value. Failure can be the
# result of no arguments or an argument containing an invalid sequence
# of characters. Side-effects include:
# setting status ()
# setting fields ()
# setting meta_info ()
# setting string ()
# setting error_input ()
sub parse {
my ($self, $str) = @_;
ref $str and croak ($self->SetDiag (1500));
my $fields = [];
my $fflags = [];
$self->{_STRING} = \$str;
if (defined $str && $self->Parse ($str, $fields, $fflags)) {
$self->{_FIELDS} = $fields;
$self->{_FFLAGS} = $fflags;
$self->{_STATUS} = 1;
}
else {
$self->{_FIELDS} = undef;
$self->{_FFLAGS} = undef;
$self->{_STATUS} = 0;
}
$self->{_STATUS};
} # parse
sub column_names {
my ($self, @keys) = @_;
@keys or
return defined $self->{_COLUMN_NAMES} ? @{$self->{_COLUMN_NAMES}} : ();
@keys == 1 && ! defined $keys[0] and
return $self->{_COLUMN_NAMES} = undef;
if (@keys == 1 && ref $keys[0] eq "ARRAY") {
@keys = @{$keys[0]};
}
elsif (join "", map { defined $_ ? ref $_ : "" } @keys) {
croak ($self->SetDiag (3001));
}
$self->{_BOUND_COLUMNS} && @keys != @{$self->{_BOUND_COLUMNS}} and
croak ($self->SetDiag (3003));
$self->{_COLUMN_NAMES} = [ map { defined $_ ? $_ : "\cAUNDEF\cA" } @keys ];
@{$self->{_COLUMN_NAMES}};
} # column_names
sub header {
my ($self, $fh, @args) = @_;
$fh or croak ($self->SetDiag (1014));
my (@seps, %args);
for (@args) {
if (ref $_ eq "ARRAY") {
push @seps, @$_;
next;
}
if (ref $_ eq "HASH") {
%args = %$_;
next;
}
croak (q{usage: $csv->header ($fh, [ seps ], { options })});
}
defined $args{detect_bom} or $args{detect_bom} = 1;
defined $args{set_column_names} or $args{set_column_names} = 1;
defined $args{munge_column_names} or $args{munge_column_names} = "lc";
# Reset any previous leftovers
$self->{_RECNO} = 0;
$self->{_AHEAD} = undef;
$self->{_COLUMN_NAMES} = undef if $args{set_column_names};
$self->{_BOUND_COLUMNS} = undef if $args{set_column_names};
if (defined $args{sep_set}) {
ref $args{sep_set} eq "ARRAY" or
croak ($self->SetDiag (1500, "sep_set should be an array ref"));
@seps = @{$args{sep_set}};
}
$^O eq "MSWin32" and binmode $fh;
my $hdr = <$fh>;
# check if $hdr can be empty here, I don't think so
defined $hdr && $hdr ne "" or croak ($self->SetDiag (1010));
my %sep;
@seps or @seps = (",", ";");
foreach my $sep (@seps) {
index ($hdr, $sep) >= 0 and $sep{$sep}++;
}
keys %sep >= 2 and croak ($self->SetDiag (1011));
$self->sep (keys %sep);
my $enc = "";
if ($args{detect_bom}) { # UTF-7 is not supported
if ($hdr =~ s/^\x00\x00\xfe\xff//) { $enc = "utf-32be" }
elsif ($hdr =~ s/^\xff\xfe\x00\x00//) { $enc = "utf-32le" }
elsif ($hdr =~ s/^\xfe\xff//) { $enc = "utf-16be" }
elsif ($hdr =~ s/^\xff\xfe//) { $enc = "utf-16le" }
elsif ($hdr =~ s/^\xef\xbb\xbf//) { $enc = "utf-8" }
elsif ($hdr =~ s/^\xf7\x64\x4c//) { $enc = "utf-1" }
elsif ($hdr =~ s/^\xdd\x73\x66\x73//) { $enc = "utf-ebcdic" }
elsif ($hdr =~ s/^\x0e\xfe\xff//) { $enc = "scsu" }
elsif ($hdr =~ s/^\xfb\xee\x28//) { $enc = "bocu-1" }
elsif ($hdr =~ s/^\x84\x31\x95\x33//) { $enc = "gb-18030" }
elsif ($hdr =~ s/^\x{feff}//) { $enc = "" }
$hdr eq "" and croak ($self->SetDiag (1010));
if ($enc) {
if ($enc =~ m/([13]).le$/) {
my $l = 0 + $1;
my $x;
$hdr .= "\0" x $l;
read $fh, $x, $l;
}
if ($enc ne "utf-8") {
require Encode;
$hdr = Encode::decode ($enc, $hdr);
}
binmode $fh, ":encoding($enc)";
}
}
my ($ahead, $eol);
if ($hdr =~ s/^([^\r\n]+)([\r\n]+)([^\r\n].+)\z/$1/s) {
$eol = $2;
$ahead = $3;
}
$args{munge_column_names} eq "lc" and $hdr = lc $hdr;
$args{munge_column_names} eq "uc" and $hdr = uc $hdr;
my $hr = \$hdr; # Will cause croak on perl-5.6.x
open my $h, "<", $hr or croak ($self->SetDiag (1010));
my $row = $self->getline ($h) or croak;
close $h;
if ($ahead) { # Must be after getline, which creates the cache
$self->_cache_set ($_cache_id{_has_ahead}, 1);
$self->{_AHEAD} = $ahead;
$eol =~ m/^\r([^\n]|\z)/ and $self->eol ($eol);
}
my @hdr = @$row;
ref $args{munge_column_names} eq "CODE" and
@hdr = map { $args{munge_column_names}->($_) } @hdr;
ref $args{munge_column_names} eq "HASH" and
@hdr = map { $args{munge_column_names}->{$_} || $_ } @hdr;
my %hdr = map { $_ => 1 } @hdr;
exists $hdr{""} and croak ($self->SetDiag (1012));
keys %hdr == @hdr or croak ($self->SetDiag (1013));
$args{set_column_names} and $self->column_names (@hdr);
wantarray ? @hdr : $self;
} # header
sub bind_columns {
my ($self, @refs) = @_;
@refs or
return defined $self->{_BOUND_COLUMNS} ? @{$self->{_BOUND_COLUMNS}} : undef;
if (@refs == 1 && ! defined $refs[0]) {
$self->{_COLUMN_NAMES} = undef;
return $self->{_BOUND_COLUMNS} = undef;
}
$self->{_COLUMN_NAMES} && @refs != @{$self->{_COLUMN_NAMES}} and
croak ($self->SetDiag (3003));
join "", map { ref $_ eq "SCALAR" ? "" : "*" } @refs and
croak ($self->SetDiag (3004));
$self->_set_attr_N ("_is_bound", scalar @refs);
$self->{_BOUND_COLUMNS} = [ @refs ];
@refs;
} # bind_columns
sub getline_hr {
my ($self, @args, %hr) = @_;
$self->{_COLUMN_NAMES} or croak ($self->SetDiag (3002));
my $fr = $self->getline (@args) or return;
if (ref $self->{_FFLAGS}) { # missing
$self->{_FFLAGS}[$_] = 0x0010
for (@$fr ? $#{$fr} + 1 : 0) .. $#{$self->{_COLUMN_NAMES}};
@$fr == 1 && (!defined $fr->[0] || $fr->[0] eq "") and
$self->{_FFLAGS}[0] ||= 0x0010;
}
@hr{@{$self->{_COLUMN_NAMES}}} = @$fr;
\%hr;
} # getline_hr
sub getline_hr_all {
my ($self, @args) = @_;
$self->{_COLUMN_NAMES} or croak ($self->SetDiag (3002));
my @cn = @{$self->{_COLUMN_NAMES}};
[ map { my %h; @h{@cn} = @$_; \%h } @{$self->getline_all (@args)} ];
} # getline_hr_all
sub say {
my ($self, $io, @f) = @_;
my $eol = $self->eol;
$eol eq "" and $self->eol ($\ || $/);
# say ($fh, undef) does not propage actual undef to print ()
my $state = $self->print ($io, @f == 1 && !defined $f[0] ? undef : @f);
$self->eol ($eol);
return $state;
} # say
sub print_hr {
my ($self, $io, $hr) = @_;
$self->{_COLUMN_NAMES} or croak ($self->SetDiag (3009));
ref $hr eq "HASH" or croak ($self->SetDiag (3010));
$self->print ($io, [ map { $hr->{$_} } $self->column_names ]);
} # print_hr
sub fragment {
my ($self, $io, $spec) = @_;
my $qd = qr{\s* [0-9]+ \s* }x; # digit
my $qs = qr{\s* (?: [0-9]+ | \* ) \s*}x; # digit or star
my $qr = qr{$qd (?: - $qs )?}x; # range
my $qc = qr{$qr (?: ; $qr )*}x; # list
defined $spec && $spec =~ m{^ \s*
\x23 ? \s* # optional leading #
( row | col | cell ) \s* =
( $qc # for row and col
| $qd , $qd (?: - $qs , $qs)? # for cell (ranges)
(?: ; $qd , $qd (?: - $qs , $qs)? )* # and cell (range) lists
) \s* $}xi or croak ($self->SetDiag (2013));
my ($type, $range) = (lc $1, $2);
my @h = $self->column_names ();
my @c;
if ($type eq "cell") {
my @spec;
my $min_row;
my $max_row = 0;
for (split m/\s*;\s*/ => $range) {
my ($tlr, $tlc, $brr, $brc) = (m{
^ \s* ([0-9]+ ) \s* , \s* ([0-9]+ ) \s*
(?: - \s* ([0-9]+ | \*) \s* , \s* ([0-9]+ | \*) \s* )?
$}x) or croak ($self->SetDiag (2013));
defined $brr or ($brr, $brc) = ($tlr, $tlc);
$tlr == 0 || $tlc == 0 ||
($brr ne "*" && ($brr == 0 || $brr < $tlr)) ||
($brc ne "*" && ($brc == 0 || $brc < $tlc))
and croak ($self->SetDiag (2013));
$tlc--;
$brc-- unless $brc eq "*";
defined $min_row or $min_row = $tlr;
$tlr < $min_row and $min_row = $tlr;
$brr eq "*" || $brr > $max_row and
$max_row = $brr;
push @spec, [ $tlr, $tlc, $brr, $brc ];
}
my $r = 0;
while (my $row = $self->getline ($io)) {
++$r < $min_row and next;
my %row;
my $lc;
foreach my $s (@spec) {
my ($tlr, $tlc, $brr, $brc) = @$s;
$r < $tlr || ($brr ne "*" && $r > $brr) and next;
!defined $lc || $tlc < $lc and $lc = $tlc;
my $rr = $brc eq "*" ? $#$row : $brc;
$row{$_} = $row->[$_] for $tlc .. $rr;
}
push @c, [ @row{sort { $a <=> $b } keys %row } ];
if (@h) {
my %h; @h{@h} = @{$c[-1]};
$c[-1] = \%h;
}
$max_row ne "*" && $r == $max_row and last;
}
return \@c;
}
# row or col
my @r;
my $eod = 0;
for (split m/\s*;\s*/ => $range) {
my ($from, $to) = m/^\s* ([0-9]+) (?: \s* - \s* ([0-9]+ | \* ))? \s* $/x
or croak ($self->SetDiag (2013));
$to ||= $from;
$to eq "*" and ($to, $eod) = ($from, 1);
# $to cannot be <= 0 due to regex and ||=
$from <= 0 || $to < $from and croak ($self->SetDiag (2013));
$r[$_] = 1 for $from .. $to;
}
my $r = 0;
$type eq "col" and shift @r;
$_ ||= 0 for @r;
while (my $row = $self->getline ($io)) {
$r++;
if ($type eq "row") {
if (($r > $#r && $eod) || $r[$r]) {
push @c, $row;
if (@h) {
my %h; @h{@h} = @{$c[-1]};
$c[-1] = \%h;
}
}
next;
}
push @c, [ map { ($_ > $#r && $eod) || $r[$_] ? $row->[$_] : () } 0..$#$row ];
if (@h) {
my %h; @h{@h} = @{$c[-1]};
$c[-1] = \%h;
}
}
return \@c;
} # fragment
my $csv_usage = q{usage: my $aoa = csv (in => $file);};
sub _csv_attr {
my %attr = (@_ == 1 && ref $_[0] eq "HASH" ? %{$_[0]} : @_) or croak;
$attr{binary} = 1;
my $enc = delete $attr{enc} || delete $attr{encoding} || "";
$enc eq "auto" and ($attr{detect_bom}, $enc) = (1, "");
$enc =~ m/^[-\w.]+$/ and $enc = ":encoding($enc)";
my $fh;
my $cls = 0; # If I open a file, I have to close it
my $in = delete $attr{in} || delete $attr{file} or croak $csv_usage;
my $out = delete $attr{out} || delete $attr{file};
ref $in eq "CODE" || ref $in eq "ARRAY" and $out ||= \*STDOUT;
$in && $out && !ref $in && !ref $out and croak join "\n" =>
qq{Cannot use a string for both in and out. Instead use:},
qq{ csv (in => csv (in => "$in"), out => "$out");\n};
if ($out) {
if ((ref $out and ref $out ne "SCALAR") or "GLOB" eq ref \$out) {
$fh = $out;
}
else {
open $fh, ">", $out or croak "$out: $!";
$cls = 1;
}
$enc and binmode $fh, $enc;
unless (defined $attr{eol}) {
my @layers = eval { PerlIO::get_layers ($fh) };
$attr{eol} = (grep m/crlf/ => @layers) ? "\n" : "\r\n";
}
}
if ( ref $in eq "CODE" or ref $in eq "ARRAY") {
# All done
}
elsif (ref $in eq "SCALAR") {
# Strings with code points over 0xFF may not be mapped into in-memory file handles
# "<$enc" does not change that :(
open $fh, "<", $in or croak "Cannot open from SCALAR using PerlIO";
$cls = 1;
}
elsif (ref $in or "GLOB" eq ref \$in) {
if (!ref $in && $] < 5.008005) {
$fh = \*$in; # uncoverable statement ancient perl version required
}
else {
$fh = $in;
}
}
else {
open $fh, "<$enc", $in or croak "$in: $!";
$cls = 1;
}
$fh or croak qq{No valid source passed. "in" is required};
my $hdrs = delete $attr{headers};
my $frag = delete $attr{fragment};
my $key = delete $attr{key};
my $kh = delete $attr{keep_headers} ||
delete $attr{keep_column_names} ||
delete $attr{kh};
my $cbai = delete $attr{callbacks}{after_in} ||
delete $attr{after_in} ||
delete $attr{callbacks}{after_parse} ||
delete $attr{after_parse};
