summaryrefslogtreecommitdiff
path: root/gnu/dist/include/opcode/sparc.h
diff options
context:
space:
mode:
authortv <tv@NetBSD.org>1999-02-02 19:51:16 +0000
committertv <tv@NetBSD.org>1999-02-02 19:51:16 +0000
commit2e8b57510c512922b01977bf9c07cb986ddbaa67 (patch)
tree99f0ff2ba55134ad127492d887b5b6567773ef25 /gnu/dist/include/opcode/sparc.h
parent269cb58003ce63bbb1763517287a25b909583ae4 (diff)
By popular demand, import binutils 2.9.1.
Diffstat (limited to 'gnu/dist/include/opcode/sparc.h')
-rw-r--r--gnu/dist/include/opcode/sparc.h4
1 files changed, 3 insertions, 1 deletions
diff --git a/gnu/dist/include/opcode/sparc.h b/gnu/dist/include/opcode/sparc.h
index 79ca7586e84..4f159bd896f 100644
--- a/gnu/dist/include/opcode/sparc.h
+++ b/gnu/dist/include/opcode/sparc.h
@@ -183,6 +183,8 @@ Kinds of operands:
* Prefetch function constant. (v9)
x OPF field (v9 impdep).
0 32/64 bit immediate for set or setx (v9) insns
+ _ Ancillary state register in rd (v9a)
+ / Ancillary state register in rs1 (v9a)
The following chars are unused: (note: ,[] are used as punctuation)
[345]
@@ -216,7 +218,7 @@ The following chars are unused: (note: ,[] are used as punctuation)
#define RS1_G0 RS1(~0)
#define RS2_G0 RS2(~0)
-extern struct sparc_opcode sparc_opcodes[];
+extern const struct sparc_opcode sparc_opcodes[];
extern const int sparc_num_opcodes;
extern int sparc_encode_asi PARAMS ((const char *));
a> 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 12302 12303 12304 12305 12306 12307 12308 12309 12310 12311 12312 12313 12314 12315 12316 12317 12318 12319 12320 12321 12322 12323 12324 12325 12326 12327 12328 12329 12330 12331 12332 12333 12334 12335 12336 12337 12338 12339 12340 12341 12342 12343 12344 12345 12346 12347 12348 12349 12350 12351 12352 12353 12354 12355 12356 12357 12358 12359 12360 12361 12362 12363 12364 12365 12366 12367 12368 12369 12370 12371 12372 12373 12374 12375 12376 12377 12378 12379 12380 12381 12382 12383 12384 12385 12386 12387 12388 12389 12390 12391 12392 12393 12394 12395 12396 12397 12398 12399 12400 12401 12402 12403 12404 12405 12406 12407 12408 12409 12410 12411 12412 12413 12414 12415 12416 12417 12418 12419 12420 12421 12422 12423 12424 12425 12426 12427 12428 12429 12430 12431 12432 12433 12434 12435 12436 12437 12438 12439 12440 12441 12442 12443 12444 12445 12446 12447 12448 12449 12450 12451 12452 12453 12454 12455 12456 12457 12458 12459 12460 12461 12462 12463 12464 12465 12466 12467 12468 12469 12470 12471 12472 12473 12474 12475 12476 12477 12478 12479 12480 12481 12482 12483 12484 12485 12486 12487 12488 12489 12490 12491 12492 12493 12494 12495 12496 12497 12498 12499 12500 12501 12502 12503 12504 12505 12506 12507 12508 12509 12510 12511 12512 12513 12514 12515 12516 12517 12518 12519 12520 12521 12522 12523 12524 12525 12526 12527 12528 12529 12530 12531 12532 12533 12534 12535 12536 12537 12538 12539 12540 12541 12542 12543 12544 12545 12546 12547 12548 12549 12550 12551 12552 12553 12554 12555 12556 12557 12558 12559 12560 12561 12562 12563 12564 12565 12566 12567 12568 12569 12570 12571 12572 12573 12574 12575 12576 12577 12578 12579 12580 12581 12582 12583 12584 12585 12586 12587 12588 12589 12590 12591 12592 12593 12594 12595 12596 12597 12598 12599 12600 12601 12602 12603 12604 12605 12606 12607 12608 12609 12610 12611 12612 12613 12614 12615 12616 12617 12618 12619 12620 12621 12622 12623 12624 12625 12626 12627 12628 12629 12630 12631 12632 12633 12634 12635 12636 12637 12638 12639 12640 12641 12642 12643 12644 12645 12646 12647 12648 12649 12650 12651 12652 12653 12654 12655 12656 12657 12658 12659 12660 12661 12662 12663 12664 12665 12666 12667 12668 12669 12670 12671 12672 12673 12674 12675 12676 12677 12678 12679 12680 12681 12682 12683 12684 12685 12686 12687 12688 12689 12690 12691 12692 12693 12694 12695 12696 12697 12698 12699 12700 12701 12702 12703 12704 12705 12706 12707 12708 12709 12710 12711 12712 12713 12714 12715 12716 12717 12718 12719 12720 12721 12722 12723 12724 12725 12726 12727 12728 12729 12730 12731 12732 12733 12734 12735 12736 12737 12738 12739 12740 12741 12742 12743 12744 12745 12746 12747 12748 12749 12750 12751 12752 12753 12754 12755 12756 12757 12758 12759 12760 12761 12762 12763 12764 12765 12766 12767 12768 12769 12770 12771 12772 12773 12774 12775 12776 12777 12778 12779 12780 12781 12782 12783 12784 12785 12786 12787 12788 12789 12790 12791 12792 12793 12794 12795 12796 12797 12798 12799 12800 12801 12802 12803 12804 12805 12806 12807 12808 12809 12810 12811 12812 12813 12814 12815 12816 12817 12818 12819 12820 12821 12822 12823 12824 12825 12826 12827 12828 12829 12830 12831 12832 12833 12834 12835 12836 12837 12838 12839 12840 12841 12842 12843 12844 12845 12846 12847 12848 12849 12850 12851 12852 12853 12854 12855 12856 12857 12858 12859 12860 12861 12862 12863 12864 12865 12866 12867 12868 12869 12870 12871 12872 12873 12874 12875 12876 12877 12878 12879 12880 12881 12882 12883 12884 12885 12886 12887 12888 12889 12890 12891 12892 12893 12894 12895 12896 12897 12898 12899 12900 12901 12902 12903 12904 12905 12906 12907 12908 12909 12910 12911 12912 12913 12914 12915 12916 12917 12918 12919 12920 12921 12922 12923 12924 12925 12926 12927 12928 12929 12930 12931 12932 12933 12934 12935 12936 12937 12938 12939 12940 12941 12942 12943 12944 12945 12946 12947 12948 12949 12950 12951 12952 12953 12954 12955 12956 12957 12958 12959 12960 12961 12962 12963 12964 12965 12966 12967 12968 12969 12970 12971 12972 12973 12974 12975 12976 12977 12978 12979 12980 12981 12982 12983 12984 12985 12986 12987 12988 12989 12990 12991 12992 12993 12994 12995 12996 12997 12998 12999 13000 13001 13002 13003 13004 13005 13006 13007 13008 13009 13010 13011 13012 13013 13014 13015 13016 13017 13018 13019 13020 13021 13022 13023 13024 13025 13026 13027 13028 13029 13030 13031 13032 13033 13034 13035 13036 13037 13038 13039 13040 13041 13042 13043 13044 13045 13046 13047 13048 13049 13050 13051 13052 13053 13054 13055 13056 13057 13058 13059 13060 13061 13062 13063 13064 13065 13066 13067 13068 13069 13070 13071 13072 13073 13074 13075 13076 13077 13078 13079 13080 13081 13082 13083 13084 13085 13086 13087 13088 13089 13090 13091 13092 13093 13094 13095 13096 13097 13098 13099 13100 13101 13102 13103 13104 13105 13106 13107 13108 13109 13110 13111 13112 13113 13114 13115 13116 13117 13118 13119 13120 13121 13122 13123 13124 13125 13126 13127 13128 13129 13130 13131 13132 13133 13134 13135 13136 13137 13138 13139 13140 13141 13142 13143 13144 13145 13146 13147 13148 13149 13150 13151 13152 13153 13154 13155 13156 13157 13158 13159 13160 13161 13162 13163 13164 13165 13166 13167 13168 13169 13170 13171 13172 13173 13174 13175 13176 13177 13178 13179 13180 13181 13182 13183 13184 13185 13186 13187 13188 13189 13190 13191 13192 13193 13194 13195 13196 13197 13198 13199 13200 13201 13202 13203 13204 13205 13206 13207 13208 13209 13210 13211 13212 13213 13214 13215 13216 13217 13218 13219 13220 13221 13222 13223 13224 13225 13226 13227 13228 13229 13230 13231 13232 13233 13234 13235 13236 13237 13238 13239 13240 13241 13242 13243 13244 13245 13246 13247 13248 13249 13250 13251 13252 13253 13254 13255 13256 13257 13258 13259 13260 13261 13262 13263 13264 13265 13266 13267 13268 13269 13270 13271 13272 13273 13274 13275 13276 13277 13278 13279 13280 13281 13282 13283 13284 13285 13286 13287 13288 13289 13290 13291 13292 13293 13294 13295 13296 13297 13298 13299 13300 13301 13302 13303 13304 13305 13306 13307 13308 13309 13310 13311 13312 13313 13314 13315 13316 13317 13318 13319 13320 13321 13322 13323 13324 13325 13326 13327 13328 13329 13330 13331 13332 13333 13334 13335 13336 13337 13338 13339 13340 13341 13342 13343 13344 13345 13346 13347 13348 13349 13350 13351 13352 13353 13354 13355 13356 13357 13358 13359 13360 13361 13362 13363 13364 13365 13366 13367 13368 13369 13370 13371 13372 13373 13374 13375 13376 13377 13378 13379 13380 13381 13382 13383 13384 13385 13386 13387 13388 13389 13390 13391 13392 13393 13394 13395 13396 13397 13398 13399 13400 13401 13402 13403 13404 13405 13406 13407 13408 13409 13410 13411 13412 13413 13414 13415 13416 13417 13418 13419 13420 13421 13422 13423 13424 13425 13426 13427 13428 13429 13430 13431 13432 13433 13434 13435 13436 13437 13438 13439 13440 13441 13442 13443 13444 13445 13446 13447 13448 13449 13450 13451 13452 13453 13454 13455 13456 13457 13458 13459 13460 13461 13462 13463 13464 13465 13466 13467 13468 13469 13470 13471 13472 13473 13474 13475 13476 13477 13478 13479 13480 13481 13482 13483 13484 13485 13486 13487 13488 13489 13490 13491 13492 13493 13494 13495 13496 13497 13498 13499 13500 13501 13502 13503 13504 13505 13506 13507 13508 13509 13510 13511 13512 13513 13514 13515 13516 13517 13518 13519 13520 13521 13522 13523 13524 13525 13526 13527 13528 13529 13530 13531 13532 13533 13534 13535 13536 13537 13538 13539 13540 13541 13542 13543 13544 13545 13546 13547 13548 13549 13550 13551 13552 13553 13554 13555 13556 13557 13558 13559 13560 13561 13562 13563 13564 13565 13566 13567 13568 13569 13570 13571 13572 13573 13574 13575 13576 13577 13578 13579 13580 13581 13582 13583 13584 13585 13586 13587 13588 13589 13590 13591 13592 13593 13594 13595 13596 13597 13598 13599 13600 13601 13602 13603 13604 13605 13606 13607 13608 13609 13610 13611 13612 13613 13614 13615 13616 13617 13618 13619 13620 13621 13622 13623 13624 13625 13626 13627 13628 13629 13630 13631 13632 13633 13634 13635 13636 13637 13638 13639 13640 13641 13642 13643 13644 13645 13646 13647 13648 13649 13650 13651 13652 13653 13654 13655 13656 13657 13658 13659 13660 13661 13662 13663 13664 13665 13666 13667 13668 13669 13670 13671 13672 13673 13674 13675 13676 13677 13678 13679 13680 13681 13682 13683 13684 13685 13686 13687 13688 13689 13690 13691 13692 13693 13694 13695 13696 13697 13698 13699 13700 13701 13702 13703 13704 13705 13706 13707 13708 13709 13710 13711 13712 13713 13714 13715 13716 13717 13718 13719 13720 13721 13722 13723 13724 13725 13726 13727 13728 13729 13730 13731 13732 13733 13734 13735 13736 13737 13738 13739 13740 13741 13742 13743 13744 13745 13746 13747 13748 13749 13750 13751 13752 13753 13754 13755 13756 13757 13758 13759 13760 13761 13762 13763 13764 13765 13766 13767 13768 13769 13770 13771 13772 13773 13774 13775 13776 13777 13778 13779 13780 13781 13782 13783 13784 13785 13786 13787 13788 13789 13790 13791 13792 13793 13794 13795 13796 13797 13798 13799 13800 13801 13802 13803 13804 13805 13806 13807 13808 13809 13810 13811 13812 13813 13814 13815 13816 13817 13818 13819 13820 13821 13822 13823 13824 13825 13826 13827 13828 13829 13830 13831 13832 13833 13834 13835 13836 13837 13838 13839 13840 13841 13842 13843 13844 13845 13846 13847 13848 13849 13850 13851 13852 13853 13854 13855 13856 13857 13858 13859 13860 13861 13862 13863 13864 13865 13866 13867 13868 13869 13870 13871 13872 13873 13874 13875 13876 13877 13878 13879 13880 13881 13882 13883 13884 13885 13886 13887 13888 13889 13890 13891 13892 13893 13894 13895 13896 13897 13898 13899 13900 13901 13902 13903 13904 13905 13906 13907 13908 13909 13910 13911 13912 13913 13914 13915 13916 13917 13918 13919 13920 13921 13922 13923 13924 13925 13926 13927 13928 13929 13930 13931 13932 13933 13934 13935 13936 13937 13938 13939 13940 13941 13942 13943 13944 13945 13946 13947 13948 13949 13950 13951 13952 13953 13954 13955 13956 13957 13958 13959 13960 13961 13962 13963 13964 13965 13966 13967 13968 13969 13970 13971 13972 13973 13974 13975 13976 13977 13978 13979 13980 13981 13982 13983 13984 13985 13986 13987 13988 13989 13990 13991 13992 13993 13994 13995 13996 13997 13998 13999 14000 14001 14002 14003 14004 14005 14006 14007 14008 14009 14010 14011 14012 14013 14014 14015 14016 14017 14018 14019 14020 14021 14022 14023 14024 14025 14026 14027 14028 14029 14030 14031 14032 14033 14034 14035 14036 14037 14038 14039 14040 14041 14042 14043 14044 14045 14046 14047 14048 14049 14050 14051 14052 14053 14054 14055 14056 14057 14058 14059 14060 14061 14062 14063 14064 14065 14066 14067 14068 14069 14070 14071 14072 14073 14074 14075 14076 14077 14078 14079 14080 14081 14082 14083 14084 14085 14086 14087 14088 14089 14090 14091 14092 14093 14094 14095 14096 14097 14098 14099 14100 14101 14102 14103 14104 14105 14106 14107 14108 14109 14110 14111 14112 14113 14114 14115 14116 14117 14118 14119 14120 14121 14122 14123 14124 14125 14126 14127 14128 14129 14130 14131 14132 14133 14134 14135 14136 14137 14138 14139 14140 14141 14142 14143 14144 14145 14146 14147 14148 14149 14150 14151 14152 14153 14154 14155 14156 14157 14158 14159 14160 14161 14162 14163 14164 14165 14166 14167 14168 14169 14170 14171 14172 14173 14174 14175 14176 14177 14178 14179 14180 14181 14182 14183 14184 14185 14186 14187 14188 14189 14190 14191 14192 14193 14194 14195 14196 14197 14198 14199 14200 14201 14202 14203 14204 14205 14206 14207 14208 14209 14210 14211 14212 14213 14214 14215 14216 14217 14218 14219 14220 14221 14222 14223 14224 14225 14226 14227 14228 14229 14230 14231 14232 14233 14234 14235 14236 14237 14238 14239 14240 14241 14242 14243 14244 14245 14246 14247 14248 14249 14250 14251 14252 14253 14254 14255 14256 14257 14258 14259 14260 14261 14262 14263 14264 14265 14266 14267 14268 14269 14270 14271 14272 14273 14274 14275 14276 14277 14278 14279 14280 14281 14282 14283 14284 14285 14286 14287 14288 14289 14290 14291 14292 14293 14294 14295 14296 14297 14298 14299 14300 14301 14302 14303 14304 14305 14306 14307 14308 14309 14310 14311 14312 14313 14314 14315 14316 14317 14318 14319 14320 14321 14322 14323 14324 14325 14326 14327 14328 14329 14330 14331 14332 14333 14334 14335 14336 14337 14338 14339 14340 14341 14342 14343 14344 14345 14346 14347 14348 14349 14350 14351 14352 14353 14354 14355 14356 14357 14358 14359 14360 14361 14362 14363 14364 14365 14366 14367 14368 14369 14370 14371 14372 14373 14374 14375 14376 14377 14378 14379 14380 14381 14382 14383 14384 14385 14386 14387 14388 14389 14390 14391 14392 14393 14394 14395 14396 14397 14398 14399 14400 14401 14402 14403 14404 14405 14406 14407 14408 14409 14410 14411 14412 14413 14414 14415 14416 14417 14418 14419 14420 14421 14422 14423 14424 14425 14426 14427 14428 14429 14430 14431 14432 14433 14434 14435 14436 14437 14438 14439 14440 14441 14442 14443 14444 14445 14446 14447 14448 14449 14450 14451 14452 14453 14454 14455 14456 14457 14458 14459 14460 14461 14462 14463 14464 14465 14466 14467 14468 14469 14470 14471 14472 14473 14474 14475 14476 14477 14478 14479 14480 14481 14482 14483 14484 14485 14486 14487 14488 14489 14490 14491 14492 14493 14494 14495 14496 14497 14498 14499 14500 14501 14502 14503 14504 14505 14506 14507 14508 14509 14510 14511 14512 14513 14514 14515 14516 14517 14518 14519 14520 14521 14522 14523 14524 14525 14526 14527 14528 14529 14530 14531 14532 14533 14534 14535 14536 14537 14538 14539 14540 14541 14542 14543 14544 14545 14546 14547 14548 14549 14550 14551 14552 14553 14554 14555 14556 14557 14558 14559 14560 14561 14562 14563 14564 14565 14566 14567 14568 14569 14570 14571 14572 14573 14574 14575 14576 14577 14578 14579 14580 14581 14582 14583 14584 14585 14586 14587 14588 14589 14590 14591 14592 14593 14594 14595 14596 14597 14598 14599 14600 14601 14602 14603 14604 14605 14606 14607 14608 14609 14610 14611 14612 14613 14614 14615 14616 14617 14618 14619 14620 14621 14622 14623 14624 14625 14626 14627 14628 14629 14630 14631 14632 14633 14634 14635 14636 14637 14638 14639 14640 14641 14642 14643 14644 14645 14646 14647 14648 14649 14650 14651 14652 14653 14654 14655 14656 14657 14658 14659 14660 14661 14662 14663 14664 14665 14666 14667 14668 14669 14670 14671 14672 14673 14674 14675 14676 14677 14678 14679 14680 14681 14682 14683 14684 14685 14686 14687 14688 14689 14690 14691 14692 14693 14694 14695 14696 14697 14698 14699 14700 14701 14702 14703 14704 14705 14706 14707 14708 14709 14710 14711 14712 14713 14714 14715 14716 14717 14718 14719 14720 14721 14722 14723 14724 14725 14726 14727 14728 14729 14730 14731 14732 14733 14734 14735 14736 14737 14738 14739 14740 14741 14742 14743 14744 14745 14746 14747 14748 14749 14750 14751 14752 14753 14754 14755 14756 14757 14758 14759 14760 14761 14762 14763 14764 14765 14766 14767 14768 14769 14770 14771 14772 14773 14774 14775 14776 14777 14778 14779 14780 14781 14782 14783 14784 14785 14786 14787 14788 14789 14790 14791 14792 14793 14794 14795 14796 14797 14798 14799 14800 14801 14802 14803 14804 14805 14806 14807 14808 14809 14810 14811 14812 14813 14814 14815 14816 14817 14818 14819 14820 14821 14822 14823 14824 14825 14826 14827 14828 14829 14830 14831 14832 14833 14834 14835 14836 14837 14838 14839 14840 14841 14842 14843 14844 14845 14846 14847 14848 14849 14850 14851 14852 14853 14854 14855 14856 14857 14858 14859 14860 14861 14862 14863 14864 14865 14866 14867 14868 14869 14870 14871 14872 14873 14874 14875 14876 14877 14878 14879 14880 14881 14882 14883 14884
This is gettext.info, produced by makeinfo version 4.8 from
gettext.texi.