my $cbbo = delete $attr{callbacks}{before_out} ||
delete $attr{before_out};
my $cboi = delete $attr{callbacks}{on_in} ||
delete $attr{on_in};
my $hd_s = delete $attr{sep_set} ||
delete $attr{seps};
my $hd_b = delete $attr{detect_bom} ||
delete $attr{bom};
my $hd_m = delete $attr{munge} ||
delete $attr{munge_column_names};
my $hd_c = delete $attr{set_column_names};
for ([ quo => "quote" ],
[ esc => "escape" ],
[ escape => "escape_char" ],
) {
my ($f, $t) = @$_;
exists $attr{$f} and !exists $attr{$t} and $attr{$t} = delete $attr{$f};
}
my $fltr = delete $attr{filter};
my %fltr = (
not_blank => sub { @{$_[1]} > 1 or defined $_[1][0] && $_[1][0] ne "" },
not_empty => sub { grep { defined && $_ ne "" } @{$_[1]} },
filled => sub { grep { defined && m/\S/ } @{$_[1]} },
);
defined $fltr && !ref $fltr && exists $fltr{$fltr} and
$fltr = { 0 => $fltr{$fltr} };
ref $fltr eq "HASH" or $fltr = undef;
exists $attr{formula} and
$attr{formula} = _supported_formula (undef, $attr{formula});
defined $attr{auto_diag} or $attr{auto_diag} = 1;
defined $attr{escape_null} or $attr{escape_null} = 0;
my $csv = delete $attr{csv} || Text::CSV_XS->new (\%attr)
or croak $last_new_err;
return {
csv => $csv,
attr => { %attr },
fh => $fh,
cls => $cls,
in => $in,
out => $out,
enc => $enc,
hdrs => $hdrs,
key => $key,
kh => $kh,
frag => $frag,
fltr => $fltr,
cbai => $cbai,
cbbo => $cbbo,
cboi => $cboi,
hd_s => $hd_s,
hd_b => $hd_b,
hd_m => $hd_m,
hd_c => $hd_c,
};
} # _csv_attr
sub csv {
@_ && ref $_[0] eq __PACKAGE__ and splice @_, 0, 0, "csv";
@_ or croak $csv_usage;
my $c = _csv_attr (@_);
my ($csv, $in, $fh, $hdrs) = @{$c}{"csv", "in", "fh", "hdrs"};
my %hdr;
if (ref $hdrs eq "HASH") {
%hdr = %$hdrs;
$hdrs = "auto";
}
if ($c->{out}) {
if (ref $in eq "CODE") {
my $hdr = 1;
while (my $row = $in->($csv)) {
if (ref $row eq "ARRAY") {
$csv->print ($fh, $row);
next;
}
if (ref $row eq "HASH") {
if ($hdr) {
$hdrs ||= [ map { $hdr{$_} || $_ } keys %$row ];
$csv->print ($fh, $hdrs);
$hdr = 0;
}
$csv->print ($fh, [ @{$row}{@$hdrs} ]);
}
}
}
elsif (ref $in->[0] eq "ARRAY") { # aoa
ref $hdrs and $csv->print ($fh, $hdrs);
for (@{$in}) {
$c->{cboi} and $c->{cboi}->($csv, $_);
$c->{cbbo} and $c->{cbbo}->($csv, $_);
$csv->print ($fh, $_);
}
}
else { # aoh
my @hdrs = ref $hdrs ? @{$hdrs} : keys %{$in->[0]};
defined $hdrs or $hdrs = "auto";
ref $hdrs || $hdrs eq "auto" and
$csv->print ($fh, [ map { $hdr{$_} || $_ } @hdrs ]);
for (@{$in}) {
local %_;
*_ = $_;
$c->{cboi} and $c->{cboi}->($csv, $_);
$c->{cbbo} and $c->{cbbo}->($csv, $_);
$csv->print ($fh, [ @{$_}{@hdrs} ]);
}
}
$c->{cls} and close $fh;
return 1;
}
my @row1;
if (defined $c->{hd_s} || defined $c->{hd_b} || defined $c->{hd_m} || defined $c->{hd_c}) {
my %harg;
defined $c->{hd_s} and $harg{set_set} = $c->{hd_s};
defined $c->{hd_d} and $harg{detect_bom} = $c->{hd_b};
defined $c->{hd_m} and $harg{munge_column_names} = $hdrs ? "none" : $c->{hd_m};
defined $c->{hd_c} and $harg{set_column_names} = $hdrs ? 0 : $c->{hd_c};
@row1 = $csv->header ($fh, \%harg);
my @hdr = $csv->column_names;
@hdr and $hdrs ||= \@hdr;
}
if ($c->{kh}) {
ref $c->{kh} eq "ARRAY" or croak ($csv->SetDiag (1501, "1501 - PRM"));
$hdrs ||= "auto";
}
my $key = $c->{key};
if ($key) {
ref $key and croak ($csv->SetDiag (1501, "1501 - PRM"));
$hdrs ||= "auto";
}
$c->{fltr} && grep m/\D/ => keys %{$c->{fltr}} and $hdrs ||= "auto";
if (defined $hdrs) {
if (!ref $hdrs) {
if ($hdrs eq "skip") {
$csv->getline ($fh); # discard;
}
elsif ($hdrs eq "auto") {
my $h = $csv->getline ($fh) or return;
$hdrs = [ map { $hdr{$_} || $_ } @$h ];
}
elsif ($hdrs eq "lc") {
my $h = $csv->getline ($fh) or return;
$hdrs = [ map { lc ($hdr{$_} || $_) } @$h ];
}
elsif ($hdrs eq "uc") {
my $h = $csv->getline ($fh) or return;
$hdrs = [ map { uc ($hdr{$_} || $_) } @$h ];
}
}
elsif (ref $hdrs eq "CODE") {
my $h = $csv->getline ($fh) or return;
my $cr = $hdrs;
$hdrs = [ map { $cr->($hdr{$_} || $_) } @$h ];
}
$c->{kh} and $hdrs and @{$c->{kh}} = @$hdrs;
}
if ($c->{fltr}) {
my %f = %{$c->{fltr}};
# convert headers to index
my @hdr;
if (ref $hdrs) {
@hdr = @{$hdrs};
for (0 .. $#hdr) {
exists $f{$hdr[$_]} and $f{$_ + 1} = delete $f{$hdr[$_]};
}
}
$csv->callbacks (after_parse => sub {
my ($CSV, $ROW) = @_; # lexical sub-variables in caps
foreach my $FLD (sort keys %f) {
local $_ = $ROW->[$FLD - 1];
local %_;
@hdr and @_{@hdr} = @$ROW;
$f{$FLD}->($CSV, $ROW) or return \"skip";
$ROW->[$FLD - 1] = $_;
}
});
}
my $frag = $c->{frag};
my $ref = ref $hdrs
? # aoh
do {
$csv->column_names ($hdrs);
$frag ? $csv->fragment ($fh, $frag) :
$key ? { map { $_->{$key} => $_ } @{$csv->getline_hr_all ($fh)} }
: $csv->getline_hr_all ($fh);
}
: # aoa
$frag ? $csv->fragment ($fh, $frag)
: $csv->getline_all ($fh);
if ($ref) {
@row1 && !$c->{hd_c} && !ref $hdrs and unshift @$ref, \@row1;
}
else {
Text::CSV_XS->auto_diag;
}
$c->{cls} and close $fh;
if ($ref and $c->{cbai} || $c->{cboi}) {
# Default is ARRAYref, but with key =>, you'll get a hashref
foreach my $r (ref $ref eq "ARRAY" ? @{$ref} : values %{$ref}) {
local %_;
ref $r eq "HASH" and *_ = $r;
$c->{cbai} and $c->{cbai}->($csv, $r);
$c->{cboi} and $c->{cboi}->($csv, $r);
}
}
defined wantarray or
return csv (%{$c->{attr}}, in => $ref, headers => $hdrs, %{$c->{attr}});
return $ref;
} # csv
1;
__END__
=encoding utf-8
=head1 NAME
Text::CSV_XS - comma-separated values manipulation routines
=head1 SYNOPSIS
# Functional interface
use Text::CSV_XS qw( csv );
# Read whole file in memory
my $aoa = csv (in => "data.csv"); # as array of array
my $aoh = csv (in => "data.csv",
headers => "auto"); # as array of hash
# Write array of arrays as csv file
csv (in => $aoa, out => "file.csv", sep_char=> ";");
# Only show lines where "code" is odd
csv (in => "data.csv", filter => { code => sub { $_ % 2 }});
# Object interface
use Text::CSV_XS;
my @rows;
# Read/parse CSV
my $csv = Text::CSV_XS->new ({ binary => 1, auto_diag => 1 });
open my $fh, "<:encoding(utf8)", "test.csv" or die "test.csv: $!";
while (my $row = $csv->getline ($fh)) {
$row->[2] =~ m/pattern/ or next; # 3rd field should match
push @rows, $row;
}
close $fh;
# and write as CSV
open $fh, ">:encoding(utf8)", "new.csv" or die "new.csv: $!";
$csv->say ($fh, $_) for @rows;
close $fh or die "new.csv: $!";
=head1 DESCRIPTION
Text::CSV_XS provides facilities for the composition and decomposition of
comma-separated values. An instance of the Text::CSV_XS class will combine
fields into a C<CSV> string and parse a C<CSV> string into fields.
The module accepts either strings or files as input and support the use of
user-specified characters for delimiters, separators, and escapes.
=head2 Embedded newlines
B<Important Note>: The default behavior is to accept only ASCII characters
in the range from C<0x20> (space) to C<0x7E> (tilde). This means that the
fields can not contain newlines. If your data contains newlines embedded in
fields, or characters above C<0x7E> (tilde), or binary data, you B<I<must>>
set C<< binary => 1 >> in the call to L</new>. To cover the widest range of
parsing options, you will always want to set binary.
But you still have the problem that you have to pass a correct line to the
L</parse> method, which is more complicated from the usual point of usage:
my $csv = Text::CSV_XS->new ({ binary => 1, eol => $/ });
while (<>) { # WRONG!
$csv->parse ($_);
my @fields = $csv->fields ();
}
this will break, as the C<while> might read broken lines: it does not care
about the quoting. If you need to support embedded newlines, the way to go
is to B<not> pass L<C<eol>|/eol> in the parser (it accepts C<\n>, C<\r>,
B<and> C<\r\n> by default) and then
my $csv = Text::CSV_XS->new ({ binary => 1 });
open my $fh, "<", $file or die "$file: $!";
while (my $row = $csv->getline ($fh)) {
my @fields = @$row;
}
The old(er) way of using global file handles is still supported
while (my $row = $csv->getline (*ARGV)) { ... }
=head2 Unicode
Unicode is only tested to work with perl-5.8.2 and up.
See also L</BOM>.
The simplest way to ensure the correct encoding is used for in- and output
is by either setting layers on the filehandles, or setting the L</encoding>
argument for L</csv>.
open my $fh, "<:encoding(UTF-8)", "in.csv" or die "in.csv: $!";
or
my $aoa = csv (in => "in.csv", encoding => "UTF-8");
open my $fh, ">:encoding(UTF-8)", "out.csv" or die "out.csv: $!";
or
csv (in => $aoa, out => "out.csv", encoding => "UTF-8");
On parsing (both for L</getline> and L</parse>), if the source is marked
being UTF8, then all fields that are marked binary will also be marked UTF8.
On combining (L</print> and L</combine>): if any of the combining fields
was marked UTF8, the resulting string will be marked as UTF8. Note however
that all fields I<before> the first field marked UTF8 and contained 8-bit
characters that were not upgraded to UTF8, these will be C<bytes> in the
resulting string too, possibly causing unexpected errors. If you pass data
of different encoding, or you don't know if there is different encoding,
force it to be upgraded before you pass them on:
$csv->print ($fh, [ map { utf8::upgrade (my $x = $_); $x } @data ]);
For complete control over encoding, please use L<Text::CSV::Encoded>:
use Text::CSV::Encoded;
my $csv = Text::CSV::Encoded->new ({
encoding_in => "iso-8859-1", # the encoding comes into Perl
encoding_out => "cp1252", # the encoding comes out of Perl
});
$csv = Text::CSV::Encoded->new ({ encoding => "utf8" });
# combine () and print () accept *literally* utf8 encoded data
# parse () and getline () return *literally* utf8 encoded data
$csv = Text::CSV::Encoded->new ({ encoding => undef }); # default
# combine () and print () accept UTF8 marked data
# parse () and getline () return UTF8 marked data
=head2 BOM
BOM (or Byte Order Mark) handling is available only inside the L</header>
method. This method supports the following encodings: C<utf-8>, C<utf-1>,
C<utf-32be>, C<utf-32le>, C<utf-16be>, C<utf-16le>, C<utf-ebcdic>, C<scsu>,
C<bocu-1>, and C<gb-18030>. See L<Wikipedia|https://en.wikipedia.org/wiki/Byte_order_mark>.
If a file has a BOM, the easiest way to deal with that is
my $aoh = csv (in => $file, detect_bom => 1);
All records will be encoded based on the detected BOM.
This implies a call to the L</header> method, which defaults to also set
the L</column_names>. So this is B<not> the same as
my $aoh = csv (in => $file, headers => "auto");
which only reads the first record to set L</column_names> but ignores any
meaning of possible present BOM.
=head1 SPECIFICATION
While no formal specification for CSV exists, L<RFC 4180|http://tools.ietf.org/html/rfc4180>
(I<1>) describes the common format and establishes C<text/csv> as the MIME
type registered with the IANA. L<RFC 7111|http://tools.ietf.org/html/rfc7111>
(I<2>) adds fragments to CSV.
Many informal documents exist that describe the C<CSV> format. L<"How To:
The Comma Separated Value (CSV) File Format"|http://www.creativyst.com/Doc/Articles/CSV/CSV01.htm>
(I<3>) provides an overview of the C<CSV> format in the most widely used
applications and explains how it can best be used and supported.
1) http://tools.ietf.org/html/rfc4180
2) http://tools.ietf.org/html/rfc7111
3) http://www.creativyst.com/Doc/Articles/CSV/CSV01.htm
The basic rules are as follows:
B<CSV> is a delimited data format that has fields/columns separated by the
comma character and records/rows separated by newlines. Fields that contain
a special character (comma, newline, or double quote), must be enclosed in
double quotes. However, if a line contains a single entry that is the empty
string, it may be enclosed in double quotes. If a field's value contains a
double quote character it is escaped by placing another double quote
character next to it. The C<CSV> file format does not require a specific
character encoding, byte order, or line terminator format.
=over 2
=item *
Each record is a single line ended by a line feed (ASCII/C<LF>=C<0x0A>) or
a carriage return and line feed pair (ASCII/C<CRLF>=C<0x0D 0x0A>), however,
line-breaks may be embedded.
=item *
Fields are separated by commas.
=item *
Allowable characters within a C<CSV> field include C<0x09> (C<TAB>) and the
inclusive range of C<0x20> (space) through C<0x7E> (tilde). In binary mode
all characters are accepted, at least in quoted fields.
=item *
A field within C<CSV> must be surrounded by double-quotes to contain a
separator character (comma).
=back
Though this is the most clear and restrictive definition, Text::CSV_XS is
way more liberal than this, and allows extension:
=over 2
=item *
Line termination by a single carriage return is accepted by default
=item *
The separation-, escape-, and escape- characters can be any ASCII character
in the range from C<0x20> (space) to C<0x7E> (tilde). Characters outside
this range may or may not work as expected. Multibyte characters, like UTF
C<U+060C> (ARABIC COMMA), C<U+FF0C> (FULLWIDTH COMMA), C<U+241B> (SYMBOL
FOR ESCAPE), C<U+2424> (SYMBOL FOR NEWLINE), C<U+FF02> (FULLWIDTH QUOTATION
MARK), and C<U+201C> (LEFT DOUBLE QUOTATION MARK) (to give some examples of
what might look promising) work for newer versions of perl for C<sep_char>,
and C<quote_char> but not for C<escape_char>.
If you use perl-5.8.2 or higher these three attributes are utf8-decoded, to
increase the likelihood of success. This way C<U+00FE> will be allowed as a
quote character.
=item *
A field in C<CSV> must be surrounded by double-quotes to make an embedded
double-quote, represented by a pair of consecutive double-quotes, valid. In
binary mode you may additionally use the sequence C<"0> for representation
of a NULL byte. Using C<0x00> in binary mode is just as valid.
=item *
Several violations of the above specification may be lifted by passing some
options as attributes to the object constructor.
=back
=head1 METHODS
=head2 version
X<version>
(Class method) Returns the current module version.
=head2 new
X<new>
(Class method) Returns a new instance of class Text::CSV_XS. The attributes
are described by the (optional) hash ref C<\%attr>.
my $csv = Text::CSV_XS->new ({ attributes ... });
The following attributes are available:
=head3 eol
X<eol>
my $csv = Text::CSV_XS->new ({ eol => $/ });
$csv->eol (undef);
my $eol = $csv->eol;
The end-of-line string to add to rows for L</print> or the record separator
for L</getline>.
When not passed in a B<parser> instance, the default behavior is to accept
C<\n>, C<\r>, and C<\r\n>, so it is probably safer to not specify C<eol> at
all. Passing C<undef> or the empty string behave the same.
When not passed in a B<generating> instance, records are not terminated at
all, so it is probably wise to pass something you expect. A safe choice for
C<eol> on output is either C<$/> or C<\r\n>.
Common values for C<eol> are C<"\012"> (C<\n> or Line Feed), C<"\015\012">
(C<\r\n> or Carriage Return, Line Feed), and C<"\015"> (C<\r> or Carriage
Return). The L<C<eol>|/eol> attribute cannot exceed 7 (ASCII) characters.
If both C<$/> and L<C<eol>|/eol> equal C<"\015">, parsing lines that end on
only a Carriage Return without Line Feed, will be L</parse>d correct.
=head3 sep_char
X<sep_char>
my $csv = Text::CSV_XS->new ({ sep_char => ";" });
$csv->sep_char (";");
my $c = $csv->sep_char;
The char used to separate fields, by default a comma. (C<,>). Limited to a
single-byte character, usually in the range from C<0x20> (space) to C<0x7E>
(tilde). When longer sequences are required, use L<C<sep>|/sep>.
The separation character can not be equal to the quote character or to the
escape character.
See also L</CAVEATS>
=head3 sep
X<sep>
my $csv = Text::CSV_XS->new ({ sep => "\N{FULLWIDTH COMMA}" });
$csv->sep (";");
my $sep = $csv->sep;
The chars used to separate fields, by default undefined. Limited to 8 bytes.
When set, overrules L<C<sep_char>|/sep_char>. If its length is one byte it
acts as an alias to L<C<sep_char>|/sep_char>.
See also L</CAVEATS>
=head3 quote_char
X<quote_char>
my $csv = Text::CSV_XS->new ({ quote_char => "'" });
$csv->quote_char (undef);
my $c = $csv->quote_char;
The character to quote fields containing blanks or binary data, by default
the double quote character (C<">). A value of undef suppresses quote chars
(for simple cases only). Limited to a single-byte character, usually in the
range from C<0x20> (space) to C<0x7E> (tilde). When longer sequences are
required, use L<C<quote>|/quote>.
C<quote_char> can not be equal to L<C<sep_char>|/sep_char>.
=head3 quote
X<quote>
my $csv = Text::CSV_XS->new ({ quote => "\N{FULLWIDTH QUOTATION MARK}" });
$csv->quote ("'");
my $quote = $csv->quote;
The chars used to quote fields, by default undefined. Limited to 8 bytes.
When set, overrules L<C<quote_char>|/quote_char>. If its length is one byte
it acts as an alias to L<C<quote_char>|/quote_char>.
See also L</CAVEATS>
=head3 escape_char
X<escape_char>
my $csv = Text::CSV_XS->new ({ escape_char => "\\" });
$csv->escape_char (":");
my $c = $csv->escape_char;
The character to escape certain characters inside quoted fields. This is
limited to a single-byte character, usually in the range from C<0x20>
(space) to C<0x7E> (tilde).
The C<escape_char> defaults to being the double-quote mark (C<">). In other
words the same as the default L<C<quote_char>|/quote_char>. This means that
doubling the quote mark in a field escapes it:
"foo","bar","Escape ""quote mark"" with two ""quote marks""","baz"
If you change the L<C<quote_char>|/quote_char> without changing the
C<escape_char>, the C<escape_char> will still be the double-quote (C<">).
If instead you want to escape the L<C<quote_char>|/quote_char> by doubling
it you will need to also change the C<escape_char> to be the same as what
you have changed the L<C<quote_char>|/quote_char> to.
Setting C<escape_char> to <undef> or C<""> will disable escaping completely
and is greatly discouraged. This will also disable C<escape_null>.
The escape character can not be equal to the separation character.
=head3 binary
X<binary>
my $csv = Text::CSV_XS->new ({ binary => 1 });
$csv->binary (0);
my $f = $csv->binary;
If this attribute is C<1>, you may use binary characters in quoted fields,
including line feeds, carriage returns and C<NULL> bytes. (The latter could
be escaped as C<"0>.) By default this feature is off.
If a string is marked UTF8, C<binary> will be turned on automatically when
binary characters other than C<CR> and C<NL> are encountered. Note that a
simple string like C<"\x{00a0}"> might still be binary, but not marked UTF8,
so setting C<< { binary => 1 } >> is still a wise option.
=head3 strict
X<strict>
my $csv = Text::CSV_XS->new ({ strict => 1 });
$csv->strict (0);
my $f = $csv->strict;
If this attribute is set to C<1>, any row that parses to a different number
of fields than the previous row will cause the parser to throw error 2014.
=head3 formula_handling
=head3 formula
X<formula_handling>
X<formula>
my $csv = Text::CSV_XS->new ({ formula => "none" });
$csv->formula ("none");
my $f = $csv->formula;
This defines the behavior of fields containing I<formulas>. As formulas are
considered dangerous in spreadsheets, this attribute can define an optional
action to be taken if a field starts with an equal sign (C<=>).
For purpose of code-readability, this can also be written as
my $csv = Text::CSV_XS->new ({ formula_handling => "none" });
$csv->formula_handling ("none");
my $f = $csv->formula_handling;
Possible values for this attribute are
=over 2
=item none
Take no specific action. This is the default.
$csv->formula ("none");
=item die
Cause the process to C<die> whenever a leading C<=> is encountered.
$csv->formula ("die");
=item croak
Cause the process to C<croak> whenever a leading C<=> is encountered. (See
L<Carp>)
$csv->formula ("croak");
=item diag
Report position and content of the field whenever a leading C<=> is found.
The value of the field is unchanged.
$csv->formula ("diag");
=item empty
Replace the content of fields that start with a C<=> with the empty string.
$csv->formula ("empty");
$csv->formula ("");
=item undef
Replace the content of fields that start with a C<=> with C<undef>.
$csv->formula ("undef");
$csv->formula (undef);
=back
All other values will give a warning and then fallback to C<diag>.
=head3 decode_utf8
X<decode_utf8>
my $csv = Text::CSV_XS->new ({ decode_utf8 => 1 });
$csv->decode_utf8 (0);
my $f = $csv->decode_utf8;
This attributes defaults to TRUE.
While I<parsing>, fields that are valid UTF-8, are automatically set to be
UTF-8, so that
$csv->parse ("\xC4\xA8\n");
results in
PV("\304\250"\0) [UTF8 "\x{128}"]
Sometimes it might not be a desired action. To prevent those upgrades, set
this attribute to false, and the result will be
PV("\304\250"\0)
=head3 auto_diag
X<auto_diag>
my $csv = Text::CSV_XS->new ({ auto_diag => 1 });
$csv->auto_diag (2);
my $l = $csv->auto_diag;
Set this attribute to a number between C<1> and C<9> causes L</error_diag>
to be automatically called in void context upon errors.
In case of error C<2012 - EOF>, this call will be void.
If C<auto_diag> is set to a numeric value greater than C<1>, it will C<die>
on errors instead of C<warn>. If set to anything unrecognized, it will be
silently ignored.
Future extensions to this feature will include more reliable auto-detection
of C<autodie> being active in the scope of which the error occurred which
will increment the value of C<auto_diag> with C<1> the moment the error is
detected.
=head3 diag_verbose
X<diag_verbose>
my $csv = Text::CSV_XS->new ({ diag_verbose => 1 });
$csv->diag_verbose (2);
my $l = $csv->diag_verbose;
Set the verbosity of the output triggered by C<auto_diag>. Currently only
adds the current input-record-number (if known) to the diagnostic output
with an indication of the position of the error.
=head3 blank_is_undef
X<blank_is_undef>
my $csv = Text::CSV_XS->new ({ blank_is_undef => 1 });
$csv->blank_is_undef (0);
my $f = $csv->blank_is_undef;
Under normal circumstances, C<CSV> data makes no distinction between quoted-
and unquoted empty fields. These both end up in an empty string field once
read, thus
1,"",," ",2
is read as
("1", "", "", " ", "2")
When I<writing> C<CSV> files with either L<C<always_quote>|/always_quote>
or L<C<quote_empty>|/quote_empty> set, the unquoted I<empty> field is the
result of an undefined value. To enable this distinction when I<reading>
C<CSV> data, the C<blank_is_undef> attribute will cause unquoted empty
fields to be set to C<undef>, causing the above to be parsed as
("1", "", undef, " ", "2")
note that this is specifically important when loading C<CSV> fields into a
database that allows C<NULL> values, as the perl equivalent for C<NULL> is
C<undef> in L<DBI> land.
=head3 empty_is_undef
X<empty_is_undef>
my $csv = Text::CSV_XS->new ({ empty_is_undef => 1 });
$csv->empty_is_undef (0);
my $f = $csv->empty_is_undef;
Going one step further than L<C<blank_is_undef>|/blank_is_undef>, this
attribute converts all empty fields to C<undef>, so
1,"",," ",2
is read as
(1, undef, undef, " ", 2)
Note that this effects only fields that are originally empty, not fields
that are empty after stripping allowed whitespace. YMMV.
=head3 allow_whitespace
X<allow_whitespace>
my $csv = Text::CSV_XS->new ({ allow_whitespace => 1 });
$csv->allow_whitespace (0);
my $f = $csv->allow_whitespace;
When this option is set to true, the whitespace (C<TAB>'s and C<SPACE>'s)
surrounding the separation character is removed when parsing. If either
C<TAB> or C<SPACE> is one of the three characters L<C<sep_char>|/sep_char>,
L<C<quote_char>|/quote_char>, or L<C<escape_char>|/escape_char> it will not
be considered whitespace.
Now lines like:
1 , "foo" , bar , 3 , zapp
are parsed as valid C<CSV>, even though it violates the C<CSV> specs.
Note that B<all> whitespace is stripped from both start and end of each
field. That would make it I<more> than a I<feature> to enable parsing bad
C<CSV> lines, as
1, 2.0, 3, ape , monkey
will now be parsed as
("1", "2.0", "3", "ape", "monkey")
even if the original line was perfectly acceptable C<CSV>.
=head3 allow_loose_quotes
X<allow_loose_quotes>
my $csv = Text::CSV_XS->new ({ allow_loose_quotes => 1 });
$csv->allow_loose_quotes (0);
my $f = $csv->allow_loose_quotes;
By default, parsing unquoted fields containing L<C<quote_char>|/quote_char>
characters like
1,foo "bar" baz,42
would result in parse error 2034. Though it is still bad practice to allow
this format, we cannot help the fact that some vendors make their
applications spit out lines styled this way.