INFO-DIR-SECTION GNU Gettext Utilities
START-INFO-DIR-ENTRY
* gettext: (gettext).                          GNU gettext utilities.
* autopoint: (gettext)autopoint Invocation.    Copy gettext infrastructure.
* envsubst: (gettext)envsubst Invocation.      Expand environment variables.
* gettextize: (gettext)gettextize Invocation.  Prepare a package for gettext.
* msgattrib: (gettext)msgattrib Invocation.    Select part of a PO file.
* msgcat: (gettext)msgcat Invocation.          Combine several PO files.
* msgcmp: (gettext)msgcmp Invocation.          Compare a PO file and template.
* msgcomm: (gettext)msgcomm Invocation.        Match two PO files.
* msgconv: (gettext)msgconv Invocation.        Convert PO file to encoding.
* msgen: (gettext)msgen Invocation.            Create an English PO file.
* msgexec: (gettext)msgexec Invocation.        Process a PO file.
* msgfilter: (gettext)msgfilter Invocation.    Pipe a PO file through a filter.
* msgfmt: (gettext)msgfmt Invocation.          Make MO files out of PO files.
* msggrep: (gettext)msggrep Invocation.        Select part of a PO file.
* msginit: (gettext)msginit Invocation.        Create a fresh PO file.
* msgmerge: (gettext)msgmerge Invocation.      Update a PO file from template.
* msgunfmt: (gettext)msgunfmt Invocation.      Uncompile MO file into PO file.
* msguniq: (gettext)msguniq Invocation.        Unify duplicates for PO file.
* ngettext: (gettext)ngettext Invocation.      Translate a message with plural.
* xgettext: (gettext)xgettext Invocation.      Extract strings into a PO file.
* ISO639: (gettext)Language Codes.             ISO 639 language codes.
* ISO3166: (gettext)Country Codes.             ISO 3166 country codes.
END-INFO-DIR-ENTRY

   This file provides documentation for GNU `gettext' utilities.  It
also serves as a reference for the free Translation Project.

   Copyright (C) 1995-1998, 2001-2005 Free Software Foundation, Inc.

   Permission is granted to make and distribute verbatim copies of this
manual provided the copyright notice and this permission notice are
preserved on all copies.

   Permission is granted to copy and distribute modified versions of
this manual under the conditions for verbatim copying, provided that
the entire resulting derived work is distributed under the terms of a
permission notice identical to this one.

   Permission is granted to copy and distribute translations of this
manual into another language, under the above conditions for modified
versions, except that this permission notice may be stated in a
translation approved by the Foundation.


File: gettext.info,  Node: Top,  Next: Introduction,  Prev: (dir),  Up: (dir)

GNU `gettext' utilities
***********************

This manual documents the GNU gettext tools and the GNU libintl library,
version 0.14.4.

* Menu:

* Introduction::                Introduction
* Basics::                      PO Files and PO Mode Basics
* Sources::                     Preparing Program Sources
* Template::                    Making the PO Template File
* Creating::                    Creating a New PO File
* Updating::                    Updating Existing PO Files
* Manipulating::                Manipulating PO Files
* Binaries::                    Producing Binary MO Files
* Users::                       The User's View
* Programmers::                 The Programmer's View
* Translators::                 The Translator's View
* Maintainers::                 The Maintainer's View
* Programming Languages::       Other Programming Languages
* Conclusion::                  Concluding Remarks

* Language Codes::              ISO 639 language codes
* Country Codes::               ISO 3166 country codes

* Program Index::               Index of Programs
* Option Index::                Index of Command-Line Options
* Variable Index::              Index of Environment Variables
* PO Mode Index::               Index of Emacs PO Mode Commands
* Autoconf Macro Index::        Index of Autoconf Macros
* Index::                       General Index

 --- The Detailed Node Listing ---

Introduction

* Why::                         The Purpose of GNU `gettext'
* Concepts::                    I18n, L10n, and Such
* Aspects::                     Aspects in Native Language Support
* Files::                       Files Conveying Translations
* Overview::                    Overview of GNU `gettext'

PO Files and PO Mode Basics

* Installation::                Completing GNU `gettext' Installation
* PO Files::                    The Format of PO Files
* Main PO Commands::            Main Commands
* Entry Positioning::           Entry Positioning
* Normalizing::                 Normalizing Strings in Entries

Preparing Program Sources

* Triggering::                  Triggering `gettext' Operations
* Preparing Strings::           Preparing Translatable Strings
* Mark Keywords::               How Marks Appear in Sources
* Marking::                     Marking Translatable Strings
* c-format Flag::               Telling something about the following string
* Special cases::               Special Cases of Translatable Strings
* Names::                       Marking Proper Names for Translation
* Libraries::                   Preparing Library Sources

Making the PO Template File

* xgettext Invocation::         Invoking the `xgettext' Program

Creating a New PO File

* msginit Invocation::          Invoking the `msginit' Program
* Header Entry::                Filling in the Header Entry

Updating Existing PO Files

* msgmerge Invocation::         Invoking the `msgmerge' Program
* Translated Entries::          Translated Entries
* Fuzzy Entries::               Fuzzy Entries
* Untranslated Entries::        Untranslated Entries
* Obsolete Entries::            Obsolete Entries
* Modifying Translations::      Modifying Translations
* Modifying Comments::          Modifying Comments
* Subedit::                     Mode for Editing Translations
* C Sources Context::           C Sources Context
* Auxiliary::                   Consulting Auxiliary PO Files
* Compendium::                  Using Translation Compendia

Using Translation Compendia

* Creating Compendia::          Merging translations for later use
* Using Compendia::             Using older translations if they fit

Manipulating PO Files

* msgcat Invocation::           Invoking the `msgcat' Program
* msgconv Invocation::          Invoking the `msgconv' Program
* msggrep Invocation::          Invoking the `msggrep' Program
* msgfilter Invocation::        Invoking the `msgfilter' Program
* msguniq Invocation::          Invoking the `msguniq' Program
* msgcomm Invocation::          Invoking the `msgcomm' Program
* msgcmp Invocation::           Invoking the `msgcmp' Program
* msgattrib Invocation::        Invoking the `msgattrib' Program
* msgen Invocation::            Invoking the `msgen' Program
* msgexec Invocation::          Invoking the `msgexec' Program
* libgettextpo::                Writing your own programs that process PO files

Producing Binary MO Files

* msgfmt Invocation::           Invoking the `msgfmt' Program
* msgunfmt Invocation::         Invoking the `msgunfmt' Program
* MO Files::                    The Format of GNU MO Files

The User's View

* Matrix::                      The Current `ABOUT-NLS' Matrix
* Installers::                  Magic for Installers
* End Users::                   Magic for End Users

The Programmer's View

* catgets::                     About `catgets'
* gettext::                     About `gettext'
* Comparison::                  Comparing the two interfaces
* Using libintl.a::             Using libintl.a in own programs
* gettext grok::                Being a `gettext' grok
* Temp Programmers::            Temporary Notes for the Programmers Chapter

About `catgets'

* Interface to catgets::        The interface
* Problems with catgets::       Problems with the `catgets' interface?!

About `gettext'

* Interface to gettext::        The interface
* Ambiguities::                 Solving ambiguities
* Locating Catalogs::           Locating message catalog files
* Charset conversion::          How to request conversion to Unicode
* Plural forms::                Additional functions for handling plurals
* GUI program problems::        Another technique for solving ambiguities
* Optimized gettext::           Optimization of the *gettext functions

Temporary Notes for the Programmers Chapter

* Temp Implementations::        Temporary - Two Possible Implementations
* Temp catgets::                Temporary - About `catgets'
* Temp WSI::                    Temporary - Why a single implementation
* Temp Notes::                  Temporary - Notes

The Translator's View

* Trans Intro 0::               Introduction 0
* Trans Intro 1::               Introduction 1
* Discussions::                 Discussions
* Organization::                Organization
* Information Flow::            Information Flow
* Prioritizing messages::       How to find which messages to translate first

Organization

* Central Coordination::        Central Coordination
* National Teams::              National Teams
* Mailing Lists::               Mailing Lists

National Teams

* Sub-Cultures::                Sub-Cultures
* Organizational Ideas::        Organizational Ideas

The Maintainer's View

* Flat and Non-Flat::           Flat or Non-Flat Directory Structures
* Prerequisites::               Prerequisite Works
* gettextize Invocation::       Invoking the `gettextize' Program
* Adjusting Files::             Files You Must Create or Alter
* autoconf macros::             Autoconf macros for use in `configure.in'
* CVS Issues::                  Integrating with CVS
* Release Management::          Creating a Distribution Tarball

Files You Must Create or Alter

* po/POTFILES.in::              `POTFILES.in' in `po/'
* po/LINGUAS::                  `LINGUAS' in `po/'
* po/Makevars::                 `Makevars' in `po/'
* configure.in::                `configure.in' at top level
* config.guess::                `config.guess', `config.sub' at top level
* mkinstalldirs::               `mkinstalldirs' at top level
* aclocal::                     `aclocal.m4' at top level
* acconfig::                    `acconfig.h' at top level
* config.h.in::                 `config.h.in' at top level
* Makefile::                    `Makefile.in' at top level
* src/Makefile::                `Makefile.in' in `src/'
* lib/gettext.h::               `gettext.h' in `lib/'

Autoconf macros for use in `configure.in'

* AM_GNU_GETTEXT::              AM_GNU_GETTEXT in `gettext.m4'
* AM_GNU_GETTEXT_VERSION::      AM_GNU_GETTEXT_VERSION in `gettext.m4'
* AM_PO_SUBDIRS::               AM_PO_SUBDIRS in `po.m4'
* AM_ICONV::                    AM_ICONV in `iconv.m4'

Integrating with CVS

* Distributed CVS::             Avoiding version mismatch in distributed development
* Files under CVS::             Files to put under CVS version control
* autopoint Invocation::        Invoking the `autopoint' Program

Other Programming Languages

* Language Implementors::       The Language Implementor's View
* Programmers for other Languages::  The Programmer's View
* Translators for other Languages::  The Translator's View
* Maintainers for other Languages::  The Maintainer's View
* List of Programming Languages::  Individual Programming Languages
* List of Data Formats::        Internationalizable Data