If there is B<really> bad C<CSV> data, like
1,"foo "bar" baz",42
or
1,""foo bar baz"",42
there is a way to get this data-line parsed and leave the quotes inside the
quoted field as-is. This can be achieved by setting C<allow_loose_quotes>
B<AND> making sure that the L<C<escape_char>|/escape_char> is I<not> equal
to L<C<quote_char>|/quote_char>.
=head3 allow_loose_escapes
X<allow_loose_escapes>
my $csv = Text::CSV_XS->new ({ allow_loose_escapes => 1 });
$csv->allow_loose_escapes (0);
my $f = $csv->allow_loose_escapes;
Parsing fields that have L<C<escape_char>|/escape_char> characters that
escape characters that do not need to be escaped, like:
my $csv = Text::CSV_XS->new ({ escape_char => "\\" });
$csv->parse (qq{1,"my bar\'s",baz,42});
would result in parse error 2025. Though it is bad practice to allow this
format, this attribute enables you to treat all escape character sequences
equal.
=head3 allow_unquoted_escape
X<allow_unquoted_escape>
my $csv = Text::CSV_XS->new ({ allow_unquoted_escape => 1 });
$csv->allow_unquoted_escape (0);
my $f = $csv->allow_unquoted_escape;
A backward compatibility issue where L<C<escape_char>|/escape_char> differs
from L<C<quote_char>|/quote_char> prevents L<C<escape_char>|/escape_char>
to be in the first position of a field. If L<C<quote_char>|/quote_char> is
equal to the default C<"> and L<C<escape_char>|/escape_char> is set to C<\>,
this would be illegal:
1,\0,2
Setting this attribute to C<1> might help to overcome issues with backward
compatibility and allow this style.
=head3 always_quote
X<always_quote>
my $csv = Text::CSV_XS->new ({ always_quote => 1 });
$csv->always_quote (0);
my $f = $csv->always_quote;
By default the generated fields are quoted only if they I<need> to be. For
example, if they contain the separator character. If you set this attribute
to C<1> then I<all> defined fields will be quoted. (C<undef> fields are not
quoted, see L</blank_is_undef>). This makes it quite often easier to handle
exported data in external applications. (Poor creatures who are better to
use Text::CSV_XS. :)
=head3 quote_space
X<quote_space>
my $csv = Text::CSV_XS->new ({ quote_space => 1 });
$csv->quote_space (0);
my $f = $csv->quote_space;
By default, a space in a field would trigger quotation. As no rule exists
this to be forced in C<CSV>, nor any for the opposite, the default is true
for safety. You can exclude the space from this trigger by setting this
attribute to 0.
=head3 quote_empty
X<quote_empty>
my $csv = Text::CSV_XS->new ({ quote_empty => 1 });
$csv->quote_empty (0);
my $f = $csv->quote_empty;
By default the generated fields are quoted only if they I<need> to be. An
empty (defined) field does not need quotation. If you set this attribute to
C<1> then I<empty> defined fields will be quoted. (C<undef> fields are not
quoted, see L</blank_is_undef>). See also L<C<always_quote>|/always_quote>.
=head3 quote_binary
X<quote_binary>
my $csv = Text::CSV_XS->new ({ quote_binary => 1 });
$csv->quote_binary (0);
my $f = $csv->quote_binary;
By default, all "unsafe" bytes inside a string cause the combined field to
be quoted. By setting this attribute to C<0>, you can disable that trigger
for bytes >= C<0x7F>.
=head3 escape_null
X<escape_null>
X<quote_null>
my $csv = Text::CSV_XS->new ({ escape_null => 1 });
$csv->escape_null (0);
my $f = $csv->escape_null;
By default, a C<NULL> byte in a field would be escaped. This option enables
you to treat the C<NULL> byte as a simple binary character in binary mode
(the C<< { binary => 1 } >> is set). The default is true. You can prevent
C<NULL> escapes by setting this attribute to C<0>.
When the C<escape_char> attribute is set to undefined, this attribute will
be set to false.
The default setting will encode "=\x00=" as
"="0="
With C<escape_null> set, this will result in
"=\x00="
The default when using the C<csv> function is C<false>.
For backward compatibility reasons, the deprecated old name C<quote_null>
is still recognized.
=head3 keep_meta_info
X<keep_meta_info>
my $csv = Text::CSV_XS->new ({ keep_meta_info => 1 });
$csv->keep_meta_info (0);
my $f = $csv->keep_meta_info;
By default, the parsing of input records is as simple and fast as possible.
However, some parsing information - like quotation of the original field -
is lost in that process. Setting this flag to true enables retrieving that
information after parsing with the methods L</meta_info>, L</is_quoted>,
and L</is_binary> described below. Default is false for performance.
If you set this attribute to a value greater than 9, than you can control
output quotation style like it was used in the input of the the last parsed
record (unless quotation was added because of other reasons).
my $csv = Text::CSV_XS->new ({
binary => 1,
keep_meta_info => 1,
quote_space => 0,
});
my $row = $csv->parse (q{1,,"", ," ",f,"g","h""h",help,"help"});
$csv->print (*STDOUT, \@row);
# 1,,, , ,f,g,"h""h",help,help
$csv->keep_meta_info (11);
$csv->print (*STDOUT, \@row);
# 1,,"", ," ",f,"g","h""h",help,"help"
=head3 verbatim
X<verbatim>
my $csv = Text::CSV_XS->new ({ verbatim => 1 });
$csv->verbatim (0);
my $f = $csv->verbatim;
This is a quite controversial attribute to set, but makes some hard things
possible.
The rationale behind this attribute is to tell the parser that the normally
special characters newline (C<NL>) and Carriage Return (C<CR>) will not be
special when this flag is set, and be dealt with as being ordinary binary
characters. This will ease working with data with embedded newlines.
When C<verbatim> is used with L</getline>, L</getline> auto-C<chomp>'s
every line.
Imagine a file format like
M^^Hans^Janssen^Klas 2\n2A^Ja^11-06-2007#\r\n
where, the line ending is a very specific C<"#\r\n">, and the sep_char is a
C<^> (caret). None of the fields is quoted, but embedded binary data is
likely to be present. With the specific line ending, this should not be too
hard to detect.
By default, Text::CSV_XS' parse function is instructed to only know about
C<"\n"> and C<"\r"> to be legal line endings, and so has to deal with the
embedded newline as a real C<end-of-line>, so it can scan the next line if
binary is true, and the newline is inside a quoted field. With this option,
we tell L</parse> to parse the line as if C<"\n"> is just nothing more than
a binary character.
For L</parse> this means that the parser has no more idea about line ending
and L</getline> C<chomp>s line endings on reading.
=head3 types
A set of column types; the attribute is immediately passed to the L</types>
method.
=head3 callbacks
X<callbacks>
See the L</Callbacks> section below.
=head3 accessors
To sum it up,
$csv = Text::CSV_XS->new ();
is equivalent to
$csv = Text::CSV_XS->new ({
eol => undef, # \r, \n, or \r\n
sep_char => ',',
sep => undef,
quote_char => '"',
quote => undef,
escape_char => '"',
binary => 0,
decode_utf8 => 1,
auto_diag => 0,
diag_verbose => 0,
blank_is_undef => 0,
empty_is_undef => 0,
allow_whitespace => 0,
allow_loose_quotes => 0,
allow_loose_escapes => 0,
allow_unquoted_escape => 0,
always_quote => 0,
quote_empty => 0,
quote_space => 1,
escape_null => 1,
quote_binary => 1,
keep_meta_info => 0,
verbatim => 0,
types => undef,
callbacks => undef,
});
For all of the above mentioned flags, an accessor method is available where
you can inquire the current value, or change the value
my $quote = $csv->quote_char;
$csv->binary (1);
It is not wise to change these settings halfway through writing C<CSV> data
to a stream. If however you want to create a new stream using the available
C<CSV> object, there is no harm in changing them.
If the L</new> constructor call fails, it returns C<undef>, and makes the
fail reason available through the L</error_diag> method.
$csv = Text::CSV_XS->new ({ ecs_char => 1 }) or
die "".Text::CSV_XS->error_diag ();
L</error_diag> will return a string like
"INI - Unknown attribute 'ecs_char'"
=head2 known_attributes
X<known_attributes>
@attr = Text::CSV_CS->known_attributes;
@attr = Text::CSV_CS::known_attributes;
@attr = $csv->known_attributes;
This method will return an ordered list of all the supported attributes as
described above. This can be useful for knowing what attributes are valid
in classes that use or extend Text::CSV_XS.
=head2 print
X<print>
$status = $csv->print ($fh, $colref);
Similar to L</combine> + L</string> + L</print>, but much more efficient.
It expects an array ref as input (not an array!) and the resulting string
is not really created, but immediately written to the C<$fh> object,
typically an IO handle or any other object that offers a L</print> method.
For performance reasons C<print> does not create a result string, so all
L</string>, L</status>, L</fields>, and L</error_input> methods will return
undefined information after executing this method.
If C<$colref> is C<undef> (explicit, not through a variable argument) and
L</bind_columns> was used to specify fields to be printed, it is possible
to make performance improvements, as otherwise data would have to be copied
as arguments to the method call:
$csv->bind_columns (\($foo, $bar));
$status = $csv->print ($fh, undef);
A short benchmark
my @data = ("aa" .. "zz");
$csv->bind_columns (\(@data));
$csv->print ($fh, [ @data ]); # 11800 recs/sec
$csv->print ($fh, \@data ); # 57600 recs/sec
$csv->print ($fh, undef ); # 48500 recs/sec
=head2 say
X<say>
$status = $csv->say ($fh, $colref);
Like L<C<print>|/print>, but L<C<eol>|/eol> defaults to C<$\>.
=head2 print_hr
X<print_hr>
$csv->print_hr ($fh, $ref);
Provides an easy way to print a C<$ref> (as fetched with L</getline_hr>)
provided the column names are set with L</column_names>.
It is just a wrapper method with basic parameter checks over
$csv->print ($fh, [ map { $ref->{$_} } $csv->column_names ]);
=head2 combine
X<combine>
$status = $csv->combine (@fields);
This method constructs a C<CSV> record from C<@fields>, returning success
or failure. Failure can result from lack of arguments or an argument that
contains an invalid character. Upon success, L</string> can be called to
retrieve the resultant C<CSV> string. Upon failure, the value returned by
L</string> is undefined and L</error_input> could be called to retrieve the
invalid argument.
=head2 string
X<string>
$line = $csv->string ();
This method returns the input to L</parse> or the resultant C<CSV> string
of L</combine>, whichever was called more recently.
=head2 getline
X<getline>
$colref = $csv->getline ($fh);
This is the counterpart to L</print>, as L</parse> is the counterpart to
L</combine>: it parses a row from the C<$fh> handle using the L</getline>
method associated with C<$fh> and parses this row into an array ref. This
array ref is returned by the function or C<undef> for failure. When C<$fh>
does not support C<getline>, you are likely to hit errors.
When fields are bound with L</bind_columns> the return value is a reference
to an empty list.
The L</string>, L</fields>, and L</status> methods are meaningless again.
=head2 getline_all
X<getline_all>
$arrayref = $csv->getline_all ($fh);
$arrayref = $csv->getline_all ($fh, $offset);
$arrayref = $csv->getline_all ($fh, $offset, $length);
This will return a reference to a list of L<getline ($fh)|/getline> results.
In this call, C<keep_meta_info> is disabled. If C<$offset> is negative, as
with C<splice>, only the last C<abs ($offset)> records of C<$fh> are taken
into consideration.
Given a CSV file with 10 lines:
lines call
----- ---------------------------------------------------------
0..9 $csv->getline_all ($fh) # all
0..9 $csv->getline_all ($fh, 0) # all
8..9 $csv->getline_all ($fh, 8) # start at 8
- $csv->getline_all ($fh, 0, 0) # start at 0 first 0 rows
0..4 $csv->getline_all ($fh, 0, 5) # start at 0 first 5 rows
4..5 $csv->getline_all ($fh, 4, 2) # start at 4 first 2 rows
8..9 $csv->getline_all ($fh, -2) # last 2 rows
6..7 $csv->getline_all ($fh, -4, 2) # first 2 of last 4 rows
=head2 getline_hr
X<getline_hr>
The L</getline_hr> and L</column_names> methods work together to allow you
to have rows returned as hashrefs. You must call L</column_names> first to
declare your column names.
$csv->column_names (qw( code name price description ));
$hr = $csv->getline_hr ($fh);
print "Price for $hr->{name} is $hr->{price} EUR\n";
L</getline_hr> will croak if called before L</column_names>.
Note that L</getline_hr> creates a hashref for every row and will be much
slower than the combined use of L</bind_columns> and L</getline> but still
offering the same ease of use hashref inside the loop:
my @cols = @{$csv->getline ($fh)};
$csv->column_names (@cols);
while (my $row = $csv->getline_hr ($fh)) {
print $row->{price};
}
Could easily be rewritten to the much faster:
my @cols = @{$csv->getline ($fh)};
my $row = {};
$csv->bind_columns (\@{$row}{@cols});
while ($csv->getline ($fh)) {
print $row->{price};
}
Your mileage may vary for the size of the data and the number of rows. With
perl-5.14.2 the comparison for a 100_000 line file with 14 rows:
Rate hashrefs getlines
hashrefs 1.00/s -- -76%
getlines 4.15/s 313% --
=head2 getline_hr_all
X<getline_hr_all>
$arrayref = $csv->getline_hr_all ($fh);
$arrayref = $csv->getline_hr_all ($fh, $offset);
$arrayref = $csv->getline_hr_all ($fh, $offset, $length);
This will return a reference to a list of L<getline_hr ($fh)|/getline_hr>
results. In this call, L<C<keep_meta_info>|/keep_meta_info> is disabled.