The Translator's View

* c-format::                    C Format Strings
* objc-format::                 Objective C Format Strings
* sh-format::                   Shell Format Strings
* python-format::               Python Format Strings
* lisp-format::                 Lisp Format Strings
* elisp-format::                Emacs Lisp Format Strings
* librep-format::               librep Format Strings
* scheme-format::               Scheme Format Strings
* smalltalk-format::            Smalltalk Format Strings
* java-format::                 Java Format Strings
* csharp-format::               C# Format Strings
* awk-format::                  awk Format Strings
* object-pascal-format::        Object Pascal Format Strings
* ycp-format::                  YCP Format Strings
* tcl-format::                  Tcl Format Strings
* perl-format::                 Perl Format Strings
* php-format::                  PHP Format Strings
* gcc-internal-format::         GCC internal Format Strings
* qt-format::                   Qt Format Strings

Individual Programming Languages

* C::                           C, C++, Objective C
* sh::                          sh - Shell Script
* bash::                        bash - Bourne-Again Shell Script
* Python::                      Python
* Common Lisp::                 GNU clisp - Common Lisp
* clisp C::                     GNU clisp C sources
* Emacs Lisp::                  Emacs Lisp
* librep::                      librep
* Scheme::                      GNU guile - Scheme
* Smalltalk::                   GNU Smalltalk
* Java::                        Java
* C#::                          C#
* gawk::                        GNU awk
* Pascal::                      Pascal - Free Pascal Compiler
* wxWindows::                   wxWindows library
* YCP::                         YCP - YaST2 scripting language
* Tcl::                         Tcl - Tk's scripting language
* Perl::                        Perl
* PHP::                         PHP Hypertext Preprocessor
* Pike::                        Pike
* GCC-source::                  GNU Compiler Collection sources

sh - Shell Script

* Preparing Shell Scripts::     Preparing Shell Scripts for Internationalization
* gettext.sh::                  Contents of `gettext.sh'
* gettext Invocation::          Invoking the `gettext' program
* ngettext Invocation::         Invoking the `ngettext' program
* envsubst Invocation::         Invoking the `envsubst' program
* eval_gettext Invocation::     Invoking the `eval_gettext' function
* eval_ngettext Invocation::    Invoking the `eval_ngettext' function

Perl

* General Problems::            General Problems Parsing Perl Code
* Default Keywords::            Which Keywords Will xgettext Look For?
* Special Keywords::            How to Extract Hash Keys
* Quote-like Expressions::      What are Strings And Quote-like Expressions?
* Interpolation I::             Invalid String Interpolation
* Interpolation II::            Valid String Interpolation
* Parentheses::                 When To Use Parentheses
* Long Lines::                  How To Grok with Long Lines
* Perl Pitfalls::               Bugs, Pitfalls, and Things That Do Not Work

Internationalizable Data

* POT::                         POT - Portable Object Template
* RST::                         Resource String Table
* Glade::                       Glade - GNOME user interface description

Concluding Remarks

* History::                     History of GNU `gettext'
* References::                  Related Readings


File: gettext.info,  Node: Introduction,  Next: Basics,  Prev: Top,  Up: Top

1 Introduction
**************

     This manual is still in _DRAFT_ state.  Some sections are still
     empty, or almost.  We keep merging material from other sources
     (essentially e-mail folders) while the proper integration of this
     material is delayed.

   In this manual, we use _he_ when speaking of the programmer or
maintainer, _she_ when speaking of the translator, and _they_ when
speaking of the installers or end users of the translated program.
This is only a convenience for clarifying the documentation.  It is
_absolutely_ not meant to imply that some roles are more appropriate to
males or females.  Besides, as you might guess, GNU `gettext' is meant
to be useful for people using computers, whatever their sex, race,
religion or nationality!

   This chapter explains the goals sought in the creation of GNU
`gettext' and the free Translation Project.  Then, it explains a few
broad concepts around Native Language Support, and positions message
translation with regard to other aspects of national and cultural
variance, as they apply to to programs.  It also surveys those files
used to convey the translations.  It explains how the various tools
interact in the initial generation of these files, and later, how the
maintenance cycle should usually operate.

   Please send suggestions and corrections to:

     Internet address:
         bug-gnu-gettext@gnu.org

Please include the manual's edition number and update date in your
messages.

* Menu:

* Why::                         The Purpose of GNU `gettext'
* Concepts::                    I18n, L10n, and Such
* Aspects::                     Aspects in Native Language Support
* Files::                       Files Conveying Translations
* Overview::                    Overview of GNU `gettext'


File: gettext.info,  Node: Why,  Next: Concepts,  Prev: Introduction,  Up: Introduction

1.1 The Purpose of GNU `gettext'
================================

Usually, programs are written and documented in English, and use
English at execution time to interact with users.  This is true not
only of GNU software, but also of a great deal of commercial and free
software.  Using a common language is quite handy for communication
between developers, maintainers and users from all countries.  On the
other hand, most people are less comfortable with English than with
their own native language, and would prefer to use their mother tongue
for day to day's work, as far as possible.  Many would simply _love_ to
see their computer screen showing a lot less of English, and far more
of their own language.

   However, to many people, this dream might appear so far fetched that
they may believe it is not even worth spending time thinking about it.
They have no confidence at all that the dream might ever become true.
Yet some have not lost hope, and have organized themselves.  The
Translation Project is a formalization of this hope into a workable
structure, which has a good chance to get all of us nearer the
achievement of a truly multi-lingual set of programs.

   GNU `gettext' is an important step for the Translation Project, as
it is an asset on which we may build many other steps.  This package
offers to programmers, translators and even users, a well integrated
set of tools and documentation.  Specifically, the GNU `gettext'
utilities are a set of tools that provides a framework within which
other free packages may produce multi-lingual messages.  These tools
include

   * A set of conventions about how programs should be written to
     support message catalogs.

   * A directory and file naming organization for the message catalogs
     themselves.

   * A runtime library supporting the retrieval of translated messages.

   * A few stand-alone programs to massage in various ways the sets of
     translatable strings, or already translated strings.

   * A special mode for Emacs(1) which helps preparing these sets and
     bringing them up to date.

   GNU `gettext' is designed to minimize the impact of
internationalization on program sources, keeping this impact as small
and hardly noticeable as possible.  Internationalization has better
chances of succeeding if it is very light weighted, or at least, appear
to be so, when looking at program sources.

   The Translation Project also uses the GNU `gettext' distribution as
a vehicle for documenting its structure and methods.  This goes beyond
the strict technicalities of documenting the GNU `gettext' proper.  By
so doing, translators will find in a single place, as far as possible,
all they need to know for properly doing their translating work.  Also,
this supplemental documentation might also help programmers, and even
curious users, in understanding how GNU `gettext' is related to the
remainder of the Translation Project, and consequently, have a glimpse
at the _big picture_.

   ---------- Footnotes ----------

   (1) In this manual, all mentions of Emacs refers to either GNU Emacs
or to XEmacs, which people sometimes call FSF Emacs and Lucid Emacs,
respectively.


File: gettext.info,  Node: Concepts,  Next: Aspects,  Prev: Why,  Up: Introduction

1.2 I18n, L10n, and Such
========================

Two long words appear all the time when we discuss support of native
language in programs, and these words have a precise meaning, worth
being explained here, once and for all in this document.  The words are
_internationalization_ and _localization_.  Many people, tired of
writing these long words over and over again, took the habit of writing
"i18n" and "l10n" instead, quoting the first and last letter of each
word, and replacing the run of intermediate letters by a number merely
telling how many such letters there are.  But in this manual, in the
sake of clarity, we will patiently write the names in full, each time...

   By "internationalization", one refers to the operation by which a
program, or a set of programs turned into a package, is made aware of
and able to support multiple languages.  This is a generalization
process, by which the programs are untied from calling only English
strings or other English specific habits, and connected to generic ways
of doing the same, instead.  Program developers may use various
techniques to internationalize their programs.  Some of these have been
standardized.  GNU `gettext' offers one of these standards.  *Note
Programmers::.

   By "localization", one means the operation by which, in a set of
programs already internationalized, one gives the program all needed
information so that it can adapt itself to handle its input and output
in a fashion which is correct for some native language and cultural
habits.  This is a particularisation process, by which generic methods
already implemented in an internationalized program are used in
specific ways.  The programming environment puts several functions to
the programmers disposal which allow this runtime configuration.  The
formal description of specific set of cultural habits for some country,
together with all associated translations targeted to the same native
language, is called the "locale" for this language or country.  Users
achieve localization of programs by setting proper values to special
environment variables, prior to executing those programs, identifying
which locale should be used.

   In fact, locale message support is only one component of the cultural
data that makes up a particular locale.  There are a whole host of
routines and functions provided to aid programmers in developing
internationalized software and which allow them to access the data
stored in a particular locale.  When someone presently refers to a
particular locale, they are obviously referring to the data stored
within that particular locale.  Similarly, if a programmer is referring
to "accessing the locale routines", they are referring to the complete
suite of routines that access all of the locale's information.

   One uses the expression "Native Language Support", or merely NLS,
for speaking of the overall activity or feature encompassing both
internationalization and localization, allowing for multi-lingual
interactions in a program.  In a nutshell, one could say that
internationalization is the operation by which further localizations
are made possible.

   Also, very roughly said, when it comes to multi-lingual messages,
internationalization is usually taken care of by programmers, and
localization is usually taken care of by translators.


File: gettext.info,  Node: Aspects,  Next: Files,  Prev: Concepts,  Up: Introduction

1.3 Aspects in Native Language Support
======================================

For a totally multi-lingual distribution, there are many things to
translate beyond output messages.

   * As of today, GNU `gettext' offers a complete toolset for
     translating messages output by C programs.  Perl scripts and shell
     scripts will also need to be translated.  Even if there are today
     some hooks by which this can be done, these hooks are not
     integrated as well as they should be.

   * Some programs, like `autoconf' or `bison', are able to produce
     other programs (or scripts).  Even if the generating programs
     themselves are internationalized, the generated programs they
     produce may need internationalization on their own, and this
     indirect internationalization could be automated right from the
     generating program.  In fact, quite usually, generating and
     generated programs could be internationalized independently, as
     the effort needed is fairly orthogonal.

   * A few programs include textual tables which might need translation
     themselves, independently of the strings contained in the program
     itself.  For example, RFC 1345 gives an English description for
     each character which the `recode' program is able to reconstruct
     at execution.  Since these descriptions are extracted from the RFC
     by mechanical means, translating them properly would require a
     prior translation of the RFC itself.

   * Almost all programs accept options, which are often worded out so
     to be descriptive for the English readers; one might want to
     consider offering translated versions for program options as well.

   * Many programs read, interpret, compile, or are somewhat driven by
     input files which are texts containing keywords, identifiers, or
     replies which are inherently translatable.  For example, one may
     want `gcc' to allow diacriticized characters in identifiers or use
     translated keywords; `rm -i' might accept something else than `y'
     or `n' for replies, etc.  Even if the program will eventually make
     most of its output in the foreign languages, one has to decide
     whether the input syntax, option values, etc., are to be localized
     or not.

   * The manual accompanying a package, as well as all documentation
     files in the distribution, could surely be translated, too.
     Translating a manual, with the intent of later keeping up with
     updates, is a major undertaking in itself, generally.


   As we already stressed, translation is only one aspect of locales.
Other internationalization aspects are system services and are handled
in GNU `libc'.  There are many attributes that are needed to define a
country's cultural conventions.  These attributes include beside the
country's native language, the formatting of the date and time, the
representation of numbers, the symbols for currency, etc.  These local
"rules" are termed the country's locale.  The locale represents the
knowledge needed to support the country's native attributes.

   There are a few major areas which may vary between countries and
hence, define what a locale must describe.  The following list helps
putting multi-lingual messages into the proper context of other tasks
related to locales.  See the GNU `libc' manual for details.

_Characters and Codesets_
     The codeset most commonly used through out the USA and most English
     speaking parts of the world is the ASCII codeset.  However, there
     are many characters needed by various locales that are not found
     within this codeset.  The 8-bit ISO 8859-1 code set has most of
     the special characters needed to handle the major European
     languages.  However, in many cases, choosing ISO 8859-1 is
     nevertheless not adequate: it doesn't even handle the major
     European currency.  Hence each locale will need to specify which
     codeset they need to use and will need to have the appropriate
     character handling routines to cope with the codeset.

_Currency_
     The symbols used vary from country to country as does the position
     used by the symbol.  Software needs to be able to transparently
     display currency figures in the native mode for each locale.

_Dates_
     The format of date varies between locales.  For example, Christmas
     day in 1994 is written as 12/25/94 in the USA and as 25/12/94 in
     Australia.  Other countries might use ISO 8601 dates, etc.

     Time of the day may be noted as HH:MM, HH.MM, or otherwise.  Some
     locales require time to be specified in 24-hour mode rather than
     as AM or PM.  Further, the nature and yearly extent of the
     Daylight Saving correction vary widely between countries.

_Numbers_
     Numbers can be represented differently in different locales.  For
     example, the following numbers are all written correctly for their
     respective locales:

          12,345.67       English
          12.345,67       German
           12345,67       French
          1,2345.67       Asia

     Some programs could go further and use different unit systems, like
     English units or Metric units, or even take into account variants
     about how numbers are spelled in full.

_Messages_
     The most obvious area is the language support within a locale.
     This is where GNU `gettext' provides the means for developers and
     users to easily change the language that the software uses to
     communicate to the user.


   Components of locale outside of message handling are standardized in
the ISO C standard and the SUSV2 specification.  GNU `libc' fully
implements this, and most other modern systems provide a more or less
reasonable support for at least some of the missing components.


File: gettext.info,  Node: Files,  Next: Overview,  Prev: Aspects,  Up: Introduction

1.4 Files Conveying Translations
================================

The letters PO in `.po' files means Portable Object, to distinguish it
from `.mo' files, where MO stands for Machine Object.  This paradigm,
as well as the PO file format, is inspired by the NLS standard
developed by Uniforum, and first implemented by Sun in their Solaris
system.

   PO files are meant to be read and edited by humans, and associate
each original, translatable string of a given package with its
translation in a particular target language.  A single PO file is
dedicated to a single target language.  If a package supports many
languages, there is one such PO file per language supported, and each
package has its own set of PO files.  These PO files are best created by
the `xgettext' program, and later updated or refreshed through the
`msgmerge' program.  Program `xgettext' extracts all marked messages
from a set of C files and initializes a PO file with empty
translations.  Program `msgmerge' takes care of adjusting PO files
between releases of the corresponding sources, commenting obsolete
entries, initializing new ones, and updating all source line
references.  Files ending with `.pot' are kind of base translation
files found in distributions, in PO file format.

   MO files are meant to be read by programs, and are binary in nature.
A few systems already offer tools for creating and handling MO files as
part of the Native Language Support coming with the system, but the
format of these MO files is often different from system to system, and
non-portable.  The tools already provided with these systems don't
support all the features of GNU `gettext'.  Therefore GNU `gettext'
uses its own format for MO files.  Files ending with `.gmo' are really
MO files, when it is known that these files use the GNU format.


File: gettext.info,  Node: Overview,  Prev: Files,  Up: Introduction

1.5 Overview of GNU `gettext'
=============================

The following diagram summarizes the relation between the files handled
by GNU `gettext' and the tools acting on these files.  It is followed
by somewhat detailed explanations, which you should read while keeping
an eye on the diagram.  Having a clear understanding of these
interrelations will surely help programmers, translators and
maintainers.

     Original C Sources ---> PO mode ---> Marked C Sources ---.
                                                              |
                   .---------<--- GNU gettext Library         |
     .--- make <---+                                          |
     |             `---------<--------------------+-----------'
     |                                            |
     |   .-----<--- PACKAGE.pot <--- xgettext <---'   .---<--- PO Compendium
     |   |                                            |             ^
     |   |                                            `---.         |
     |   `---.                                            +---> PO mode ---.
     |       +----> msgmerge ------> LANG.po ---->--------'                |
     |   .---'                                                             |
     |   |                                                                 |
     |   `-------------<---------------.                                   |
     |                                 +--- New LANG.po <------------------'
     |   .--- LANG.gmo <--- msgfmt <---'
     |   |
     |   `---> install ---> /.../LANG/PACKAGE.mo ---.
     |                                              +---> "Hello world!"
     `-------> install ---> /.../bin/PROGRAM -------'

   The indication `PO mode' appears in two places in this picture, and
you may safely read it as merely meaning "hand editing", using any
editor of your choice, really.  However, for those of you being the
lucky users of Emacs, PO mode has been specifically created for
providing a cozy environment for editing or modifying PO files.  While
editing a PO file, PO mode allows for the easy browsing of auxiliary
and compendium PO files, as well as for following references into the
set of C program sources from which PO files have been derived.  It has
a few special features, among which are the interactive marking of
program strings as translatable, and the validation of PO files with
easy repositioning to PO file lines showing errors.

   As a programmer, the first step to bringing GNU `gettext' into your
package is identifying, right in the C sources, those strings which are
meant to be translatable, and those which are untranslatable.  This
tedious job can be done a little more comfortably using emacs PO mode,
but you can use any means familiar to you for modifying your C sources.
Beside this some other simple, standard changes are needed to properly
initialize the translation library.  *Note Sources::, for more
information about all this.

   For newly written software the strings of course can and should be
marked while writing it.  The `gettext' approach makes this very easy.
Simply put the following lines at the beginning of each file or in a
central header file:

     #define _(String) (String)
     #define N_(String) String
     #define textdomain(Domain)
     #define bindtextdomain(Package, Directory)

Doing this allows you to prepare the sources for internationalization.
Later when you feel ready for the step to use the `gettext' library
simply replace these definitions by the following:

     #include <libintl.h>
     #define _(String) gettext (String)
     #define gettext_noop(String) String
     #define N_(String) gettext_noop (String)

and link against `libintl.a' or `libintl.so'.  Note that on GNU
systems, you don't need to link with `libintl' because the `gettext'
library functions are already contained in GNU libc.  That is all you
have to change.

   Once the C sources have been modified, the `xgettext' program is
used to find and extract all translatable strings, and create a PO
template file out of all these.  This `PACKAGE.pot' file contains all
original program strings.  It has sets of pointers to exactly where in
C sources each string is used.  All translations are set to empty.  The
letter `t' in `.pot' marks this as a Template PO file, not yet oriented
towards any particular language.  *Note xgettext Invocation::, for more
details about how one calls the `xgettext' program.  If you are
_really_ lazy, you might be interested at working a lot more right
away, and preparing the whole distribution setup (*note Maintainers::).
By doing so, you spare yourself typing the `xgettext' command, as
`make' should now generate the proper things automatically for you!

   The first time through, there is no `LANG.po' yet, so the `msgmerge'
step may be skipped and replaced by a mere copy of `PACKAGE.pot' to
`LANG.po', where LANG represents the target language.  See *Note
Creating:: for details.

   Then comes the initial translation of messages.  Translation in
itself is a whole matter, still exclusively meant for humans, and whose
complexity far overwhelms the level of this manual.  Nevertheless, a
few hints are given in some other chapter of this manual (*note
Translators::).  You will also find there indications about how to
contact translating teams, or becoming part of them, for sharing your
translating concerns with others who target the same native language.

   While adding the translated messages into the `LANG.po' PO file, if
you do not have Emacs handy, you are on your own for ensuring that your
efforts fully respect the PO file format, and quoting conventions
(*note PO Files::).  This is surely not an impossible task, as this is
the way many people have handled PO files already for Uniforum or
Solaris.  On the other hand, by using PO mode in Emacs, most details of
PO file format are taken care of for you, but you have to acquire some
familiarity with PO mode itself.  Besides main PO mode commands (*note
Main PO Commands::), you should know how to move between entries (*note
Entry Positioning::), and how to handle untranslated entries (*note
Untranslated Entries::).

   If some common translations have already been saved into a compendium
PO file, translators may use PO mode for initializing untranslated
entries from the compendium, and also save selected translations into
the compendium, updating it (*note Compendium::).  Compendium files are
meant to be exchanged between members of a given translation team.

   Programs, or packages of programs, are dynamic in nature: users write
bug reports and suggestion for improvements, maintainers react by
modifying programs in various ways.  The fact that a package has
already been internationalized should not make maintainers shy of
adding new strings, or modifying strings already translated.  They just
do their job the best they can.  For the Translation Project to work
smoothly, it is important that maintainers do not carry translation
concerns on their already loaded shoulders, and that translators be
kept as free as possible of programming concerns.

   The only concern maintainers should have is carefully marking new
strings as translatable, when they should be, and do not otherwise
worry about them being translated, as this will come in proper time.
Consequently, when programs and their strings are adjusted in various
ways by maintainers, and for matters usually unrelated to translation,
`xgettext' would construct `PACKAGE.pot' files which are evolving over
time, so the translations carried by `LANG.po' are slowly fading out of
date.

   It is important for translators (and even maintainers) to understand
that package translation is a continuous process in the lifetime of a
package, and not something which is done once and for all at the start.
After an initial burst of translation activity for a given package,
interventions are needed once in a while, because here and there,
translated entries become obsolete, and new untranslated entries
appear, needing translation.

   The `msgmerge' program has the purpose of refreshing an already
existing `LANG.po' file, by comparing it with a newer `PACKAGE.pot'
template file, extracted by `xgettext' out of recent C sources.  The
refreshing operation adjusts all references to C source locations for
strings, since these strings move as programs are modified.  Also,
`msgmerge' comments out as obsolete, in `LANG.po', those already
translated entries which are no longer used in the program sources
(*note Obsolete Entries::).  It finally discovers new strings and
inserts them in the resulting PO file as untranslated entries (*note
Untranslated Entries::).  *Note msgmerge Invocation::, for more
information about what `msgmerge' really does.

   Whatever route or means taken, the goal is to obtain an updated
`LANG.po' file offering translations for all strings.

   The temporal mobility, or fluidity of PO files, is an integral part
of the translation game, and should be well understood, and accepted.
People resisting it will have a hard time participating in the
Translation Project, or will give a hard time to other participants!  In
particular, maintainers should relax and include all available official
PO files in their distributions, even if these have not recently been
updated, without exerting pressure on the translator teams to get the
job done.  The pressure should rather come from the community of users
speaking a particular language, and maintainers should consider
themselves fairly relieved of any concern about the adequacy of
translation files.  On the other hand, translators should reasonably
try updating the PO files they are responsible for, while the package
is undergoing pretest, prior to an official distribution.

   Once the PO file is complete and dependable, the `msgfmt' program is
used for turning the PO file into a machine-oriented format, which may
yield efficient retrieval of translations by the programs of the
package, whenever needed at runtime (*note MO Files::).  *Note msgfmt
Invocation::, for more information about all modes of execution for the
`msgfmt' program.

   Finally, the modified and marked C sources are compiled and linked
with the GNU `gettext' library, usually through the operation of
`make', given a suitable `Makefile' exists for the project, and the
resulting executable is installed somewhere users will find it.  The MO
files themselves should also be properly installed.  Given the
appropriate environment variables are set (*note End Users::), the
program should localize itself automatically, whenever it executes.

   The remainder of this manual has the purpose of explaining in depth
the various steps outlined above.


File: gettext.info,  Node: Basics,  Next: Sources,  Prev: Introduction,  Up: Top

2 PO Files and PO Mode Basics
*****************************

The GNU `gettext' toolset helps programmers and translators at
producing, updating and using translation files, mainly those PO files
which are textual, editable files.  This chapter stresses the format of
PO files, and contains a PO mode starter.  PO mode description is
spread throughout this manual instead of being concentrated in one
place.  Here we present only the basics of PO mode.

* Menu:

* Installation::                Completing GNU `gettext' Installation
* PO Files::                    The Format of PO Files
* Main PO Commands::            Main Commands
* Entry Positioning::           Entry Positioning
* Normalizing::                 Normalizing Strings in Entries


File: gettext.info,  Node: Installation,  Next: PO Files,  Prev: Basics,  Up: Basics

2.1 Completing GNU `gettext' Installation
=========================================

Once you have received, unpacked, configured and compiled the GNU
`gettext' distribution, the `make install' command puts in place the
programs `xgettext', `msgfmt', `gettext', and `msgmerge', as well as
their available message catalogs.  To top off a comfortable
installation, you might also want to make the PO mode available to your
Emacs users.

   During the installation of the PO mode, you might want to modify your
file `.emacs', once and for all, so it contains a few lines looking
like:

     (setq auto-mode-alist
           (cons '("\\.po\\'\\|\\.po\\." . po-mode) auto-mode-alist))
     (autoload 'po-mode "po-mode" "Major mode for translators to edit PO files" t)

   Later, whenever you edit some `.po' file, or any file having the
string `.po.' within its name, Emacs loads `po-mode.elc' (or
`po-mode.el') as needed, and automatically activates PO mode commands
for the associated buffer.  The string _PO_ appears in the mode line
for any buffer for which PO mode is active.  Many PO files may be
active at once in a single Emacs session.

   If you are using Emacs version 20 or newer, and have already
installed the appropriate international fonts on your system, you may
also tell Emacs how to determine automatically the coding system of
every PO file.  This will often (but not always) cause the necessary
fonts to be loaded and used for displaying the translations on your
Emacs screen.  For this to happen, add the lines:

     (modify-coding-system-alist 'file "\\.po\\'\\|\\.po\\."
                                 'po-find-file-coding-system)
     (autoload 'po-find-file-coding-system "po-mode")

to your `.emacs' file.  If, with this, you still see boxes instead of
international characters, try a different font set (via Shift Mouse
button 1).


File: gettext.info,  Node: PO Files,  Next: Main PO Commands,  Prev: Installation,  Up: Basics

2.2 The Format of PO Files
==========================

A PO file is made up of many entries, each entry holding the relation
between an original untranslated string and its corresponding
translation.  All entries in a given PO file usually pertain to a
single project, and all translations are expressed in a single target
language.  One PO file "entry" has the following schematic structure:

     WHITE-SPACE
     #  TRANSLATOR-COMMENTS
     #. AUTOMATIC-COMMENTS
     #: REFERENCE...
     #, FLAG...
     msgid UNTRANSLATED-STRING
     msgstr TRANSLATED-STRING

   The general structure of a PO file should be well understood by the
translator.  When using PO mode, very little has to be known about the
format details, as PO mode takes care of them for her.

   A simple entry can look like this:

     #: lib/error.c:116
     msgid "Unknown system error"
     msgstr "Error desconegut del sistema"

   Entries begin with some optional white space.  Usually, when
generated through GNU `gettext' tools, there is exactly one blank line
between entries.  Then comments follow, on lines all starting with the
character `#'.  There are two kinds of comments: those which have some
white space immediately following the `#', which comments are created
and maintained exclusively by the translator, and those which have some
non-white character just after the `#', which comments are created and
maintained automatically by GNU `gettext' tools.  All comments, of
either kind, are optional.

   After white space and comments, entries show two strings, namely
first the untranslated string as it appears in the original program
sources, and then, the translation of this string.  The original string
is introduced by the keyword `msgid', and the translation, by `msgstr'.
The two strings, untranslated and translated, are quoted in various
ways in the PO file, using `"' delimiters and `\' escapes, but the
translator does not really have to pay attention to the precise quoting
format, as PO mode fully takes care of quoting for her.

   The `msgid' strings, as well as automatic comments, are produced and
managed by other GNU `gettext' tools, and PO mode does not provide
means for the translator to alter these.  The most she can do is merely
deleting them, and only by deleting the whole entry.  On the other
hand, the `msgstr' string, as well as translator comments, are really
meant for the translator, and PO mode gives her the full control she
needs.

   The comment lines beginning with `#,' are special because they are
not completely ignored by the programs as comments generally are.  The
comma separated list of FLAGs is used by the `msgfmt' program to give
the user some better diagnostic messages.  Currently there are two
forms of flags defined:

`fuzzy'
     This flag can be generated by the `msgmerge' program or it can be
     inserted by the translator herself.  It shows that the `msgstr'
     string might not be a correct translation (anymore).  Only the
     translator can judge if the translation requires further
     modification, or is acceptable as is.  Once satisfied with the
     translation, she then removes this `fuzzy' attribute.  The
     `msgmerge' program inserts this when it combined the `msgid' and
     `msgstr' entries after fuzzy search only.  *Note Fuzzy Entries::.

`c-format'
`no-c-format'
     These flags should not be added by a human.  Instead only the
     `xgettext' program adds them.  In an automated PO file processing
     system as proposed here the user changes would be thrown away
     again as soon as the `xgettext' program generates a new template
     file.

     The `c-format' flag tells that the untranslated string and the
     translation are supposed to be C format strings.  The `no-c-format'
     flag tells that they are not C format strings, even though the
     untranslated string happens to look like a C format string (with
     `%' directives).

     In case the `c-format' flag is given for a string the `msgfmt'
     does some more tests to check to validity of the translation.
     *Note msgfmt Invocation::, *Note c-format Flag:: and *Note
     c-format::.

`objc-format'
`no-objc-format'
     Likewise for Objective C, see *Note objc-format::.

`sh-format'
`no-sh-format'
     Likewise for Shell, see *Note sh-format::.

`python-format'
`no-python-format'
     Likewise for Python, see *Note python-format::.

`lisp-format'
`no-lisp-format'
     Likewise for Lisp, see *Note lisp-format::.

`elisp-format'
`no-elisp-format'
     Likewise for Emacs Lisp, see *Note elisp-format::.

`librep-format'
`no-librep-format'
     Likewise for librep, see *Note librep-format::.

`scheme-format'
`no-scheme-format'
     Likewise for Scheme, see *Note scheme-format::.

`smalltalk-format'
`no-smalltalk-format'
     Likewise for Smalltalk, see *Note smalltalk-format::.

`java-format'
`no-java-format'
     Likewise for Java, see *Note java-format::.

`csharp-format'
`no-csharp-format'
     Likewise for C#, see *Note csharp-format::.

`awk-format'
`no-awk-format'
     Likewise for awk, see *Note awk-format::.

`object-pascal-format'
`no-object-pascal-format'
     Likewise for Object Pascal, see *Note object-pascal-format::.

`ycp-format'
`no-ycp-format'
     Likewise for YCP, see *Note ycp-format::.

`tcl-format'
`no-tcl-format'
     Likewise for Tcl, see *Note tcl-format::.

`perl-format'
`no-perl-format'
     Likewise for Perl, see *Note perl-format::.

`perl-brace-format'
`no-perl-brace-format'
     Likewise for Perl brace, see *Note perl-format::.

`php-format'
`no-php-format'
     Likewise for PHP, see *Note php-format::.

`gcc-internal-format'
`no-gcc-internal-format'
     Likewise for the GCC sources, see *Note gcc-internal-format::.

`qt-format'
`no-qt-format'
     Likewise for Qt, see *Note qt-format::.


   A different kind of entries is used for translations which involve
plural forms.

     WHITE-SPACE
     #  TRANSLATOR-COMMENTS
     #. AUTOMATIC-COMMENTS
     #: REFERENCE...
     #, FLAG...
     msgid UNTRANSLATED-STRING-SINGULAR
     msgid_plural UNTRANSLATED-STRING-PLURAL
     msgstr[0] TRANSLATED-STRING-CASE-0
     ...
     msgstr[N] TRANSLATED-STRING-CASE-N

   Such an entry can look like this:

     #: src/msgcmp.c:338 src/po-lex.c:699
     #, c-format
     msgid "found %d fatal error"
     msgid_plural "found %d fatal errors"
     msgstr[0] "s'ha trobat %d error fatal"
     msgstr[1] "s'han trobat %d errors fatals"

   It happens that some lines, usually whitespace or comments, follow
the very last entry of a PO file.  Such lines are not part of any entry,
and PO mode is unable to take action on those lines.  By using the PO
mode function `M-x po-normalize', the translator may get rid of those
spurious lines.  *Note Normalizing::.