=head2 parse
X<parse>
$status = $csv->parse ($line);
This method decomposes a C<CSV> string into fields, returning success or
failure. Failure can result from a lack of argument or the given C<CSV>
string is improperly formatted. Upon success, L</fields> can be called to
retrieve the decomposed fields. Upon failure calling L</fields> will return
undefined data and L</error_input> can be called to retrieve the invalid
argument.
You may use the L</types> method for setting column types. See L</types>'
description below.
The C<$line> argument is supposed to be a simple scalar. Everything else is
supposed to croak and set error 1500.
=head2 fragment
X<fragment>
This function tries to implement RFC7111 (URI Fragment Identifiers for the
text/csv Media Type) - http://tools.ietf.org/html/rfc7111
my $AoA = $csv->fragment ($fh, $spec);
In specifications, C<*> is used to specify the I<last> item, a dash (C<->)
to indicate a range. All indices are C<1>-based: the first row or column
has index C<1>. Selections can be combined with the semi-colon (C<;>).
When using this method in combination with L</column_names>, the returned
reference will point to a list of hashes instead of a list of lists. A
disjointed cell-based combined selection might return rows with different
number of columns making the use of hashes unpredictable.
$csv->column_names ("Name", "Age");
my $AoH = $csv->fragment ($fh, "col=3;8");
If the L</after_parse> callback is active, it is also called on every line
parsed and skipped before the fragment.
=over 2
=item row
row=4
row=5-7
row=6-*
row=1-2;4;6-*
=item col
col=2
col=1-3
col=4-*
col=1-2;4;7-*
=item cell
In cell-based selection, the comma (C<,>) is used to pair row and column
cell=4,1
The range operator (C<->) using C<cell>s can be used to define top-left and
bottom-right C<cell> location
cell=3,1-4,6
The C<*> is only allowed in the second part of a pair
cell=3,2-*,2 # row 3 till end, only column 2
cell=3,2-3,* # column 2 till end, only row 3
cell=3,2-*,* # strip row 1 and 2, and column 1
Cells and cell ranges may be combined with C<;>, possibly resulting in rows
with different number of columns
cell=1,1-2,2;3,3-4,4;1,4;4,1
Disjointed selections will only return selected cells. The cells that are
not specified will not be included in the returned set, not even as
C<undef>. As an example given a C<CSV> like
11,12,13,...19
21,22,...28,29
: :
91,...97,98,99
with C<cell=1,1-2,2;3,3-4,4;1,4;4,1> will return:
11,12,14
21,22
33,34
41,43,44
Overlapping cell-specs will return those cells only once, So
C<cell=1,1-3,3;2,2-4,4;2,3;4,2> will return:
11,12,13
21,22,23,24
31,32,33,34
42,43,44
=back
L<RFC7111|http://tools.ietf.org/html/rfc7111> does B<not> allow different
types of specs to be combined (either C<row> I<or> C<col> I<or> C<cell>).
Passing an invalid fragment specification will croak and set error 2013.
=head2 column_names
X<column_names>
Set the "keys" that will be used in the L</getline_hr> calls. If no keys
(column names) are passed, it will return the current setting as a list.
L</column_names> accepts a list of scalars (the column names) or a single
array_ref, so you can pass the return value from L</getline> too:
$csv->column_names ($csv->getline ($fh));
L</column_names> does B<no> checking on duplicates at all, which might lead
to unexpected results. Undefined entries will be replaced with the string
C<"\cAUNDEF\cA">, so
$csv->column_names (undef, "", "name", "name");
$hr = $csv->getline_hr ($fh);
Will set C<< $hr->{"\cAUNDEF\cA"} >> to the 1st field, C<< $hr->{""} >> to
the 2nd field, and C<< $hr->{name} >> to the 4th field, discarding the 3rd
field.
L</column_names> croaks on invalid arguments.
=head2 header
This method does NOT work in perl-5.6.x
Parse the CSV header and set L<C<sep>|/sep>, column_names and encoding.
my @hdr = $csv->header ($fh);
$csv->header ($fh, { sep_set => [ ";", ",", "|", "\t" ] });
$csv->header ($fh, { detect_bom => 1, munge_column_names => "lc" });
The first argument should be a file handle.
This method resets some object properties, as it is supposed to be invoked
only once per file or stream. It will leave attributes C<column_names> and
C<bound_columns> alone of setting column names is disabled. Reading headers
on previously process objects might fail on perl-5.8.0 and older.
Assuming that the file opened for parsing has a header, and the header does
not contain problematic characters like embedded newlines, read the first
line from the open handle then auto-detect whether the header separates the
column names with a character from the allowed separator list.
If any of the allowed separators matches, and none of the I<other> allowed
separators match, set L<C<sep>|/sep> to that separator for the current
CSV_XS instance and use it to parse the first line, map those to lowercase,
and use that to set the instance L</column_names>:
my $csv = Text::CSV_XS->new ({ binary => 1, auto_diag => 1 });
open my $fh, "<", "file.csv";
binmode $fh; # for Windows
$csv->header ($fh);
while (my $row = $csv->getline_hr ($fh)) {
...
}
If the header is empty, contains more than one unique separator out of the
allowed set, contains empty fields, or contains identical fields (after
folding), it will croak with error 1010, 1011, 1012, or 1013 respectively.
If the header contains embedded newlines or is not valid CSV in any other
way, this method will croak and leave the parse error untouched.
A successful call to C<header> will always set the L<C<sep>|/sep> of the
C<$csv> object. This behavior can not be disabled.
=head3 return value
On error this method will croak.
In list context, the headers will be returned whether they are used to set
L</column_names> or not.
In scalar context, the instance itself is returned. B<Note>: the values as
found in the header will effectively be B<lost> if C<set_column_names> is
false.
=head3 Options
=over 2
=item sep_set
X<sep_set>
$csv->header ($fh, { sep_set => [ ";", ",", "|", "\t" ] });
The list of legal separators defaults to C<[ ";", "," ]> and can be changed
by this option. As this is probably the most often used option, it can be
passed on its own as an unnamed argument:
$csv->header ($fh, [ ";", ",", "|", "\t", "::", "\x{2063}" ]);
Multi-byte sequences are allowed, both multi-character and Unicode. See
L<C<sep>|/sep>.
=item detect_bom
X<detect_bom>
$csv->header ($fh, { detect_bom => 1 });
The default behavior is to detect if the header line starts with a BOM. If
the header has a BOM, use that to set the encoding of C<$fh>. This default
behavior can be disabled by passing a false value to C<detect_bom>.
Supported encodings from BOM are: UTF-8, UTF-16BE, UTF-16LE, UTF-32BE, and
UTF-32LE. BOM's also support UTF-1, UTF-EBCDIC, SCSU, BOCU-1, and GB-18030
but L<Encode> does not (yet). UTF-7 is not supported.
The encoding is set using C<binmode> on C<$fh>.
If the handle was opened in a (correct) encoding, this method will B<not>
alter the encoding, as it checks the leading B<bytes> of the first line.
=item munge_column_names
X<munge_column_names>
This option offers the means to modify the column names into something that
is most useful to the application. The default is to map all column names
to lower case.
$csv->header ($fh, { munge_column_names => "lc" });
The following values are available:
lc - lower case
uc - upper case
none - do not change
\%hash - supply a mapping
\&cb - supply a callback
Literal:
$csv->header ($fh, { munge_column_names => "none" });
Hash:
$csv->header ($fh, { munge_column_names => { foo => "sombrero" });
if a value does not exist, the original value is used unchanged
Callback:
$csv->header ($fh, { munge_column_names => sub { fc } });
$csv->header ($fh, { munge_column_names => sub { "column_".$col++ } });
$csv->header ($fh, { munge_column_names => sub { lc (s/\W+/_/gr) } });
As this callback is called in a C<map>, you can use C<$_> directly.
=item set_column_names
X<set_column_names>
$csv->header ($fh, { set_column_names => 1 });
The default is to set the instances column names using L</column_names> if
the method is successful, so subsequent calls to L</getline_hr> can return
a hash. Disable setting the header can be forced by using a false value for
this option.
As described in L</return value> above, content is lost in scalar context.
=back
=head3 Validation
When receiving CSV files from external sources, this method can be used to
protect against changes in the layout by restricting to known headers (and
typos in the header fields).
my %known = (
"record key" => "c_rec",
"rec id" => "c_rec",
"id_rec" => "c_rec",
"kode" => "code",
"code" => "code",
"vaule" => "value",
"value" => "value",
);
my $csv = Text::CSV_XS->new ({ binary => 1, auto_diag => 1 });
open my $fh, "<", $source or die "$source: $!";
$csv->header ($fh, { munge_column_names => sub {
s/\s+$//;
s/^\s+//;
$known{lc $_} or die "Unknown column '$_' in $source";
}});
while (my $row = $csv->getline_hr ($fh)) {
say join "\t", $row->{c_rec}, $row->{code}, $row->{value};
}
=head2 bind_columns
X<bind_columns>
Takes a list of scalar references to be used for output with L</print> or
to store in the fields fetched by L</getline>. When you do not pass enough
references to store the fetched fields in, L</getline> will fail with error
C<3006>. If you pass more than there are fields to return, the content of
the remaining references is left untouched.
$csv->bind_columns (\$code, \$name, \$price, \$description);
while ($csv->getline ($fh)) {
print "The price of a $name is \x{20ac} $price\n";
}
To reset or clear all column binding, call L</bind_columns> with the single
argument C<undef>. This will also clear column names.
$csv->bind_columns (undef);
If no arguments are passed at all, L</bind_columns> will return the list of
current bindings or C<undef> if no binds are active.
Note that in parsing with C<bind_columns>, the fields are set on the fly.
That implies that if the third field of a row causes an error (or this row
has just two fields where the previous row had more), the first two fields
already have been assigned the values of the current row, while the rest of
the fields will still hold the values of the previous row. If you want the
parser to fail in these cases, use the L<C<strict>|/strict> attribute.
=head2 eof
X<eof>
$eof = $csv->eof ();
If L</parse> or L</getline> was used with an IO stream, this method will
return true (1) if the last call hit end of file, otherwise it will return
false (''). This is useful to see the difference between a failure and end
of file.
Note that if the parsing of the last line caused an error, C<eof> is still
true. That means that if you are I<not> using L</auto_diag>, an idiom like
while (my $row = $csv->getline ($fh)) {
# ...
}
$csv->eof or $csv->error_diag;
will I<not> report the error. You would have to change that to
while (my $row = $csv->getline ($fh)) {
# ...
}
+$csv->error_diag and $csv->error_diag;
=head2 types
X<types>
$csv->types (\@tref);
This method is used to force that (all) columns are of a given type. For
example, if you have an integer column, two columns with doubles and a
string column, then you might do a
$csv->types ([Text::CSV_XS::IV (),
Text::CSV_XS::NV (),
Text::CSV_XS::NV (),
Text::CSV_XS::PV ()]);
Column types are used only for I<decoding> columns while parsing, in other
words by the L</parse> and L</getline> methods.
You can unset column types by doing a
$csv->types (undef);
or fetch the current type settings with
$types = $csv->types ();
=over 4
=item IV
X<IV>
Set field type to integer.
=item NV
X<NV>
Set field type to numeric/float.
=item PV
X<PV>
Set field type to string.
=back
=head2 fields
X<fields>
@columns = $csv->fields ();
This method returns the input to L</combine> or the resultant decomposed
fields of a successful L</parse>, whichever was called more recently.
Note that the return value is undefined after using L</getline>, which does
not fill the data structures returned by L</parse>.
=head2 meta_info
X<meta_info>
@flags = $csv->meta_info ();
This method returns the "flags" of the input to L</combine> or the flags of
the resultant decomposed fields of L</parse>, whichever was called more
recently.
For each field, a meta_info field will hold flags that inform something
about the field returned by the L</fields> method or passed to the
L</combine> method. The flags are bit-wise-C<or>'d like:
=over 2
=item C< >0x0001
The field was quoted.
=item C< >0x0002
The field was binary.
=back
See the C<is_***> methods below.
=head2 is_quoted
X<is_quoted>
my $quoted = $csv->is_quoted ($column_idx);
Where C<$column_idx> is the (zero-based) index of the column in the last
result of L</parse>.
This returns a true value if the data in the indicated column was enclosed
in L<C<quote_char>|/quote_char> quotes. This might be important for fields
where content C<,20070108,> is to be treated as a numeric value, and where
C<,"20070108",> is explicitly marked as character string data.
This method is only valid when L</keep_meta_info> is set to a true value.
=head2 is_binary
X<is_binary>
my $binary = $csv->is_binary ($column_idx);
Where C<$column_idx> is the (zero-based) index of the column in the last
result of L</parse>.
This returns a true value if the data in the indicated column contained any
byte in the range C<[\x00-\x08,\x10-\x1F,\x7F-\xFF]>.
This method is only valid when L</keep_meta_info> is set to a true value.
=head2 is_missing
X<is_missing>
my $missing = $csv->is_missing ($column_idx);
Where C<$column_idx> is the (zero-based) index of the column in the last
result of L</getline_hr>.
$csv->keep_meta_info (1);
while (my $hr = $csv->getline_hr ($fh)) {
$csv->is_missing (0) and next; # This was an empty line
}
When using L</getline_hr>, it is impossible to tell if the parsed fields
are C<undef> because they where not filled in the C<CSV> stream or because
they were not read at all, as B<all> the fields defined by L</column_names>
are set in the hash-ref. If you still need to know if all fields in each
row are provided, you should enable L<C<keep_meta_info>|/keep_meta_info> so
you can check the flags.
If L<C<keep_meta_info>|/keep_meta_info> is C<false>, C<is_missing> will
always return C<undef>, regardless of C<$column_idx> being valid or not. If
this attribute is C<true> it will return either C<0> (the field is present)
or C<1> (the field is missing).
A special case is the empty line. If the line is completely empty - after
dealing with the flags - this is still a valid CSV line: it is a record of
just one single empty field. However, if C<keep_meta_info> is set, invoking
C<is_missing> with index C<0> will now return true.
=head2 status
X<status>
$status = $csv->status ();
This method returns the status of the last invoked L</combine> or L</parse>
call. Status is success (true: C<1>) or failure (false: C<undef> or C<0>).