   The remainder of this section may be safely skipped by those using
PO mode, yet it may be interesting for everybody to have a better idea
of the precise format of a PO file.  On the other hand, those not
having Emacs handy should carefully continue reading on.

   Each of UNTRANSLATED-STRING and TRANSLATED-STRING respects the C
syntax for a character string, including the surrounding quotes and
embedded backslashed escape sequences.  When the time comes to write
multi-line strings, one should not use escaped newlines.  Instead, a
closing quote should follow the last character on the line to be
continued, and an opening quote should resume the string at the
beginning of the following PO file line.  For example:

     msgid ""
     "Here is an example of how one might continue a very long string\n"
     "for the common case the string represents multi-line output.\n"

In this example, the empty string is used on the first line, to allow
better alignment of the `H' from the word `Here' over the `f' from the
word `for'.  In this example, the `msgid' keyword is followed by three
strings, which are meant to be concatenated.  Concatenating the empty
string does not change the resulting overall string, but it is a way
for us to comply with the necessity of `msgid' to be followed by a
string on the same line, while keeping the multi-line presentation
left-justified, as we find this to be a cleaner disposition.  The empty
string could have been omitted, but only if the string starting with
`Here' was promoted on the first line, right after `msgid'.(1) It was
not really necessary either to switch between the two last quoted
strings immediately after the newline `\n', the switch could have
occurred after _any_ other character, we just did it this way because
it is neater.

   One should carefully distinguish between end of lines marked as `\n'
_inside_ quotes, which are part of the represented string, and end of
lines in the PO file itself, outside string quotes, which have no
incidence on the represented string.

   Outside strings, white lines and comments may be used freely.
Comments start at the beginning of a line with `#' and extend until the
end of the PO file line.  Comments written by translators should have
the initial `#' immediately followed by some white space.  If the `#'
is not immediately followed by white space, this comment is most likely
generated and managed by specialized GNU tools, and might disappear or
be replaced unexpectedly when the PO file is given to `msgmerge'.

   ---------- Footnotes ----------

   (1) This limitation is not imposed by GNU `gettext', but is for
compatibility with the `msgfmt' implementation on Solaris.


File: gettext.info,  Node: Main PO Commands,  Next: Entry Positioning,  Prev: PO Files,  Up: Basics

2.3 Main PO mode Commands
=========================

After setting up Emacs with something similar to the lines in *Note
Installation::, PO mode is activated for a window when Emacs finds a PO
file in that window.  This puts the window read-only and establishes a
po-mode-map, which is a genuine Emacs mode, in a way that is not derived
from text mode in any way.  Functions found on `po-mode-hook', if any,
will be executed.

   When PO mode is active in a window, the letters `PO' appear in the
mode line for that window.  The mode line also displays how many
entries of each kind are held in the PO file.  For example, the string
`132t+3f+10u+2o' would tell the translator that the PO mode contains
132 translated entries (*note Translated Entries::, 3 fuzzy entries
(*note Fuzzy Entries::), 10 untranslated entries (*note Untranslated
Entries::) and 2 obsolete entries (*note Obsolete Entries::).
Zero-coefficients items are not shown.  So, in this example, if the
fuzzy entries were unfuzzied, the untranslated entries were translated
and the obsolete entries were deleted, the mode line would merely
display `145t' for the counters.

   The main PO commands are those which do not fit into the other
categories of subsequent sections.  These allow for quitting PO mode or
for managing windows in special ways.

`_'
     Undo last modification to the PO file (`po-undo').

`Q'
     Quit processing and save the PO file (`po-quit').

`q'
     Quit processing, possibly after confirmation
     (`po-confirm-and-quit').

`0'
     Temporary leave the PO file window (`po-other-window').

`?'
`h'
     Show help about PO mode (`po-help').

`='
     Give some PO file statistics (`po-statistics').

`V'
     Batch validate the format of the whole PO file (`po-validate').


   The command `_' (`po-undo') interfaces to the Emacs _undo_ facility.
*Note Undoing Changes: (emacs)Undo.  Each time `U' is typed,
modifications which the translator did to the PO file are undone a
little more.  For the purpose of undoing, each PO mode command is
atomic.  This is especially true for the `<RET>' command: the whole
edition made by using a single use of this command is undone at once,
even if the edition itself implied several actions.  However, while in
the editing window, one can undo the edition work quite parsimoniously.

   The commands `Q' (`po-quit') and `q' (`po-confirm-and-quit') are
used when the translator is done with the PO file.  The former is a bit
less verbose than the latter.  If the file has been modified, it is
saved to disk first.  In both cases, and prior to all this, the
commands check if any untranslated messages remain in the PO file and,
if so, the translator is asked if she really wants to leave off working
with this PO file.  This is the preferred way of getting rid of an
Emacs PO file buffer.  Merely killing it through the usual command
`C-x k' (`kill-buffer') is not the tidiest way to proceed.

   The command `0' (`po-other-window') is another, softer way, to leave
PO mode, temporarily.  It just moves the cursor to some other Emacs
window, and pops one if necessary.  For example, if the translator just
got PO mode to show some source context in some other, she might
discover some apparent bug in the program source that needs correction.
This command allows the translator to change sex, become a programmer,
and have the cursor right into the window containing the program she
(or rather _he_) wants to modify.  By later getting the cursor back in
the PO file window, or by asking Emacs to edit this file once again, PO
mode is then recovered.

   The command `h' (`po-help') displays a summary of all available PO
mode commands.  The translator should then type any character to resume
normal PO mode operations.  The command `?' has the same effect as `h'.

   The command `=' (`po-statistics') computes the total number of
entries in the PO file, the ordinal of the current entry (counted from
1), the number of untranslated entries, the number of obsolete entries,
and displays all these numbers.

   The command `V' (`po-validate') launches `msgfmt' in checking and
verbose mode over the current PO file.  This command first offers to
save the current PO file on disk.  The `msgfmt' tool, from GNU
`gettext', has the purpose of creating a MO file out of a PO file, and
PO mode uses the features of this program for checking the overall
format of a PO file, as well as all individual entries.

   The program `msgfmt' runs asynchronously with Emacs, so the
translator regains control immediately while her PO file is being
studied.  Error output is collected in the Emacs `*compilation*' buffer,
displayed in another window.  The regular Emacs command `C-x`'
(`next-error'), as well as other usual compile commands, allow the
translator to reposition quickly to the offending parts of the PO file.
Once the cursor is on the line in error, the translator may decide on
any PO mode action which would help correcting the error.


File: gettext.info,  Node: Entry Positioning,  Next: Normalizing,  Prev: Main PO Commands,  Up: Basics

2.4 Entry Positioning
=====================

The cursor in a PO file window is almost always part of an entry.  The
only exceptions are the special case when the cursor is after the last
entry in the file, or when the PO file is empty.  The entry where the
cursor is found to be is said to be the current entry.  Many PO mode
commands operate on the current entry, so moving the cursor does more
than allowing the translator to browse the PO file, this also selects
on which entry commands operate.

   Some PO mode commands alter the position of the cursor in a
specialized way.  A few of those special purpose positioning are
described here, the others are described in following sections (for a
complete list try `C-h m'):

`.'
     Redisplay the current entry (`po-current-entry').

`n'
     Select the entry after the current one (`po-next-entry').

`p'
     Select the entry before the current one (`po-previous-entry').

`<'
     Select the first entry in the PO file (`po-first-entry').

`>'
     Select the last entry in the PO file (`po-last-entry').

`m'
     Record the location of the current entry for later use
     (`po-push-location').

`r'
     Return to a previously saved entry location (`po-pop-location').

`x'
     Exchange the current entry location with the previously saved one
     (`po-exchange-location').


   Any Emacs command able to reposition the cursor may be used to
select the current entry in PO mode, including commands which move by
characters, lines, paragraphs, screens or pages, and search commands.
However, there is a kind of standard way to display the current entry
in PO mode, which usual Emacs commands moving the cursor do not
especially try to enforce.  The command `.' (`po-current-entry') has
the sole purpose of redisplaying the current entry properly, after the
current entry has been changed by means external to PO mode, or the
Emacs screen otherwise altered.

   It is yet to be decided if PO mode helps the translator, or otherwise
irritates her, by forcing a rigid window disposition while she is doing
her work.  We originally had quite precise ideas about how windows
should behave, but on the other hand, anyone used to Emacs is often
happy to keep full control.  Maybe a fixed window disposition might be
offered as a PO mode option that the translator might activate or
deactivate at will, so it could be offered on an experimental basis.
If nobody feels a real need for using it, or a compulsion for writing
it, we should drop this whole idea.  The incentive for doing it should
come from translators rather than programmers, as opinions from an
experienced translator are surely more worth to me than opinions from
programmers _thinking_ about how _others_ should do translation.

   The commands `n' (`po-next-entry') and `p' (`po-previous-entry')
move the cursor the entry following, or preceding, the current one.  If
`n' is given while the cursor is on the last entry of the PO file, or
if `p' is given while the cursor is on the first entry, no move is done.

   The commands `<' (`po-first-entry') and `>' (`po-last-entry') move
the cursor to the first entry, or last entry, of the PO file.  When the
cursor is located past the last entry in a PO file, most PO mode
commands will return an error saying `After last entry'.  Moreover, the
commands `<' and `>' have the special property of being able to work
even when the cursor is not into some PO file entry, and one may use
them for nicely correcting this situation.  But even these commands
will fail on a truly empty PO file.  There are development plans for
the PO mode for it to interactively fill an empty PO file from sources.
*Note Marking::.

   The translator may decide, before working at the translation of a
particular entry, that she needs to browse the remainder of the PO
file, maybe for finding the terminology or phraseology used in related
entries.  She can of course use the standard Emacs idioms for saving
the current cursor location in some register, and use that register for
getting back, or else, use the location ring.

   PO mode offers another approach, by which cursor locations may be
saved onto a special stack.  The command `m' (`po-push-location')
merely adds the location of current entry to the stack, pushing the
already saved locations under the new one.  The command `r'
(`po-pop-location') consumes the top stack element and repositions the
cursor to the entry associated with that top element.  This position is
then lost, for the next `r' will move the cursor to the previously
saved location, and so on until no locations remain on the stack.

   If the translator wants the position to be kept on the location
stack, maybe for taking a look at the entry associated with the top
element, then go elsewhere with the intent of getting back later, she
ought to use `m' immediately after `r'.

   The command `x' (`po-exchange-location') simultaneously repositions
the cursor to the entry associated with the top element of the stack of
saved locations, and replaces that top element with the location of the
current entry before the move.  Consequently, repeating the `x' command
toggles alternatively between two entries.  For achieving this, the
translator will position the cursor on the first entry, use `m', then
position to the second entry, and merely use `x' for making the switch.


File: gettext.info,  Node: Normalizing,  Prev: Entry Positioning,  Up: Basics

2.5 Normalizing Strings in Entries
==================================

There are many different ways for encoding a particular string into a
PO file entry, because there are so many different ways to split and
quote multi-line strings, and even, to represent special characters by
backslashed escaped sequences.  Some features of PO mode rely on the
ability for PO mode to scan an already existing PO file for a
particular string encoded into the `msgid' field of some entry.  Even
if PO mode has internally all the built-in machinery for implementing
this recognition easily, doing it fast is technically difficult.  To
facilitate a solution to this efficiency problem, we decided on a
canonical representation for strings.

   A conventional representation of strings in a PO file is currently
under discussion, and PO mode experiments with a canonical
representation.  Having both `xgettext' and PO mode converging towards
a uniform way of representing equivalent strings would be useful, as
the internal normalization needed by PO mode could be automatically
satisfied when using `xgettext' from GNU `gettext'.  An explicit PO
mode normalization should then be only necessary for PO files imported
from elsewhere, or for when the convention itself evolves.

   So, for achieving normalization of at least the strings of a given
PO file needing a canonical representation, the following PO mode
command is available:

`M-x po-normalize'
     Tidy the whole PO file by making entries more uniform.


   The special command `M-x po-normalize', which has no associated
keys, revises all entries, ensuring that strings of both original and
translated entries use uniform internal quoting in the PO file.  It
also removes any crumb after the last entry.  This command may be
useful for PO files freshly imported from elsewhere, or if we ever
improve on the canonical quoting format we use.  This canonical format
is not only meant for getting cleaner PO files, but also for greatly
speeding up `msgid' string lookup for some other PO mode commands.

   `M-x po-normalize' presently makes three passes over the entries.
The first implements heuristics for converting PO files for GNU
`gettext' 0.6 and earlier, in which `msgid' and `msgstr' fields were
using K&R style C string syntax for multi-line strings.  These
heuristics may fail for comments not related to obsolete entries and
ending with a backslash; they also depend on subsequent passes for
finalizing the proper commenting of continued lines for obsolete
entries.  This first pass might disappear once all oldish PO files
would have been adjusted.  The second and third pass normalize all
`msgid' and `msgstr' strings respectively.  They also clean out those
trailing backslashes used by XView's `msgfmt' for continued lines.

   Having such an explicit normalizing command allows for importing PO
files from other sources, but also eases the evolution of the current
convention, evolution driven mostly by aesthetic concerns, as of now.
It is easy to make suggested adjustments at a later time, as the
normalizing command and eventually, other GNU `gettext' tools should
greatly automate conformance.  A description of the canonical string
format is given below, for the particular benefit of those not having
Emacs handy, and who would nevertheless want to handcraft their PO
files in nice ways.

   Right now, in PO mode, strings are single line or multi-line.  A
string goes multi-line if and only if it has _embedded_ newlines, that
is, if it matches `[^\n]\n+[^\n]'.  So, we would have:

     msgstr "\n\nHello, world!\n\n\n"

   but, replacing the space by a newline, this becomes:

     msgstr ""
     "\n"
     "\n"
     "Hello,\n"
     "world!\n"
     "\n"
     "\n"

   We are deliberately using a caricatural example, here, to make the
point clearer.  Usually, multi-lines are not that bad looking.  It is
probable that we will implement the following suggestion.  We might
lump together all initial newlines into the empty string, and also all
newlines introducing empty lines (that is, for N > 1, the N-1'th last
newlines would go together on a separate string), so making the
previous example appear:

     msgstr "\n\n"
     "Hello,\n"
     "world!\n"
     "\n\n"

   There are a few yet undecided little points about string
normalization, to be documented in this manual, once these questions
settle.


File: gettext.info,  Node: Sources,  Next: Template,  Prev: Basics,  Up: Top

3 Preparing Program Sources
***************************

For the programmer, changes to the C source code fall into three
categories.  First, you have to make the localization functions known
to all modules needing message translation.  Second, you should
properly trigger the operation of GNU `gettext' when the program
initializes, usually from the `main' function.  Last, you should
identify and especially mark all constant strings in your program
needing translation.

   Presuming that your set of programs, or package, has been adjusted
so all needed GNU `gettext' files are available, and your `Makefile'
files are adjusted (*note Maintainers::), each C module having
translated C strings should contain the line:

     #include <libintl.h>

   Similarly, each C module containing `printf()'/`fprintf()'/...
calls with a format string that could be a translated C string (even if
the C string comes from a different C module) should contain the line:

     #include <libintl.h>

   The remaining changes to your C sources are discussed in the further
sections of this chapter.

* Menu:

* Triggering::                  Triggering `gettext' Operations
* Preparing Strings::           Preparing Translatable Strings
* Mark Keywords::               How Marks Appear in Sources
* Marking::                     Marking Translatable Strings
* c-format Flag::               Telling something about the following string
* Special cases::               Special Cases of Translatable Strings
* Names::                       Marking Proper Names for Translation
* Libraries::                   Preparing Library Sources


File: gettext.info,  Node: Triggering,  Next: Preparing Strings,  Prev: Sources,  Up: Sources

3.1 Triggering `gettext' Operations
===================================

The initialization of locale data should be done with more or less the
same code in every program, as demonstrated below:

     int
     main (int argc, char *argv[])
     {
       ...
       setlocale (LC_ALL, "");
       bindtextdomain (PACKAGE, LOCALEDIR);
       textdomain (PACKAGE);
       ...
     }

   PACKAGE and LOCALEDIR should be provided either by `config.h' or by
the Makefile.  For now consult the `gettext' or `hello' sources for
more information.

   The use of `LC_ALL' might not be appropriate for you.  `LC_ALL'
includes all locale categories and especially `LC_CTYPE'.  This later
category is responsible for determining character classes with the
`isalnum' etc. functions from `ctype.h' which could especially for
programs, which process some kind of input language, be wrong.  For
example this would mean that a source code using the c, (c-cedilla
character) is runnable in France but not in the U.S.

   Some systems also have problems with parsing numbers using the
`scanf' functions if an other but the `LC_ALL' locale is used.  The
standards say that additional formats but the one known in the `"C"'
locale might be recognized.  But some systems seem to reject numbers in
the `"C"' locale format.  In some situation, it might also be a problem
with the notation itself which makes it impossible to recognize whether
the number is in the `"C"' locale or the local format.  This can happen
if thousands separator characters are used.  Some locales define this
character according to the national conventions to `'.'' which is the
same character used in the `"C"' locale to denote the decimal point.

   So it is sometimes necessary to replace the `LC_ALL' line in the
code above by a sequence of `setlocale' lines

     {
       ...
       setlocale (LC_CTYPE, "");
       setlocale (LC_MESSAGES, "");
       ...
     }

On all POSIX conformant systems the locale categories `LC_CTYPE',
`LC_MESSAGES', `LC_COLLATE', `LC_MONETARY', `LC_NUMERIC', and `LC_TIME'
are available.  On some systems which are only ISO C compliant,
`LC_MESSAGES' is missing, but a substitute for it is defined in GNU
gettext's `<libintl.h>'.

   Note that changing the `LC_CTYPE' also affects the functions
declared in the `<ctype.h>' standard header.  If this is not desirable
in your application (for example in a compiler's parser), you can use a
set of substitute functions which hardwire the C locale, such as found
in the `<c-ctype.h>' and `<c-ctype.c>' files in the gettext source
distribution.

   It is also possible to switch the locale forth and back between the
environment dependent locale and the C locale, but this approach is
normally avoided because a `setlocale' call is expensive, because it is
tedious to determine the places where a locale switch is needed in a
large program's source, and because switching a locale is not
multithread-safe.


File: gettext.info,  Node: Preparing Strings,  Next: Mark Keywords,  Prev: Triggering,  Up: Sources

3.2 Preparing Translatable Strings
==================================

Before strings can be marked for translations, they sometimes need to
be adjusted.  Usually preparing a string for translation is done right
before marking it, during the marking phase which is described in the
next sections.  What you have to keep in mind while doing that is the
following.

   * Decent English style.

   * Entire sentences.

   * Split at paragraphs.

   * Use format strings instead of string concatenation.

Let's look at some examples of these guidelines.

   Translatable strings should be in good English style.  If slang
language with abbreviations and shortcuts is used, often translators
will not understand the message and will produce very inappropriate
translations.

     "%s: is parameter\n"

This is nearly untranslatable: Is the displayed item _a_ parameter or
_the_ parameter?

     "No match"

The ambiguity in this message makes it ununderstandable: Is the program
attempting to set something on fire? Does it mean "The given object does
not match the template"? Does it mean "The template does not fit for any
of the objects"?

   In both cases, adding more words to the message will help both the
translator and the English speaking user.

   Translatable strings should be entire sentences.  It is often not
possible to translate single verbs or adjectives in a substitutable way.

     printf ("File %s is %s protected", filename, rw ? "write" : "read");

Most translators will not look at the source and will thus only see the
string `"File %s is %s protected"', which is unintelligible.  Change
this to

     printf (rw ? "File %s is write protected" : "File %s is read protected",
             filename);

This way the translator will not only understand the message, she will
also be able to find the appropriate grammatical construction.  The
French translator for example translates "write protected" like
"protected against writing".

   Entire sentences are also important because in many languages, the
declination of some word in a sentence depends on the gender or the
number (singular/plural) of another part of the sentence.  There are
usually more interdependencies between words than in English.  The
consequence is that asking a translator to translate two half-sentences
and then combining these two half-sentences through dumb string
concatenation will not work, for many languages, even though it would
work for English.  That's why translators need to handle entire
sentences.

   Often sentences don't fit into a single line.  If a sentence is
output using two subsequent `printf' statements, like this

     printf ("Locale charset \"%s\" is different from\n", lcharset);
     printf ("input file charset \"%s\".\n", fcharset);

the translator would have to translate two half sentences, but nothing
in the POT file would tell her that the two half sentences belong
together.  It is necessary to merge the two `printf' statements so that
the translator can handle the entire sentence at once and decide at
which place to insert a line break in the translation (if at all):

     printf ("Locale charset \"%s\" is different from\n\
     input file charset \"%s\".\n", lcharset, fcharset);

   You may now ask: how about two or more adjacent sentences? Like in
this case:

     puts ("Apollo 13 scenario: Stack overflow handling failed.");
     puts ("On the next stack overflow we will crash!!!");

Should these two statements merged into a single one? I would recommend
to merge them if the two sentences are related to each other, because
then it makes it easier for the translator to understand and translate
both.  On the other hand, if one of the two messages is a stereotypic
one, occurring in other places as well, you will do a favour to the
translator by not merging the two.  (Identical messages occurring in
several places are combined by xgettext, so the translator has to
handle them once only.)

   Translatable strings should be limited to one paragraph; don't let a
single message be longer than ten lines.  The reason is that when the
translatable string changes, the translator is faced with the task of
updating the entire translated string.  Maybe only a single word will
have changed in the English string, but the translator doesn't see that
(with the current translation tools), therefore she has to proofread
the entire message.

   Many GNU programs have a `--help' output that extends over several
screen pages.  It is a courtesy towards the translators to split such a
message into several ones of five to ten lines each.  While doing that,
you can also attempt to split the documented options into groups, such
as the input options, the output options, and the informative output
options.  This will help every user to find the option he is looking
for.

   Hardcoded string concatenation is sometimes used to construct English
strings:

     strcpy (s, "Replace ");
     strcat (s, object1);
     strcat (s, " with ");
     strcat (s, object2);
     strcat (s, "?");

In order to present to the translator only entire sentences, and also
because in some languages the translator might want to swap the order
of `object1' and `object2', it is necessary to change this to use a
format string:

     sprintf (s, "Replace %s with %s?", object1, object2);

   A similar case is compile time concatenation of strings.  The ISO C
99 include file `<inttypes.h>' contains a macro `PRId64' that can be
used as a formatting directive for outputting an `int64_t' integer
through `printf'.  It expands to a constant string, usually "d" or "ld"
or "lld" or something like this, depending on the platform.  Assume you
have code like

     printf ("The amount is %0" PRId64 "\n", number);

The `gettext' tools and library have special support for these
`<inttypes.h>' macros.  You can therefore simply write

     printf (gettext ("The amount is %0" PRId64 "\n"), number);

The PO file will contain the string "The amount is %0<PRId64>\n".  The
translators will provide a translation containing "%0<PRId64>" as well,
and at runtime the `gettext' function's result will contain the
appropriate constant string, "d" or "ld" or "lld".

   This works only for the predefined `<inttypes.h>' macros.  If you
have defined your own similar macros, let's say `MYPRId64', that are
not known to `xgettext', the solution for this problem is to change the
code like this:

     char buf1[100];
     sprintf (buf1, "%0" MYPRId64, number);
     printf (gettext ("The amount is %s\n"), buf1);

   This means, you put the platform dependent code in one statement,
and the internationalization code in a different statement.  Note that
a buffer length of 100 is safe, because all available hardware integer
types are limited to 128 bits, and to print a 128 bit integer one needs
at most 54 characters, regardless whether in decimal, octal or
hexadecimal.

   All this applies to other programming languages as well.  For
example, in Java and C#, string contenation is very frequently used,
because it is a compiler built-in operator.  Like in C, in Java, you
would change

     System.out.println("Replace "+object1+" with "+object2+"?");

into a statement involving a format string:

     System.out.println(
         MessageFormat.format("Replace {0} with {1}?",
                              new Object[] { object1, object2 }));

Similarly, in C#, you would change

     Console.WriteLine("Replace "+object1+" with "+object2+"?");

into a statement involving a format string:

     Console.WriteLine(
         String.Format("Replace {0} with {1}?", object1, object2));


File: gettext.info,  Node: Mark Keywords,  Next: Marking,  Prev: Preparing Strings,  Up: Sources

3.3 How Marks Appear in Sources
===============================

All strings requiring translation should be marked in the C sources.
Marking is done in such a way that each translatable string appears to
be the sole argument of some function or preprocessor macro.  There are
only a few such possible functions or macros meant for translation, and
their names are said to be marking keywords.  The marking is attached
to strings themselves, rather than to what we do with them.  This
approach has more uses.  A blatant example is an error message produced
by formatting.  The format string needs translation, as well as some
strings inserted through some `%s' specification in the format, while
the result from `sprintf' may have so many different instances that it
is impractical to list them all in some `error_string_out()' routine,
say.

   This marking operation has two goals.  The first goal of marking is
for triggering the retrieval of the translation, at run time.  The
keyword are possibly resolved into a routine able to dynamically return
the proper translation, as far as possible or wanted, for the argument
string.  Most localizable strings are found in executable positions,
that is, attached to variables or given as parameters to functions.
But this is not universal usage, and some translatable strings appear
in structured initializations.  *Note Special cases::.

   The second goal of the marking operation is to help `xgettext' at
properly extracting all translatable strings when it scans a set of
program sources and produces PO file templates.

   The canonical keyword for marking translatable strings is `gettext',
it gave its name to the whole GNU `gettext' package.  For packages
making only light use of the `gettext' keyword, macro or function, it
is easily used _as is_.  However, for packages using the `gettext'
interface more heavily, it is usually more convenient to give the main
keyword a shorter, less obtrusive name.  Indeed, the keyword might
appear on a lot of strings all over the package, and programmers
usually do not want nor need their program sources to remind them
forcefully, all the time, that they are internationalized.  Further, a
long keyword has the disadvantage of using more horizontal space,
forcing more indentation work on sources for those trying to keep them
within 79 or 80 columns.

   Many packages use `_' (a simple underline) as a keyword, and write
`_("Translatable string")' instead of `gettext ("Translatable
string")'.  Further, the coding rule, from GNU standards, wanting that
there is a space between the keyword and the opening parenthesis is
relaxed, in practice, for this particular usage.  So, the textual
overhead per translatable string is reduced to only three characters:
the underline and the two parentheses.  However, even if GNU `gettext'
uses this convention internally, it does not offer it officially.  The
real, genuine keyword is truly `gettext' indeed.  It is fairly easy for
those wanting to use `_' instead of `gettext' to declare:

     #include <libintl.h>
     #define _(String) gettext (String)

instead of merely using `#include <libintl.h>'.

   Later on, the maintenance is relatively easy.  If, as a programmer,
you add or modify a string, you will have to ask yourself if the new or
altered string requires translation, and include it within `_()' if you
think it should be translated.  `"%s: %d"' is an example of string
_not_ requiring translation!


File: gettext.info,  Node: Marking,  Next: c-format Flag,  Prev: Mark Keywords,  Up: Sources

3.4 Marking Translatable Strings
================================

In PO mode, one set of features is meant more for the programmer than
for the translator, and allows him to interactively mark which strings,
in a set of program sources, are translatable, and which are not.  Even
if it is a fairly easy job for a programmer to find and mark such
strings by other means, using any editor of his choice, PO mode makes
this work more comfortable.  Further, this gives translators who feel a
little like programmers, or programmers who feel a little like
translators, a tool letting them work at marking translatable strings
in the program sources, while simultaneously producing a set of
translation in some language, for the package being internationalized.

   The set of program sources, targetted by the PO mode commands
describe here, should have an Emacs tags table constructed for your
project, prior to using these PO file commands.  This is easy to do.
In any shell window, change the directory to the root of your project,
then execute a command resembling:

     etags src/*.[hc] lib/*.[hc]

presuming here you want to process all `.h' and `.c' files from the
`src/' and `lib/' directories.  This command will explore all said
files and create a `TAGS' file in your root directory, somewhat
summarizing the contents using a special file format Emacs can
understand.

   For packages following the GNU coding standards, there is a make
goal `tags' or `TAGS' which constructs the tag files in all directories
and for all files containing source code.

   Once your `TAGS' file is ready, the following commands assist the
programmer at marking translatable strings in his set of sources.  But
these commands are necessarily driven from within a PO file window, and
it is likely that you do not even have such a PO file yet.  This is not
a problem at all, as you may safely open a new, empty PO file, mainly
for using these commands.  This empty PO file will slowly fill in while
you mark strings as translatable in your program sources.

`,'
     Search through program sources for a string which looks like a
     candidate for translation (`po-tags-search').

`M-,'
     Mark the last string found with `_()' (`po-mark-translatable').

`M-.'
     Mark the last string found with a keyword taken from a set of
     possible keywords.  This command with a prefix allows some
     management of these keywords (`po-select-mark-and-mark').


   The `,' (`po-tags-search') command searches for the next occurrence
of a string which looks like a possible candidate for translation, and
displays the program source in another Emacs window, positioned in such
a way that the string is near the top of this other window.  If the
string is too big to fit whole in this window, it is positioned so only
its end is shown.  In any case, the cursor is left in the PO file
window.  If the shown string would be better presented differently in
different native languages, you may mark it using `M-,' or `M-.'.
Otherwise, you might rather ignore it and skip to the next string by
merely repeating the `,' command.

   A string is a good candidate for translation if it contains a
sequence of three or more letters.  A string containing at most two
letters in a row will be considered as a candidate if it has more
letters than non-letters.  The command disregards strings containing no
letters, or isolated letters only.  It also disregards strings within
comments, or strings already marked with some keyword PO mode knows
(see below).

   If you have never told Emacs about some `TAGS' file to use, the
command will request that you specify one from the minibuffer, the
first time you use the command.  You may later change your `TAGS' file
by using the regular Emacs command `M-x visit-tags-table', which will
ask you to name the precise `TAGS' file you want to use.  *Note Tag
Tables: (emacs)Tags.

   Each time you use the `,' command, the search resumes from where it
was left by the previous search, and goes through all program sources,
obeying the `TAGS' file, until all sources have been processed.
However, by giving a prefix argument to the command (`C-u ,'), you may
request that the search be restarted all over again from the first
program source; but in this case, strings that you recently marked as
translatable will be automatically skipped.

   Using this `,' command does not prevent using of other regular Emacs
tags commands.  For example, regular `tags-search' or
`tags-query-replace' commands may be used without disrupting the
independent `,' search sequence.  However, as implemented, the
_initial_ `,' command (or the `,' command is used with a prefix) might
also reinitialize the regular Emacs tags searching to the first tags
file, this reinitialization might be considered spurious.