=head2 error_input
X<error_input>
$bad_argument = $csv->error_input ();
This method returns the erroneous argument (if it exists) of L</combine> or
L</parse>, whichever was called more recently. If the last invocation was
successful, C<error_input> will return C<undef>.
=head2 error_diag
X<error_diag>
Text::CSV_XS->error_diag ();
$csv->error_diag ();
$error_code = 0 + $csv->error_diag ();
$error_str = "" . $csv->error_diag ();
($cde, $str, $pos, $rec, $fld) = $csv->error_diag ();
If (and only if) an error occurred, this function returns the diagnostics
of that error.
If called in void context, this will print the internal error code and the
associated error message to STDERR.
If called in list context, this will return the error code and the error
message in that order. If the last error was from parsing, the rest of the
values returned are a best guess at the location within the line that was
being parsed. Their values are 1-based. The position currently is index of
the byte at which the parsing failed in the current record. It might change
to be the index of the current character in a later release. The records is
the index of the record parsed by the csv instance. The field number is the
index of the field the parser thinks it is currently trying to parse. See
F<examples/csv-check> for how this can be used.
If called in scalar context, it will return the diagnostics in a single
scalar, a-la C<$!>. It will contain the error code in numeric context, and
the diagnostics message in string context.
When called as a class method or a direct function call, the diagnostics
are that of the last L</new> call.
=head2 record_number
X<record_number>
$recno = $csv->record_number ();
Returns the records parsed by this csv instance. This value should be more
accurate than C<$.> when embedded newlines come in play. Records written by
this instance are not counted.
=head2 SetDiag
X<SetDiag>
$csv->SetDiag (0);
Use to reset the diagnostics if you are dealing with errors.
=head1 FUNCTIONS
=head2 csv
X<csv>
This function is not exported by default and should be explicitly requested:
use Text::CSV_XS qw( csv );
This is an high-level function that aims at simple (user) interfaces. This
can be used to read/parse a C<CSV> file or stream (the default behavior) or
to produce a file or write to a stream (define the C<out> attribute). It
returns an array- or hash-reference on parsing (or C<undef> on fail) or the
numeric value of L</error_diag> on writing. When this function fails you
can get to the error using the class call to L</error_diag>
my $aoa = csv (in => "test.csv") or
die Text::CSV_XS->error_diag;
This function takes the arguments as key-value pairs. This can be passed as
a list or as an anonymous hash:
my $aoa = csv ( in => "test.csv", sep_char => ";");
my $aoh = csv ({ in => $fh, headers => "auto" });
The arguments passed consist of two parts: the arguments to L</csv> itself
and the optional attributes to the C<CSV> object used inside the function
as enumerated and explained in L</new>.
If not overridden, the default option used for CSV is
auto_diag => 1
escape_null => 0
The option that is always set and cannot be altered is
binary => 1
As this function will likely be used in one-liners, it allows C<quote> to
be abbreviated as C<quo>, and C<escape_char> to be abbreviated as C<esc>
or C<escape>.
Alternative invocations:
my $aoa = Text::CSV_XS::csv (in => "file.csv");
my $csv = Text::CSV_XS->new ();
my $aoa = $csv->csv (in => "file.csv");
In the latter case, the object attributes are used from the existing object
and the attribute arguments in the function call are ignored:
my $csv = Text::CSV_XS->new ({ sep_char => ";" });
my $aoh = $csv->csv (in => "file.csv", bom => 1);
will parse using C<;> as C<sep_char>, not C<,>.
=head3 in
X<in>
Used to specify the source. C<in> can be a file name (e.g. C<"file.csv">),
which will be opened for reading and closed when finished, a file handle
(e.g. C<$fh> or C<FH>), a reference to a glob (e.g. C<\*ARGV>), the glob
itself (e.g. C<*STDIN>), or a reference to a scalar (e.g. C<\q{1,2,"csv"}>).
When used with L</out>, C<in> should be a reference to a CSV structure (AoA
or AoH) or a CODE-ref that returns an array-reference or a hash-reference.
The code-ref will be invoked with no arguments.
my $aoa = csv (in => "file.csv");
open my $fh, "<", "file.csv";
my $aoa = csv (in => $fh);
my $csv = [ [qw( Foo Bar )], [ 1, 2 ], [ 2, 3 ]];
my $err = csv (in => $csv, out => "file.csv");
If called in void context without the L</out> attribute, the resulting ref
will be used as input to a subsequent call to csv:
csv (in => "file.csv", filter => { 2 => sub { length > 2 }})
will be a shortcut to
csv (in => csv (in => "file.csv", filter => { 2 => sub { length > 2 }}))
where, in the absence of the C<out> attribute, this is a shortcut to
csv (in => csv (in => "file.csv", filter => { 2 => sub { length > 2 }}),
out => *STDOUT)
=head3 out
X<out>
csv (in => $aoa, out => "file.csv");
csv (in => $aoa, out => $fh);
csv (in => $aoa, out => STDOUT);
csv (in => $aoa, out => *STDOUT);
csv (in => $aoa, out => \*STDOUT);
csv (in => $aoa, out => \my $data);
In output mode, the default CSV options when producing CSV are
eol => "\r\n"
The L</fragment> attribute is ignored in output mode.
C<out> can be a file name (e.g. C<"file.csv">), which will be opened for
writing and closed when finished, a file handle (e.g. C<$fh> or C<FH>), a
reference to a glob (e.g. C<\*STDOUT>), the glob itself (e.g. C<*STDOUT>),
or a reference to a scalar (e.g. C<\my $data>).
csv (in => sub { $sth->fetch }, out => "dump.csv");
csv (in => sub { $sth->fetchrow_hashref }, out => "dump.csv",
headers => $sth->{NAME_lc});
When a code-ref is used for C<in>, the output is generated per invocation,
so no buffering is involved. This implies that there is no size restriction
on the number of records. The C<csv> function ends when the coderef returns
a false value.
=head3 encoding
X<encoding>
If passed, it should be an encoding accepted by the C<:encoding()> option
to C<open>. There is no default value. This attribute does not work in perl
5.6.x. C<encoding> can be abbreviated to C<enc> for ease of use in command
line invocations.
If C<encoding> is set to the literal value C<"auto">, the method L</header>
will be invoked on the opened stream to check if there is a BOM and set the
encoding accordingly. This is equal to passing a true value in the option
L<C<detect_bom>|/detect_bom>.
=head3 detect_bom
X<detect_bom>
If C<detect_bom> is given, the method L</header> will be invoked on the
opened stream to check if there is a BOM and set the encoding accordingly.
C<detect_bom> can be abbreviated to C<bom>.
This is the same as setting L<C<encoding>|/encoding> to C<"auto">.
Note that as the method L</header> is invoked, its default is to also set
the headers.
=head3 headers
X<headers>
If this attribute is not given, the default behavior is to produce an array
of arrays.
If C<headers> is supplied, it should be an anonymous list of column names,
an anonymous hashref, a coderef, or a literal flag: C<auto>, C<lc>, C<uc>,
or C<skip>.
=over 2
=item skip
X<skip>
When C<skip> is used, the header will not be included in the output.
my $aoa = csv (in => $fh, headers => "skip");
=item auto
X<auto>
If C<auto> is used, the first line of the C<CSV> source will be read as the
list of field headers and used to produce an array of hashes.
my $aoh = csv (in => $fh, headers => "auto");
=item lc
X<lc>
If C<lc> is used, the first line of the C<CSV> source will be read as the
list of field headers mapped to lower case and used to produce an array of
hashes. This is a variation of C<auto>.
my $aoh = csv (in => $fh, headers => "lc");
=item uc
X<uc>
If C<uc> is used, the first line of the C<CSV> source will be read as the
list of field headers mapped to upper case and used to produce an array of
hashes. This is a variation of C<auto>.
my $aoh = csv (in => $fh, headers => "uc");
=item CODE
X<CODE>
If a coderef is used, the first line of the C<CSV> source will be read as
the list of mangled field headers in which each field is passed as the only
argument to the coderef. This list is used to produce an array of hashes.
my $aoh = csv (in => $fh,
headers => sub { lc ($_[0]) =~ s/kode/code/gr });
this example is a variation of using C<lc> where all occurrences of C<kode>
are replaced with C<code>.
=item ARRAY
X<ARRAY>
If C<headers> is an anonymous list, the entries in the list will be used
as field names. The first line is considered data instead of headers.
my $aoh = csv (in => $fh, headers => [qw( Foo Bar )]);
csv (in => $aoa, out => $fh, headers => [qw( code description price )]);
=item HASH
X<HASH>
If C<headers> is an hash reference, this implies C<auto>, but header fields
for that exist as key in the hashref will be replaced by the value for that
key. Given a CSV file like
post-kode,city,name,id number,fubble
1234AA,Duckstad,Donald,13,"X313DF"
using
csv (headers => { "post-kode" => "pc", "id number" => "ID" }, ...
will return an entry like
{ pc => "1234AA",
city => "Duckstad",
name => "Donald",
ID => "13",
fubble => "X313DF",
}
=back
See also L<C<munge_column_names>|/munge_column_names> and
L<C<set_column_names>|/set_column_names>.
=head3 munge_column_names
X<munge_column_names>
If C<munge_column_names> is set, the method L</header> is invoked on the
opened stream with all matching arguments to detect and set the headers.
C<munge_column_names> can be abbreviated to C<munge>.
=head3 key
X<key>
If passed, will default L<C<headers>|/headers> to C<"auto"> and return a
hashref instead of an array of hashes.
my $ref = csv (in => "test.csv", key => "code");
with test.csv like
code,product,price,color
1,pc,850,gray
2,keyboard,12,white
3,mouse,5,black
will return
{ 1 => {
code => 1,
color => 'gray',
price => 850,
product => 'pc'
},
2 => {
code => 2,
color => 'white',
price => 12,
product => 'keyboard'
},
3 => {
code => 3,
color => 'black',
price => 5,
product => 'mouse'
}
}
The C<key> attribute can be combined with L<C<headers>|/headers> for C<CSV>
date that has no header line, like
my $ref = csv (
in => "foo.csv",
headers => [qw( c_foo foo bar description stock )],
key => "c_foo",
);
=head3 keep_headers
X<keep_headers>
X<keep_column_names>
X<kh>
When using hashes, keep the column names into the arrayref passed, so all
headers are available after the call in the original order.
my $aoh = csv (in => "file.csv", keep_headers => \my @hdr);
This attribute can be abbreviated to C<kh> or passed as C<keep_column_names>.
This attribute implies a default of C<auto> for the C<headers> attribute.
=head3 fragment
X<fragment>
Only output the fragment as defined in the L</fragment> method. This option
is ignored when I<generating> C<CSV>. See L</out>.
Combining all of them could give something like
use Text::CSV_XS qw( csv );
my $aoh = csv (
in => "test.txt",
encoding => "utf-8",
headers => "auto",
sep_char => "|",
fragment => "row=3;6-9;15-*",
);
say $aoh->[15]{Foo};
=head3 sep_set
X<sep_set>
X<seps>
If C<sep_set> is set, the method L</header> is invoked on the opened stream
to detect and set L<C<sep_char>|/sep_char> with the given set.
C<sep_set> can be abbreviated to C<seps>.
Note that as the L</header> method is invoked, its default is to also set
the headers.
=head3 set_column_names
X<set_column_names>
If C<set_column_names> is passed, the method L</header> is invoked on the
opened stream with all arguments meant for L</header>.
If C<set_column_names> is passed as a false value, the content of the first
row is only preserved if the output is AoA:
With an input-file like
bAr,foo
1,2
3,4,5
This call
my $aoa = csv (in => $file, set_column_names => 0);
will result in
[[ "bar", "foo" ],
[ "1", "2" ],
[ "3", "4", "5" ]]
and
my $aoa = csv (in => $file, set_column_names => 0, munge => "none");
will result in
[[ "bAr", "foo" ],
[ "1", "2" ],
[ "3", "4", "5" ]]
=head2 Callbacks
X<Callbacks>
Callbacks enable actions triggered from the I<inside> of Text::CSV_XS.
While most of what this enables can easily be done in an unrolled loop as
described in the L</SYNOPSIS> callbacks can be used to meet special demands
or enhance the L</csv> function.
=over 2
=item error
X<error>
$csv->callbacks (error => sub { $csv->SetDiag (0) });
the C<error> callback is invoked when an error occurs, but I<only> when
L</auto_diag> is set to a true value. A callback is invoked with the values
returned by L</error_diag>:
my ($c, $s);
sub ignore3006
{
my ($err, $msg, $pos, $recno, $fldno) = @_;
if ($err == 3006) {
# ignore this error
($c, $s) = (undef, undef);
Text::CSV_XS->SetDiag (0);
}
# Any other error
return;
} # ignore3006
$csv->callbacks (error => \&ignore3006);
$csv->bind_columns (\$c, \$s);
while ($csv->getline ($fh)) {
# Error 3006 will not stop the loop
}
=item after_parse
X<after_parse>
$csv->callbacks (after_parse => sub { push @{$_[1]}, "NEW" });
while (my $row = $csv->getline ($fh)) {
$row->[-1] eq "NEW";
}
This callback is invoked after parsing with L</getline> only if no error
occurred. The callback is invoked with two arguments: the current C<CSV>
parser object and an array reference to the fields parsed.
The return code of the callback is ignored unless it is a reference to the
string "skip", in which case the record will be skipped in L</getline_all>.
sub add_from_db
{
my ($csv, $row) = @_;
$sth->execute ($row->[4]);
push @$row, $sth->fetchrow_array;
} # add_from_db
my $aoa = csv (in => "file.csv", callbacks => {
after_parse => \&add_from_db });
This hook can be used for validation:
X<validation>
=over 2
=item FAIL
Die if any of the records does not validate a rule:
after_parse => sub {
$_[1][4] =~ m/^[0-9]{4}\s?[A-Z]{2}$/ or
die "5th field does not have a valid Dutch zipcode";
}
=item DEFAULT
Replace invalid fields with a default value:
after_parse => sub { $_[1][2] =~ m/^\d+$/ or $_[1][2] = 0 }
=item SKIP
Skip records that have invalid fields (only applies to L</getline_all>):
after_parse => sub { $_[1][0] =~ m/^\d+$/ or return \"skip"; }
=back
=item before_print
X<before_print>
my $idx = 1;
$csv->callbacks (before_print => sub { $_[1][0] = $idx++ });
$csv->print (*STDOUT, [ 0, $_ ]) for @members;
This callback is invoked before printing with L</print> only if no error
occurred. The callback is invoked with two arguments: the current C<CSV>
parser object and an array reference to the fields passed.
The return code of the callback is ignored.
sub max_4_fields
{
my ($csv, $row) = @_;
@$row > 4 and splice @$row, 4;
} # max_4_fields
csv (in => csv (in => "file.csv"), out => *STDOUT,
callbacks => { before print => \&max_4_fields });
This callback is not active for L</combine>.
=back
=head3 Callbacks for csv ()
The L</csv> allows for some callbacks that do not integrate in XS internals
but only feature the L</csv> function.
csv (in => "file.csv",
callbacks => {
filter => { 6 => sub { $_ > 15 } }, # first
after_parse => sub { say "AFTER PARSE"; }, # first
after_in => sub { say "AFTER IN"; }, # second
on_in => sub { say "ON IN"; }, # third
},
);
csv (in => $aoh,
out => "file.csv",
callbacks => {
on_in => sub { say "ON IN"; }, # first
before_out => sub { say "BEFORE OUT"; }, # second
before_print => sub { say "BEFORE PRINT"; }, # third
},
);
=over 2
=item filter
X<filter>
This callback can be used to filter records. It is called just after a new
record has been scanned. The callback accepts a hashref where the keys are
the index to the row (the field number, 1-based) and the values are subs to
return a true or false value.
csv (in => "file.csv", filter => {
3 => sub { m/a/ }, # third field should contain an "a"
5 => sub { length > 4 }, # length of the 5th field minimal 5
});
csv (in => "file.csv", filter => "not_blank");
csv (in => "file.csv", filter => "not_empty");
csv (in => "file.csv", filter => "filled");
If the keys to the filter hash contain any character that is not a digit it
will also implicitly set L</headers> to C<"auto"> unless L</headers> was
already passed as argument. When headers are active, returning an array of
hashes, the filter is not applicable to the header itself.
csv (in => "file.csv", filter => { foo => sub { $_ > 4 }});
All sub results should match, as in AND.
The context of the callback sets C<$_> localized to the field indicated by
the filter. The two arguments are as with all other callbacks, so the other
fields in the current row can be seen:
filter => { 3 => sub { $_ > 100 ? $_[1][1] =~ m/A/ : $_[1][6] =~ m/B/ }}
If the context is set to return a list of hashes (L</headers> is defined),
the current record will also be available in the localized C<%_>:
filter => { 3 => sub { $_ > 100 && $_{foo} =~ m/A/ && $_{bar} < 1000 }}
If the filter is used to I<alter> the content by changing C<$_>, make sure
that the sub returns true in order not to have that record skipped:
filter => { 2 => sub { $_ = uc }}
will upper-case the second field, and then skip it if the resulting content
evaluates to false. To always accept, end with truth:
filter => { 2 => sub { $_ = uc; 1 }}
B<Predefined filters>
Given a file like (line numbers prefixed for doc purpose only):
1:1,2,3
2:
3:,
4:""
5:,,
6:, ,
7:"",
8:" "
9:4,5,6
=over 2
=item not_blank
Filter out the blank lines
This filter is a shortcut for
filter => { 0 => sub { @{$_[1]} > 1 or
defined $_[1][0] && $_[1][0] ne "" } }
Due to the implementation, it is currently impossible to also filter lines
that consists only of a quoted empty field. These lines are also considered
blank lines.
With the given example, lines 2 and 4 will be skipped.
=item not_empty
Filter out lines where all the fields are empty.
This filter is a shortcut for
filter => { 0 => sub { grep { defined && $_ ne "" } @{$_[1]} } }
A space is not regarded being empty, so given the example data, lines 2, 3,
4, 5, and 7 are skipped.
=item filled
Filter out lines that have no visible data
This filter is a shortcut for
filter => { 0 => sub { grep { defined && m/\S/ } @{$_[1]} } }
This filter rejects all lines that I<not> have at least one field that does
not evaluate to the empty string.
With the given example data, this filter would skip lines 2 through 8.
=back
=item after_in
X<after_in>
This callback is invoked for each record after all records have been parsed
but before returning the reference to the caller. The hook is invoked with
two arguments: the current C<CSV> parser object and a reference to the
record. The reference can be a reference to a HASH or a reference to an
ARRAY as determined by the arguments.
This callback can also be passed as an attribute without the C<callbacks>
wrapper.
=item before_out
X<before_out>
This callback is invoked for each record before the record is printed. The
hook is invoked with two arguments: the current C<CSV> parser object and a
reference to the record. The reference can be a reference to a HASH or a
reference to an ARRAY as determined by the arguments.
This callback can also be passed as an attribute without the C<callbacks>
wrapper.
This callback makes the row available in C<%_> if the row is a hashref. In
this case C<%_> is writable and will change the original row.
=item on_in
X<on_in>
This callback acts exactly as the L</after_in> or the L</before_out> hooks.
This callback can also be passed as an attribute without the C<callbacks>
wrapper.
This callback makes the row available in C<%_> if the row is a hashref. In
this case C<%_> is writable and will change the original row. So e.g. with
my $aoh = csv (
in => \"foo\n1\n2\n",
headers => "auto",
on_in => sub { $_{bar} = 2; },
);
C<$aoh> will be:
[ { foo => 1,
bar => 2,
}
{ foo => 2,
bar => 2,
}
]
=item csv
The I<function> L</csv> can also be called as a method or with an existing
Text::CSV_XS object. This could help if the function is to be invoked a lot
of times and the overhead of creating the object internally over and over
again would be prevented by passing an existing instance.
my $csv = Text::CSV_XS->new ({ binary => 1, auto_diag => 1 });
my $aoa = $csv->csv (in => $fh);
my $aoa = csv (in => $fh, csv => $csv);
both act the same. Running this 20000 times on a 20 lines CSV file, showed
a 53% speedup.
=back
=head1 INTERNALS
=over 4
=item Combine (...)
=item Parse (...)
=back
The arguments to these internal functions are deliberately not described or
documented in order to enable the module authors make changes it when they
feel the need for it. Using them is highly discouraged as the API may
change in future releases.
=head1 EXAMPLES
=head2 Reading a CSV file line by line:
my $csv = Text::CSV_XS->new ({ binary => 1, auto_diag => 1 });
open my $fh, "<", "file.csv" or die "file.csv: $!";
while (my $row = $csv->getline ($fh)) {
# do something with @$row
}
close $fh or die "file.csv: $!";
or
my $aoa = csv (in => "file.csv", on_in => sub {
# do something with %_
});
=head3 Reading only a single column
my $csv = Text::CSV_XS->new ({ binary => 1, auto_diag => 1 });
open my $fh, "<", "file.csv" or die "file.csv: $!";
# get only the 4th column
my @column = map { $_->[3] } @{$csv->getline_all ($fh)};
close $fh or die "file.csv: $!";
with L</csv>, you could do
my @column = map { $_->[0] }
@{csv (in => "file.csv", fragment => "col=4")};
=head2 Parsing CSV strings:
my $csv = Text::CSV_XS->new ({ keep_meta_info => 1, binary => 1 });
my $sample_input_string =
qq{"I said, ""Hi!""",Yes,"",2.34,,"1.09","\x{20ac}",};
if ($csv->parse ($sample_input_string)) {
my @field = $csv->fields;
foreach my $col (0 .. $#field) {
my $quo = $csv->is_quoted ($col) ? $csv->{quote_char} : "";
printf "%2d: %s%s%s\n", $col, $quo, $field[$col], $quo;
}
}
else {
print STDERR "parse () failed on argument: ",
$csv->error_input, "\n";
$csv->error_diag ();
}
=head3 Parsing CSV from memory
Given a complete CSV data-set in scalar C<$data>, generate a list of lists
to represent the rows and fields
# The data
my $data = join "\r\n" => map { join "," => 0 .. 5 } 0 .. 5;
# in a loop
my $csv = Text::CSV_XS->new ({ binary => 1, auto_diag => 1 });
open my $fh, "<", \$data;
my @foo;
while (my $row = $csv->getline ($fh)) {
push @foo, $row;
}
close $fh;
# a single call
my $foo = csv (in => \$data);
=head2 Printing CSV data
=head3 The fast way: using L</print>
An example for creating C<CSV> files using the L</print> method:
my $csv = Text::CSV_XS->new ({ binary => 1, eol => $/ });
open my $fh, ">", "foo.csv" or die "foo.csv: $!";
for (1 .. 10) {
$csv->print ($fh, [ $_, "$_" ]) or $csv->error_diag;
}
close $fh or die "$tbl.csv: $!";
=head3 The slow way: using L</combine> and L</string>
or using the slower L</combine> and L</string> methods:
my $csv = Text::CSV_XS->new;
open my $csv_fh, ">", "hello.csv" or die "hello.csv: $!";
my @sample_input_fields = (
'You said, "Hello!"', 5.67,
'"Surely"', '', '3.14159');
if ($csv->combine (@sample_input_fields)) {
print $csv_fh $csv->string, "\n";
}
else {
print "combine () failed on argument: ",
$csv->error_input, "\n";
}
close $csv_fh or die "hello.csv: $!";
=head3 Generating CSV into memory
Format a data-set (C<@foo>) into a scalar value in memory (C<$data>):
# The data
my @foo = map { [ 0 .. 5 ] } 0 .. 3;
# in a loop
my $csv = Text::CSV_XS->new ({ binary => 1, auto_diag => 1, eol => "\r\n" });
open my $fh, ">", \my $data;
$csv->print ($fh, $_) for @foo;
close $fh;
# a single call
csv (in => \@foo, out => \my $data);
=head2 Rewriting CSV
Rewrite C<CSV> files with C<;> as separator character to well-formed C<CSV>:
use Text::CSV_XS qw( csv );
csv (in => csv (in => "bad.csv", sep_char => ";"), out => *STDOUT);
As C<STDOUT> is now default in L</csv>, a one-liner converting a UTF-16 CSV
file with BOM and TAB-separation to valid UTF-8 CSV could be:
$ perl -C3 -MText::CSV_XS=csv -we\
'csv(in=>"utf16tab.csv",encoding=>"utf16",sep=>"\t")' >utf8.csv
=head2 Dumping database tables to CSV
Dumping a database table can be simple as this (TIMTOWTDI):
my $dbh = DBI->connect (...);
my $sql = "select * from foo";
# using your own loop
open my $fh, ">", "foo.csv" or die "foo.csv: $!\n";
my $csv = Text::CSV_XS->new ({ binary => 1, eol => "\r\n" });
my $sth = $dbh->prepare ($sql); $sth->execute;
$csv->print ($fh, $sth->{NAME_lc});
while (my $row = $sth->fetch) {
$csv->print ($fh, $row);
}
# using the csv function, all in memory
csv (out => "foo.csv", in => $dbh->selectall_arrayref ($sql));
# using the csv function, streaming with callbacks
my $sth = $dbh->prepare ($sql); $sth->execute;
csv (out => "foo.csv", in => sub { $sth->fetch });
csv (out => "foo.csv", in => sub { $sth->fetchrow_hashref });
Note that this does not discriminate between "empty" values and NULL-values
from the database, as both will be the same empty field in CSV. To enable
distinction between the two, use L<C<quote_empty>|/quote_empty>.
csv (out => "foo.csv", in => sub { $sth->fetch }, quote_empty => 1);
If the database import utility supports special sequences to insert C<NULL>
values into the database, like MySQL/MariaDB supports C<\N>, use a filter
or a map
csv (out => "foo.csv", in => sub { $sth->fetch },
on_in => sub { $_ //= "\\N" for @{$_[1]} });
while (my $row = $sth->fetch) {
$csv->print ($fh, [ map { $_ // "\\N" } @$row ]);
}
these special sequences are not recognized by Text::CSV_XS on parsing the
CSV generated like this, but map and filter are your friends again
while (my $row = $csv->getline ($fh)) {
$sth->execute (map { $_ eq "\\N" ? undef : $_ } @$row);
}
csv (in => "foo.csv", filter => { 1 => sub {
$sth->execute (map { $_ eq "\\N" ? undef : $_ } @{$_[1]}); 0; }});
=head2 The examples folder
For more extended examples, see the F<examples/> C<1>. sub-directory in the
original distribution or the git repository C<2>.
1. https://github.com/Tux/Text-CSV_XS/tree/master/examples
2. https://github.com/Tux/Text-CSV_XS
The following files can be found there:
=over 2
=item parser-xs.pl
X<parser-xs.pl>
This can be used as a boilerplate to parse invalid C<CSV> and parse beyond
(expected) errors alternative to using the L</error> callback.
$ perl examples/parser-xs.pl bad.csv >good.csv
=item csv-check
X<csv-check>
This is a command-line tool that uses parser-xs.pl techniques to check the
C<CSV> file and report on its content.
$ csv-check files/utf8.csv
Checked files/utf8.csv with csv-check 1.9
using Text::CSV_XS 1.32 with perl 5.26.0 and Unicode 9.0.0
OK: rows: 1, columns: 2
sep = <,>, quo = <">, bin = <1>, eol = <"\n">
=item csv2xls
X<csv2xls>
A script to convert C<CSV> to Microsoft Excel (C<XLS>). This requires extra
modules L<Date::Calc> and L<Spreadsheet::WriteExcel>. The converter accepts
various options and can produce UTF-8 compliant Excel files.
=item csv2xlsx
X<csv2xlsx>
A script to convert C<CSV> to Microsoft Excel (C<XLSX>). This requires the
modules L<Date::Calc> and L<Spreadsheet::Writer::XLSX>. The converter does
accept various options including merging several C<CSV> files into a single
Excel file.