   The `M-,' (`po-mark-translatable') command will mark the recently
found string with the `_' keyword.  The `M-.'
(`po-select-mark-and-mark') command will request that you type one
keyword from the minibuffer and use that keyword for marking the
string.  Both commands will automatically create a new PO file
untranslated entry for the string being marked, and make it the current
entry (making it easy for you to immediately proceed to its
translation, if you feel like doing it right away).  It is possible
that the modifications made to the program source by `M-,' or `M-.'
render some source line longer than 80 columns, forcing you to break
and re-indent this line differently.  You may use the `O' command from
PO mode, or any other window changing command from Emacs, to break out
into the program source window, and do any needed adjustments.  You
will have to use some regular Emacs command to return the cursor to the
PO file window, if you want command `,' for the next string, say.

   The `M-.' command has a few built-in speedups, so you do not have to
explicitly type all keywords all the time.  The first such speedup is
that you are presented with a _preferred_ keyword, which you may accept
by merely typing `<RET>' at the prompt.  The second speedup is that you
may type any non-ambiguous prefix of the keyword you really mean, and
the command will complete it automatically for you.  This also means
that PO mode has to _know_ all your possible keywords, and that it will
not accept mistyped keywords.

   If you reply `?' to the keyword request, the command gives a list of
all known keywords, from which you may choose.  When the command is
prefixed by an argument (`C-u M-.'), it inhibits updating any program
source or PO file buffer, and does some simple keyword management
instead.  In this case, the command asks for a keyword, written in
full, which becomes a new allowed keyword for later `M-.' commands.
Moreover, this new keyword automatically becomes the _preferred_
keyword for later commands.  By typing an already known keyword in
response to `C-u M-.', one merely changes the _preferred_ keyword and
does nothing more.

   All keywords known for `M-.' are recognized by the `,' command when
scanning for strings, and strings already marked by any of those known
keywords are automatically skipped.  If many PO files are opened
simultaneously, each one has its own independent set of known keywords.
There is no provision in PO mode, currently, for deleting a known
keyword, you have to quit the file (maybe using `q') and reopen it
afresh.  When a PO file is newly brought up in an Emacs window, only
`gettext' and `_' are known as keywords, and `gettext' is preferred for
the `M-.' command.  In fact, this is not useful to prefer `_', as this
one is already built in the `M-,' command.


File: gettext.info,  Node: c-format Flag,  Next: Special cases,  Prev: Marking,  Up: Sources

3.5 Special Comments preceding Keywords
=======================================

In C programs strings are often used within calls of functions from the
`printf' family.  The special thing about these format strings is that
they can contain format specifiers introduced with `%'.  Assume we have
the code

     printf (gettext ("String `%s' has %d characters\n"), s, strlen (s));

A possible German translation for the above string might be:

     "%d Zeichen lang ist die Zeichenkette `%s'"

   A C programmer, even if he cannot speak German, will recognize that
there is something wrong here.  The order of the two format specifiers
is changed but of course the arguments in the `printf' don't have.
This will most probably lead to problems because now the length of the
string is regarded as the address.

   To prevent errors at runtime caused by translations the `msgfmt'
tool can check statically whether the arguments in the original and the
translation string match in type and number.  If this is not the case
and the `-c' option has been passed to `msgfmt', `msgfmt' will give an
error and refuse to produce a MO file.  Thus consequent use of `msgfmt
-c' will catch the error, so that it cannot cause cause problems at
runtime.

If the word order in the above German translation would be correct one
would have to write

     "%2$d Zeichen lang ist die Zeichenkette `%1$s'"

The routines in `msgfmt' know about this special notation.

   Because not all strings in a program must be format strings it is not
useful for `msgfmt' to test all the strings in the `.po' file.  This
might cause problems because the string might contain what looks like a
format specifier, but the string is not used in `printf'.

   Therefore the `xgettext' adds a special tag to those messages it
thinks might be a format string.  There is no absolute rule for this,
only a heuristic.  In the `.po' file the entry is marked using the
`c-format' flag in the `#,' comment line (*note PO Files::).

   The careful reader now might say that this again can cause problems.
The heuristic might guess it wrong.  This is true and therefore
`xgettext' knows about a special kind of comment which lets the
programmer take over the decision.  If in the same line as or the
immediately preceding line to the `gettext' keyword the `xgettext'
program finds a comment containing the words `xgettext:c-format', it
will mark the string in any case with the `c-format' flag.  This kind
of comment should be used when `xgettext' does not recognize the string
as a format string but it really is one and it should be tested.
Please note that when the comment is in the same line as the `gettext'
keyword, it must be before the string to be translated.

   This situation happens quite often.  The `printf' function is often
called with strings which do not contain a format specifier.  Of course
one would normally use `fputs' but it does happen.  In this case
`xgettext' does not recognize this as a format string but what happens
if the translation introduces a valid format specifier?  The `printf'
function will try to access one of the parameters but none exists
because the original code does not pass any parameters.

   `xgettext' of course could make a wrong decision the other way
round, i.e. a string marked as a format string actually is not a format
string.  In this case the `msgfmt' might give too many warnings and
would prevent translating the `.po' file.  The method to prevent this
wrong decision is similar to the one used above, only the comment to
use must contain the string `xgettext:no-c-format'.

   If a string is marked with `c-format' and this is not correct the
user can find out who is responsible for the decision.  See *Note
xgettext Invocation:: to see how the `--debug' option can be used for
solving this problem.


File: gettext.info,  Node: Special cases,  Next: Names,  Prev: c-format Flag,  Up: Sources

3.6 Special Cases of Translatable Strings
=========================================

The attentive reader might now point out that it is not always possible
to mark translatable string with `gettext' or something like this.
Consider the following case:

     {
       static const char *messages[] = {
         "some very meaningful message",
         "and another one"
       };
       const char *string;
       ...
       string
         = index > 1 ? "a default message" : messages[index];

       fputs (string);
       ...
     }

   While it is no problem to mark the string `"a default message"' it
is not possible to mark the string initializers for `messages'.  What
is to be done?  We have to fulfill two tasks.  First we have to mark the
strings so that the `xgettext' program (*note xgettext Invocation::)
can find them, and second we have to translate the string at runtime
before printing them.

   The first task can be fulfilled by creating a new keyword, which
names a no-op.  For the second we have to mark all access points to a
string from the array.  So one solution can look like this:

     #define gettext_noop(String) String

     {
       static const char *messages[] = {
         gettext_noop ("some very meaningful message"),
         gettext_noop ("and another one")
       };
       const char *string;
       ...
       string
         = index > 1 ? gettext ("a default message") : gettext (messages[index]);

       fputs (string);
       ...
     }

   Please convince yourself that the string which is written by `fputs'
is translated in any case.  How to get `xgettext' know the additional
keyword `gettext_noop' is explained in *Note xgettext Invocation::.

   The above is of course not the only solution.  You could also come
along with the following one:

     #define gettext_noop(String) String

     {
       static const char *messages[] = {
         gettext_noop ("some very meaningful message",
         gettext_noop ("and another one")
       };
       const char *string;
       ...
       string
         = index > 1 ? gettext_noop ("a default message") : messages[index];

       fputs (gettext (string));
       ...
     }

   But this has a drawback.  The programmer has to take care that he
uses `gettext_noop' for the string `"a default message"'.  A use of
`gettext' could have in rare cases unpredictable results.

   One advantage is that you need not make control flow analysis to make
sure the output is really translated in any case.  But this analysis is
generally not very difficult.  If it should be in any situation you can
use this second method in this situation.


File: gettext.info,  Node: Names,  Next: Libraries,  Prev: Special cases,  Up: Sources

3.7 Marking Proper Names for Translation
========================================

Should names of persons, cities, locations etc. be marked for
translation or not?  People who only know languages that can be written
with Latin letters (English, Spanish, French, German, etc.) are tempted
to say "no", because names usually do not change when transported
between these languages.  However, in general when translating from one
script to another, names are translated too, usually phonetically or by
transliteration.  For example, Russian or Greek names are converted to
the Latin alphabet when being translated to English, and English or
French names are converted to the Katakana script when being translated
to Japanese.  This is necessary because the speakers of the target
language in general cannot read the script the name is originally
written in.

   As a programmer, you should therefore make sure that names are marked
for translation, with a special comment telling the translators that it
is a proper name and how to pronounce it.  Like this:

     printf (_("Written by %s.\n"),
             /* TRANSLATORS: This is a proper name.  See the gettext
                manual, section Names.  Note this is actually a non-ASCII
                name: The first name is (with Unicode escapes)
                "Fran\u00e7ois" or (with HTML entities) "Fran&ccedil;ois".
                Pronounciation is like "fraa-swa pee-nar".  */
             _("Francois Pinard"));

   As a translator, you should use some care when translating names,
because it is frustrating if people see their names mutilated or
distorted.  If your language uses the Latin script, all you need to do
is to reproduce the name as perfectly as you can within the usual
character set of your language.  In this particular case, this means to
provide a translation containing the c-cedilla character.  If your
language uses a different script and the people speaking it don't
usually read Latin words, it means transliteration; but you should
still give, in parentheses, the original writing of the name - for the
sake of the people that do read the Latin script.  Here is an example,
using Greek as the target script:

     #. This is a proper name.  See the gettext
     #. manual, section Names.  Note this is actually a non-ASCII
     #. name: The first name is (with Unicode escapes)
     #. "Fran\u00e7ois" or (with HTML entities) "Fran&ccedil;ois".
     #. Pronounciation is like "fraa-swa pee-nar".
     msgid "Francois Pinard"
     msgstr "\phi\rho\alpha\sigma\omicron\alpha \pi\iota\nu\alpha\rho"
            " (Francois Pinard)"

   Because translation of names is such a sensitive domain, it is a good
idea to test your translation before submitting it.

   The translation project `http://sourceforge.net/projects/translation'
has set up a POT file and translation domain consisting of program
author names, with better facilities for the translator than those
presented here.  Namely, there the original name is written directly in
Unicode (rather than with Unicode escapes or HTML entities), and the
pronounciation is denoted using the International Phonetic Alphabet (see
`http://www.wikipedia.org/wiki/International_Phonetic_Alphabet').

   However, we don't recommend this approach for all POT files in all
packages, because this would force translators to use PO files in UTF-8
encoding, which is - in the current state of software (as of 2003) - a
major hassle for translators using GNU Emacs or XEmacs with po-mode.


File: gettext.info,  Node: Libraries,  Prev: Names,  Up: Sources

3.8 Preparing Library Sources
=============================

When you are preparing a library, not a program, for the use of
`gettext', only a few details are different.  Here we assume that the
library has a translation domain and a POT file of its own.  (If it
uses the translation domain and POT file of the main program, then the
previous sections apply without changes.)

  1. The library code doesn't call `setlocale (LC_ALL, "")'.  It's the
     responsibility of the main program to set the locale.  The
     library's documentation should mention this fact, so that
     developers of programs using the library are aware of it.

  2. The library code doesn't call `textdomain (PACKAGE)', because it
     would interfere with the text domain set by the main program.

  3. The initialization code for a program was

            setlocale (LC_ALL, "");
            bindtextdomain (PACKAGE, LOCALEDIR);
            textdomain (PACKAGE);

     For a library it is reduced to

            bindtextdomain (PACKAGE, LOCALEDIR);

     If your library's API doesn't already have an initialization
     function, you need to create one, containing at least the
     `bindtextdomain' invocation.  However, you usually don't need to
     export and document this initialization function: It is sufficient
     that all entry points of the library call the initialization
     function if it hasn't been called before.  The typical idiom used
     to achieve this is a static boolean variable that indicates
     whether the initialization function has been called. Like this:

          static bool libfoo_initialized;

          static void
          libfoo_initialize (void)
          {
            bindtextdomain (PACKAGE, LOCALEDIR);
            libfoo_initialized = true;
          }

          /* This function is part of the exported API.  */
          struct foo *
          create_foo (...)
          {
            /* Must ensure the initialization is performed.  */
            if (!libfoo_initialized)
              libfoo_initialize ();
            ...
          }

          /* This function is part of the exported API.  The argument must be
             non-NULL and have been created through create_foo().  */
          int
          foo_refcount (struct foo *argument)
          {
            /* No need to invoke the initialization function here, because
               create_foo() must already have been called before.  */
            ...
          }

  4. The usual declaration of the `_' macro in each source file was

          #include <libintl.h>
          #define _(String) gettext (String)

     for a program.  For a library, which has its own translation
     domain, it reads like this:

          #include <libintl.h>
          #define _(String) dgettext (PACKAGE, String)

     In other words, `dgettext' is used instead of `gettext'.
     Similary, the `dngettext' function should be used in place of the
     `ngettext' function.


File: gettext.info,  Node: Template,  Next: Creating,  Prev: Sources,  Up: Top

4 Making the PO Template File
*****************************

After preparing the sources, the programmer creates a PO template file.
This section explains how to use `xgettext' for this purpose.

   `xgettext' creates a file named `DOMAINNAME.po'.  You should then
rename it to `DOMAINNAME.pot'.  (Why doesn't `xgettext' create it under
the name `DOMAINNAME.pot' right away?  The answer is: for historical
reasons.  When `xgettext' was specified, the distinction between a PO
file and PO file template was fuzzy, and the suffix `.pot' wasn't in
use at that time.)

* Menu:

* xgettext Invocation::         Invoking the `xgettext' Program


File: gettext.info,  Node: xgettext Invocation,  Prev: Template,  Up: Template

4.1 Invoking the `xgettext' Program
===================================

     xgettext [OPTION] [INPUTFILE] ...

   The `xgettext' program extracts translatable strings from given
input files.

4.1.1 Input file location
-------------------------

`INPUTFILE ...'
     Input files.

`-f FILE'
`--files-from=FILE'
     Read the names of the input files from FILE instead of getting
     them from the command line.

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.  The resulting `.po'
     file will be written relative to the current directory, though.


   If INPUTFILE is `-', standard input is read.

4.1.2 Output file location
--------------------------

`-d NAME'
`--default-domain=NAME'
     Use `NAME.po' for output (instead of `messages.po').

`-o FILE'
`--output=FILE'
     Write output to specified file (instead of `NAME.po' or
     `messages.po').

`-p DIR'
`--output-dir=DIR'
     Output files will be placed in directory DIR.


   If the output FILE is `-' or `/dev/stdout', the output is written to
standard output.

4.1.3 Choice of input file language
-----------------------------------

`-L NAME'
`--language=NAME'
     Specifies the language of the input files.  The supported languages
     are `C', `C++', `ObjectiveC', `PO', `Python', `Lisp', `EmacsLisp',
     `librep', `Scheme', `Smalltalk', `Java', `JavaProperties', `C#',
     `awk', `YCP', `Tcl', `Perl', `PHP', `GCC-source', `NXStringTable',
     `RST', `Glade'.

`-C'
`--c++'
     This is a shorthand for `--language=C++'.


   By default the language is guessed depending on the input file name
extension.

4.1.4 Input file interpretation
-------------------------------

`--from-code=NAME'
     Specifies the encoding of the input files.  This option is needed
     only if some untranslated message strings or their corresponding
     comments contain non-ASCII characters.  Note that Python, Tcl, and
     Glade input files are always assumed to be in UTF-8, regardless of
     this option.


   By default the input files are assumed to be in ASCII.

4.1.5 Operation mode
--------------------

`-j'
`--join-existing'
     Join messages with existing file.

`-x FILE'
`--exclude-file=FILE'
     Entries from FILE are not extracted.  FILE should be a PO or POT
     file.

`-c [TAG]'
`--add-comments[=TAG]'
     Place comment block with TAG (or those preceding keyword lines) in
     output file.


4.1.6 Language specific options
-------------------------------

`-a'
`--extract-all'
     Extract all strings.