=item csvdiff
X<csvdiff>
A script that provides colorized diff on sorted CSV files, assuming first
line is header and first field is the key. Output options include colorized
ANSI escape codes or HTML.
$ csvdiff --html --output=diff.html file1.csv file2.csv
=item rewrite.pl
X<rewrite.pl>
A script to rewrite (in)valid CSV into valid CSV files. Script has options
to generate confusing CSV files or CSV files that conform to Dutch MS-Excel
exports (using C<;> as separation).
Script - by default - honors BOM and auto-detects separation converting it
to default standard CSV with C<,> as separator.
=back
=head1 CAVEATS
Text::CSV_XS is I<not> designed to detect the characters used to quote and
separate fields. The parsing is done using predefined (default) settings.
In the examples sub-directory, you can find scripts that demonstrate how
you could try to detect these characters yourself.
=head2 Microsoft Excel
The import/export from Microsoft Excel is a I<risky task>, according to the
documentation in C<Text::CSV::Separator>. Microsoft uses the system's list
separator defined in the regional settings, which happens to be a semicolon
for Dutch, German and Spanish (and probably some others as well). For the
English locale, the default is a comma. In Windows however, the user is
free to choose a predefined locale, and then change I<every> individual
setting in it, so checking the locale is no solution.
As of version 1.17, a lone first line with just
sep=;
will be recognized and honored when parsing with L</getline>.
=head1 TODO
=over 2
=item More Errors & Warnings
New extensions ought to be clear and concise in reporting what error has
occurred where and why, and maybe also offer a remedy to the problem.
L</error_diag> is a (very) good start, but there is more work to be done in
this area.
Basic calls should croak or warn on illegal parameters. Errors should be
documented.
=item setting meta info
Future extensions might include extending the L</meta_info>, L</is_quoted>,
and L</is_binary> to accept setting these flags for fields, so you can
specify which fields are quoted in the L</combine>/L</string> combination.
$csv->meta_info (0, 1, 1, 3, 0, 0);
$csv->is_quoted (3, 1);
L<Metadata Vocabulary for Tabular Data|http://w3c.github.io/csvw/metadata/>
(a W3C editor's draft) could be an example for supporting more metadata.
=item Parse the whole file at once
Implement new methods or functions that enable parsing of a complete file
at once, returning a list of hashes. Possible extension to this could be to
enable a column selection on the call:
my @AoH = $csv->parse_file ($filename, { cols => [ 1, 4..8, 12 ]});
Returning something like
[ { fields => [ 1, 2, "foo", 4.5, undef, "", 8 ],
flags => [ ... ],
},
{ fields => [ ... ],
.
},
]
Note that the L</csv> function already supports most of this, but does not
return flags. L</getline_all> returns all rows for an open stream, but this
will not return flags either. L</fragment> can reduce the required rows
I<or> columns, but cannot combine them.
=item Cookbook
Write a document that has recipes for most known non-standard (and maybe
some standard) C<CSV> formats, including formats that use C<TAB>, C<;>,
C<|>, or other non-comma separators.
Examples could be taken from W3C's L<CSV on the Web: Use Cases and
Requirements|http://w3c.github.io/csvw/use-cases-and-requirements/index.html>
=item Steal
Steal good new ideas and features from L<PapaParse|http://papaparse.com> or
L<csvkit|http://csvkit.readthedocs.org>.
=item Perl6 support
I'm already working on perl6 support L<here|https://github.com/Tux/CSV>. No
promises yet on when it is finished (or fast). Trying to keep the API alike
as much as possible.
=back
=head2 NOT TODO
=over 2
=item combined methods
Requests for adding means (methods) that combine L</combine> and L</string>
in a single call will B<not> be honored (use L</print> instead). Likewise
for L</parse> and L</fields> (use L</getline> instead), given the problems
with embedded newlines.
=back
=head2 Release plan
No guarantees, but this is what I had in mind some time ago:
=over 2
=item *
DIAGNOSTICS section in pod to *describe* the errors (see below)
=back
=head1 EBCDIC
The current hard-coding of characters and character ranges makes this code
unusable on C<EBCDIC> systems. Recent work in perl-5.20 might change that.
Opening C<EBCDIC> encoded files on C<ASCII>+ systems is likely to succeed
using Encode's C<cp37>, C<cp1047>, or C<posix-bc>:
open my $fh, "<:encoding(cp1047)", "ebcdic_file.csv" or die "...";
=head1 DIAGNOSTICS
Still under construction ...
If an error occurs, C<< $csv->error_diag >> can be used to get information
on the cause of the failure. Note that for speed reasons the internal value
is never cleared on success, so using the value returned by L</error_diag>
in normal cases - when no error occurred - may cause unexpected results.
If the constructor failed, the cause can be found using L</error_diag> as a
class method, like C<< Text::CSV_XS->error_diag >>.
The C<< $csv->error_diag >> method is automatically invoked upon error when
the contractor was called with L<C<auto_diag>|/auto_diag> set to C<1> or
C<2>, or when L<autodie> is in effect. When set to C<1>, this will cause a
C<warn> with the error message, when set to C<2>, it will C<die>. C<2012 -
EOF> is excluded from L<C<auto_diag>|/auto_diag> reports.
Errors can be (individually) caught using the L</error> callback.
The errors as described below are available. I have tried to make the error
itself explanatory enough, but more descriptions will be added. For most of
these errors, the first three capitals describe the error category:
=over 2
=item *
INI
Initialization error or option conflict.
=item *
ECR
Carriage-Return related parse error.
=item *
EOF
End-Of-File related parse error.
=item *
EIQ
Parse error inside quotation.
=item *
EIF
Parse error inside field.
=item *
ECB
Combine error.
=item *
EHR
HashRef parse related error.
=back
And below should be the complete list of error codes that can be returned:
=over 2
=item *
1001 "INI - sep_char is equal to quote_char or escape_char"
X<1001>
The L<separation character|/sep_char> cannot be equal to L<the quotation
character|/quote_char> or to L<the escape character|/escape_char>, as this
would invalidate all parsing rules.
=item *
1002 "INI - allow_whitespace with escape_char or quote_char SP or TAB"
X<1002>
Using the L<C<allow_whitespace>|/allow_whitespace> attribute when either
L<C<quote_char>|/quote_char> or L<C<escape_char>|/escape_char> is equal to
C<SPACE> or C<TAB> is too ambiguous to allow.
=item *
1003 "INI - \r or \n in main attr not allowed"
X<1003>
Using default L<C<eol>|/eol> characters in either L<C<sep_char>|/sep_char>,
L<C<quote_char>|/quote_char>, or L<C<escape_char>|/escape_char> is not
allowed.
=item *
1004 "INI - callbacks should be undef or a hashref"
X<1004>
The L<C<callbacks>|/Callbacks> attribute only allows one to be C<undef> or
a hash reference.
=item *
1005 "INI - EOL too long"
X<1005>
The value passed for EOL is exceeding its maximum length (16).
=item *
1006 "INI - SEP too long"
X<1006>
The value passed for SEP is exceeding its maximum length (16).
=item *
1007 "INI - QUOTE too long"
X<1007>
The value passed for QUOTE is exceeding its maximum length (16).
=item *
1008 "INI - SEP undefined"
X<1008>
The value passed for SEP should be defined and not empty.
=item *
1010 "INI - the header is empty"
X<1010>
The header line parsed in the L</header> is empty.
=item *
1011 "INI - the header contains more than one valid separator"
X<1011>
The header line parsed in the L</header> contains more than one (unique)
separator character out of the allowed set of separators.
=item *
1012 "INI - the header contains an empty field"
X<1012>
The header line parsed in the L</header> is contains an empty field.
=item *
1013 "INI - the header contains nun-unique fields"
X<1013>
The header line parsed in the L</header> contains at least two identical
fields.
=item *
1014 "INI - header called on undefined stream"
X<1014>
The header line cannot be parsed from an undefined sources.
=item *
1500 "PRM - Invalid/unsupported argument(s)"
X<1500>
Function or method called with invalid argument(s) or parameter(s).
=item *
1501 "PRM - The key attribute is passed as an unsupported type"
X<1501>
The C<key> attribute is of an unsupported type.
=item *
2010 "ECR - QUO char inside quotes followed by CR not part of EOL"
X<2010>
When L<C<eol>|/eol> has been set to anything but the default, like
C<"\r\t\n">, and the C<"\r"> is following the B<second> (closing)
L<C<quote_char>|/quote_char>, where the characters following the C<"\r"> do
not make up the L<C<eol>|/eol> sequence, this is an error.
=item *
2011 "ECR - Characters after end of quoted field"
X<2011>
Sequences like C<1,foo,"bar"baz,22,1> are not allowed. C<"bar"> is a quoted
field and after the closing double-quote, there should be either a new-line
sequence or a separation character.
=item *
2012 "EOF - End of data in parsing input stream"
X<2012>
Self-explaining. End-of-file while inside parsing a stream. Can happen only
when reading from streams with L</getline>, as using L</parse> is done on
strings that are not required to have a trailing L<C<eol>|/eol>.
=item *
2013 "INI - Specification error for fragments RFC7111"
X<2013>
Invalid specification for URI L</fragment> specification.
=item *
2014 "ENF - Inconsistent number of fields"
X<2014>
Inconsistent number of fields under strict parsing.
=item *
2021 "EIQ - NL char inside quotes, binary off"
X<2021>
Sequences like C<1,"foo\nbar",22,1> are allowed only when the binary option
has been selected with the constructor.
=item *
2022 "EIQ - CR char inside quotes, binary off"
X<2022>
Sequences like C<1,"foo\rbar",22,1> are allowed only when the binary option
has been selected with the constructor.
=item *
2023 "EIQ - QUO character not allowed"
X<2023>
Sequences like C<"foo "bar" baz",qu> and C<2023,",2008-04-05,"Foo, Bar",\n>
will cause this error.
=item *
2024 "EIQ - EOF cannot be escaped, not even inside quotes"
X<2024>
The escape character is not allowed as last character in an input stream.
=item *
2025 "EIQ - Loose unescaped escape"
X<2025>
An escape character should escape only characters that need escaping.
Allowing the escape for other characters is possible with the attribute
L</allow_loose_escape>.
=item *
2026 "EIQ - Binary character inside quoted field, binary off"
X<2026>
Binary characters are not allowed by default. Exceptions are fields that
contain valid UTF-8, that will automatically be upgraded if the content is
valid UTF-8. Set L<C<binary>|/binary> to C<1> to accept binary data.
=item *
2027 "EIQ - Quoted field not terminated"
X<2027>
When parsing a field that started with a quotation character, the field is
expected to be closed with a quotation character. When the parsed line is
exhausted before the quote is found, that field is not terminated.
=item *
2030 "EIF - NL char inside unquoted verbatim, binary off"
X<2030>
=item *
2031 "EIF - CR char is first char of field, not part of EOL"
X<2031>
=item *
2032 "EIF - CR char inside unquoted, not part of EOL"
X<2032>
=item *
2034 "EIF - Loose unescaped quote"
X<2034>
=item *
2035 "EIF - Escaped EOF in unquoted field"
X<2035>
=item *
2036 "EIF - ESC error"
X<2036>
=item *
2037 "EIF - Binary character in unquoted field, binary off"
X<2037>
=item *
2110 "ECB - Binary character in Combine, binary off"
X<2110>
=item *
2200 "EIO - print to IO failed. See errno"
X<2200>
=item *
3001 "EHR - Unsupported syntax for column_names ()"
X<3001>
=item *
3002 "EHR - getline_hr () called before column_names ()"
X<3002>
=item *
3003 "EHR - bind_columns () and column_names () fields count mismatch"
X<3003>
=item *
3004 "EHR - bind_columns () only accepts refs to scalars"
X<3004>
=item *
3006 "EHR - bind_columns () did not pass enough refs for parsed fields"
X<3006>
=item *
3007 "EHR - bind_columns needs refs to writable scalars"
X<3007>
=item *
3008 "EHR - unexpected error in bound fields"
X<3008>
=item *
3009 "EHR - print_hr () called before column_names ()"
X<3009>
=item *
3010 "EHR - print_hr () called with invalid arguments"
X<3010>
=back
=head1 SEE ALSO
L<IO::File>, L<IO::Handle>, L<IO::Wrap>, L<Text::CSV>, L<Text::CSV_PP>,
L<Text::CSV::Encoded>, L<Text::CSV::Separator>, L<Text::CSV::Slurp>,
L<Spreadsheet::CSV> and L<Spreadsheet::Read>, and of course L<perl>.
If you are using perl6, you can have a look at C<Text::CSV> in the perl6
ecosystem, offering the same features.
=head3 non-perl
A CSV parser in JavaScript, also used by L<W3C|http://www.w3.org>, is the
multi-threaded in-browser L<PapaParse|http://papaparse.com/>.
L<csvkit|http://csvkit.readthedocs.org> is a python CSV parsing toolkit.
=head1 AUTHOR
Alan Citterman F<E<lt>alan@mfgrtl.comE<gt>> wrote the original Perl module.
Please don't send mail concerning Text::CSV_XS to Alan, who is not involved
in the C/XS part that is now the main part of the module.
Jochen Wiedmann F<E<lt>joe@ispsoft.deE<gt>> rewrote the en- and decoding in
C by implementing a simple finite-state machine. He added variable quote,
escape and separator characters, the binary mode and the print and getline
methods. See F<ChangeLog> releases 0.10 through 0.23.
H.Merijn Brand F<E<lt>h.m.brand@xs4all.nlE<gt>> cleaned up the code, added
the field flags methods, wrote the major part of the test suite, completed
the documentation, fixed most RT bugs, added all the allow flags and the
L</csv> function. See ChangeLog releases 0.25 and on.
=head1 COPYRIGHT AND LICENSE
Copyright (C) 2007-2017 H.Merijn Brand. All rights reserved.
Copyright (C) 1998-2001 Jochen Wiedmann. All rights reserved.
Copyright (C) 1997 Alan Citterman. All rights reserved.
This library is free software; you can redistribute and/or modify it under
the same terms as Perl itself.
=cut
=for elvis
:ex:se gw=75|color guide #ff0000:
=cut
|