     This option has an effect with most languages, namely C, C++,
     ObjectiveC, Shell, Python, Lisp, EmacsLisp, librep, Java, C#, awk,
     Tcl, Perl, PHP, GCC-source, Glade.

`-k KEYWORDSPEC'
`--keyword[=KEYWORDSPEC]'
     Additional keyword to be looked for (without KEYWORDSPEC means not
     to use default keywords).

     If KEYWORDSPEC is a C identifer ID, `xgettext' looks for strings
     in the first argument of each call to the function or macro ID.
     If KEYWORDSPEC is of the form `ID:ARGNUM', `xgettext' looks for
     strings in the ARGNUMth argument of the call.  If KEYWORDSPEC is
     of the form `ID:ARGNUM1,ARGNUM2', `xgettext' looks for strings in
     the ARGNUM1st argument and in the ARGNUM2nd argument of the call,
     and treats them as singular/plural variants for a message with
     plural handling.
     The default keyword specifications, which are always looked for if
     not explicitly disabled, are `gettext', `dgettext:2',
     `dcgettext:2', `ngettext:1,2', `dngettext:2,3', `dcngettext:2,3',
     and `gettext_noop'.
     This option has an effect with most languages, namely C, C++,
     ObjectiveC, Shell, Python, Lisp, EmacsLisp, librep, Java, C#, awk,
     Tcl, Perl, PHP, GCC-source, Glade.

`--flag=WORD:ARG:FLAG'
     Specifies additional flags for strings occurring as part of the
     ARGth argument of the function WORD.  The possible flags are the
     possible format string indicators, such as `c-format', and their
     negations, such as `no-c-format', possibly prefixed with `pass-'.
     The meaning of `--flag=FUNCTION:ARG:LANG-format' is that in
     language LANG, the specified FUNCTION expects as ARGth argument a
     format string.  (For those of you familiar with GCC function
     attributes, `--flag=FUNCTION:ARG:c-format' is roughly equivalent
     to the declaration `__attribute__ ((__format__ (__printf__, ARG,
     ...)))' attached to FUNCTION in a C source file.)  For example, if
     you use the `error' function from GNU libc, you can specify its
     behaviour through `--flag=error:3:c-format'.  The effect of this
     specification is that `xgettext' will mark as format strings all
     `gettext' invocations that occur as ARGth argument of FUNCTION.
     This is useful when such strings contain no format string
     directives: together with the checks done by `msgfmt -c' it will
     ensure that translators cannot accidentally use format string
     directives that would lead to a crash at runtime.
     The meaning of `--flag=FUNCTION:ARG:pass-LANG-format' is that in
     language LANG, if the FUNCTION call occurs in a position that must
     yield a format string, then its ARGth argument must yield a format
     string of the same type as well.  (If you know GCC function
     attributes, the `--flag=FUNCTION:ARG:pass-c-format' option is
     roughly equivalent to the declaration `__attribute__
     ((__format_arg__ (ARG)))' attached to FUNCTION in a C source file.)
     For example, if you use the `_' shortcut for the `gettext'
     function, you should use `--flag=_:1:pass-c-format'.  The effect
     of this specification is that `xgettext' will propagate a format
     string requirement for a `_("string")' call to its first argument,
     the literal `"string"', and thus mark it as a format string.  This
     is useful when such strings contain no format string directives:
     together with the checks done by `msgfmt -c' it will ensure that
     translators cannot accidentally use format string directives that
     would lead to a crash at runtime.
     This option has an effect with most languages, namely C, C++,
     ObjectiveC, Shell, Python, Lisp, EmacsLisp, librep, Scheme, Java,
     C#, awk, YCP, Tcl, Perl, PHP, GCC-source.

`-T'
`--trigraphs'
     Understand ANSI C trigraphs for input.
     This option has an effect only with the languages C, C++,
     ObjectiveC.

`--qt'
     Recognize Qt format strings.
     This option has an effect only with the language C++.

`--debug'
     Use the flags `c-format' and `possible-c-format' to show who was
     responsible for marking a message as a format string.  The latter
     form is used if the `xgettext' program decided, the format form is
     used if the programmer prescribed it.

     By default only the `c-format' form is used.  The translator should
     not have to care about these details.


   This implementation of `xgettext' is able to process a few awkward
cases, like strings in preprocessor macros, ANSI concatenation of
adjacent strings, and escaped end of lines for continued strings.

4.1.7 Output details
--------------------

`--force-po'
     Always write an output file even if no message is defined.

`-i'
`--indent'
     Write the .po file using indented style.

`--no-location'
     Do not write `#: FILENAME:LINE' lines.

`-n'
`--add-location'
     Generate `#: FILENAME:LINE' lines (default).

`--strict'
     Write out a strict Uniforum conforming PO file.  Note that this
     Uniforum format should be avoided because it doesn't support the
     GNU extensions.

`--properties-output'
     Write out a Java ResourceBundle in Java `.properties' syntax.  Note
     that this file format doesn't support plural forms and silently
     drops obsolete messages.

`--stringtable-output'
     Write out a NeXTstep/GNUstep localized resource file in `.strings'
     syntax.  Note that this file format doesn't support plural forms.

`-w NUMBER'
`--width=NUMBER'
     Set the output page width.  Long strings in the output files will
     be split across multiple lines in order to ensure that each line's
     width (= number of screen columns) is less or equal to the given
     NUMBER.

`--no-wrap'
     Do not break long message lines.  Message lines whose width
     exceeds the output page width will not be split into several
     lines.  Only file reference lines which are wider than the output
     page width will be split.

`-s'
`--sort-output'
     Generate sorted output.  Note that using this option makes it much
     harder for the translator to understand each message's context.

`-F'
`--sort-by-file'
     Sort output by file location.

`--omit-header'
     Don't write header with `msgid ""' entry.

     This is useful for testing purposes because it eliminates a source
     of variance for generated `.gmo' files.  With `--omit-header', two
     invocations of `xgettext' on the same files with the same options
     at different times are guaranteed to produce the same results.

`--copyright-holder=STRING'
     Set the copyright holder in the output.  STRING should be the
     copyright holder of the surrounding package.  (Note that the msgstr
     strings, extracted from the package's sources, belong to the
     copyright holder of the package.)  Translators are expected to
     transfer or disclaim the copyright for their translations, so that
     package maintainers can distribute them without legal risk.  If
     STRING is empty, the output files are marked as being in the
     public domain; in this case, the translators are expected to
     disclaim their copyright, again so that package maintainers can
     distribute them without legal risk.

     The default value for STRING is the Free Software Foundation, Inc.,
     simply because `xgettext' was first used in the GNU project.

`--foreign-user'
     Omit FSF copyright in output.  This option is equivalent to
     `--copyright-holder='''.  It can be useful for packages outside
     the GNU project that want their translations to be in the public
     domain.

`--msgid-bugs-address=EMAIL@ADDRESS'
     Set the reporting address for msgid bugs.  This is the email
     address or URL to which the translators shall report bugs in the
     untranslated strings:

        - Strings which are not entire sentences, see the maintainer
          guidelines in *Note Preparing Strings::.

        - Strings which use unclear terms or require additional context
          to be understood.

        - Strings which make invalid assumptions about notation of
          date, time or money.

        - Pluralisation problems.

        - Incorrect English spelling.

        - Incorrect formatting.

     It can be your email address, or a mailing list address where
     translators can write to without being subscribed, or the URL of a
     web page through which the translators can contact you.

     The default value is empty, which means that translators will be
     clueless!  Don't forget to specify this option.

`-m [STRING]'
`--msgstr-prefix[=STRING]'
     Use STRING (or "" if not specified) as prefix for msgstr entries.

`-M [STRING]'
`--msgstr-suffix[=STRING]'
     Use STRING (or "" if not specified) as suffix for msgstr entries.


4.1.8 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.



File: gettext.info,  Node: Creating,  Next: Updating,  Prev: Template,  Up: Top

5 Creating a New PO File
************************

When starting a new translation, the translator creates a file called
`LANG.po', as a copy of the `PACKAGE.pot' template file with
modifications in the initial comments (at the beginning of the file)
and in the header entry (the first entry, near the beginning of the
file).

   The easiest way to do so is by use of the `msginit' program.  For
example:

     $ cd PACKAGE-VERSION
     $ cd po
     $ msginit

   The alternative way is to do the copy and modifications by hand.  To
do so, the translator copies `PACKAGE.pot' to `LANG.po'.  Then she
modifies the initial comments and the header entry of this file.

* Menu:

* msginit Invocation::          Invoking the `msginit' Program
* Header Entry::                Filling in the Header Entry


File: gettext.info,  Node: msginit Invocation,  Next: Header Entry,  Prev: Creating,  Up: Creating

5.1 Invoking the `msginit' Program
==================================

     msginit [OPTION]

   The `msginit' program creates a new PO file, initializing the meta
information with values from the user's environment.

5.1.1 Input file location
-------------------------

`-i INPUTFILE'
`--input=INPUTFILE'
     Input POT file.


   If no INPUTFILE is given, the current directory is searched for the
POT file.  If it is `-', standard input is read.

5.1.2 Output file location
--------------------------

`-o FILE'
`--output-file=FILE'
     Write output to specified PO file.


   If no output file is given, it depends on the `--locale' option or
the user's locale setting.  If it is `-', the results are written to
standard output.

5.1.3 Input file syntax
-----------------------

`-P'
`--properties-input'
     Assume the input file is a Java ResourceBundle in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input file is a NeXTstep/GNUstep localized resource
     file in `.strings' syntax, not in PO file syntax.


5.1.4 Output details
--------------------

`-l LL_CC'
`--locale=LL_CC'
     Set target locale.  LL should be a language code, and CC should be
     a country code.  The command `locale -a' can be used to output a
     list of all installed locales.  The default is the user's locale
     setting.

`--no-translator'
     Declares that the PO file will not have a human translator and is
     instead automatically generated.

`-p'
`--properties-output'
     Write out a Java ResourceBundle in Java `.properties' syntax.  Note
     that this file format doesn't support plural forms and silently
     drops obsolete messages.

`--stringtable-output'
     Write out a NeXTstep/GNUstep localized resource file in `.strings'
     syntax.  Note that this file format doesn't support plural forms.

`-w NUMBER'
`--width=NUMBER'
     Set the output page width.  Long strings in the output files will
     be split across multiple lines in order to ensure that each line's
     width (= number of screen columns) is less or equal to the given
     NUMBER.

`--no-wrap'
     Do not break long message lines.  Message lines whose width
     exceeds the output page width will not be split into several
     lines.  Only file reference lines which are wider than the output
     page width will be split.


5.1.5 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.



File: gettext.info,  Node: Header Entry,  Prev: msginit Invocation,  Up: Creating

5.2 Filling in the Header Entry
===============================

The initial comments "SOME DESCRIPTIVE TITLE", "YEAR" and "FIRST AUTHOR
<EMAIL@ADDRESS>, YEAR" ought to be replaced by sensible information.
This can be done in any text editor; if Emacs is used and it switched
to PO mode automatically (because it has recognized the file's suffix),
you can disable it by typing `M-x fundamental-mode'.

   Modifying the header entry can already be done using PO mode: in
Emacs, type `M-x po-mode RET' and then `RET' again to start editing the
entry.  You should fill in the following fields.

Project-Id-Version
     This is the name and version of the package.

Report-Msgid-Bugs-To
     This has already been filled in by `xgettext'.  It contains an
     email address or URL where you can report bugs in the untranslated
     strings:

        - Strings which are not entire sentences, see the maintainer
          guidelines in *Note Preparing Strings::.

        - Strings which use unclear terms or require additional context
          to be understood.

        - Strings which make invalid assumptions about notation of
          date, time or money.

        - Pluralisation problems.

        - Incorrect English spelling.

        - Incorrect formatting.

POT-Creation-Date
     This has already been filled in by `xgettext'.

PO-Revision-Date
     You don't need to fill this in.  It will be filled by the Emacs PO
     mode when you save the file.

Last-Translator
     Fill in your name and email address (without double quotes).

Language-Team
     Fill in the English name of the language, and the email address or
     homepage URL of the language team you are part of.

     Before starting a translation, it is a good idea to get in touch
     with your translation team, not only to make sure you don't do
     duplicated work, but also to coordinate difficult linguistic
     issues.

     In the Free Translation Project, each translation team has its own
     mailing list.  The up-to-date list of teams can be found at the
     Free Translation Project's homepage,
     `http://www.iro.umontreal.ca/contrib/po/HTML/', in the "National
     teams" area.

Content-Type
     Replace `CHARSET' with the character encoding used for your
     language, in your locale, or UTF-8.  This field is needed for
     correct operation of the `msgmerge' and `msgfmt' programs, as well
     as for users whose locale's character encoding differs from yours
     (see *Note Charset conversion::).

     You get the character encoding of your locale by running the shell
     command `locale charmap'.  If the result is `C' or
     `ANSI_X3.4-1968', which is equivalent to `ASCII' (= `US-ASCII'),
     it means that your locale is not correctly configured.  In this
     case, ask your translation team which charset to use.  `ASCII' is
     not usable for any language except Latin.

     Because the PO files must be portable to operating systems with
     less advanced internationalization facilities, the character
     encodings that can be used are limited to those supported by both
     GNU `libc' and GNU `libiconv'.  These are: `ASCII', `ISO-8859-1',
     `ISO-8859-2', `ISO-8859-3', `ISO-8859-4', `ISO-8859-5',
     `ISO-8859-6', `ISO-8859-7', `ISO-8859-8', `ISO-8859-9',
     `ISO-8859-13', `ISO-8859-14', `ISO-8859-15', `KOI8-R', `KOI8-U',
     `KOI8-T', `CP850', `CP866', `CP874', `CP932', `CP949', `CP950',
     `CP1250', `CP1251', `CP1252', `CP1253', `CP1254', `CP1255',
     `CP1256', `CP1257', `GB2312', `EUC-JP', `EUC-KR', `EUC-TW',
     `BIG5', `BIG5-HKSCS', `GBK', `GB18030', `SHIFT_JIS', `JOHAB',
     `TIS-620', `VISCII', `GEORGIAN-PS', `UTF-8'.

     In the GNU system, the following encodings are frequently used for
     the corresponding languages.

        * `ISO-8859-1' for Afrikaans, Albanian, Basque, Breton,
          Catalan, Cornish, Danish, Dutch, English, Estonian, Faroese,
          Finnish, French, Galician, German, Greenlandic, Icelandic,
          Indonesian, Irish, Italian, Malay, Manx, Norwegian, Occitan,
          Portuguese, Spanish, Swedish, Tagalog, Uzbek, Walloon,

        * `ISO-8859-2' for Bosnian, Croatian, Czech, Hungarian, Polish,
          Romanian, Serbian, Slovak, Slovenian,

        * `ISO-8859-3' for Maltese,

        * `ISO-8859-5' for Macedonian, Serbian,

        * `ISO-8859-6' for Arabic,

        * `ISO-8859-7' for Greek,

        * `ISO-8859-8' for Hebrew,

        * `ISO-8859-9' for Turkish,

        * `ISO-8859-13' for Latvian, Lithuanian, Maori,

        * `ISO-8859-14' for Welsh,

        * `ISO-8859-15' for Basque, Catalan, Dutch, English, Finnish,
          French, Galician, German, Irish, Italian, Portuguese,
          Spanish, Swedish, Walloon,

        * `KOI8-R' for Russian,

        * `KOI8-U' for Ukrainian,

        * `KOI8-T' for Tajik,

        * `CP1251' for Bulgarian, Byelorussian,

        * `GB2312', `GBK', `GB18030' for simplified writing of Chinese,

        * `BIG5', `BIG5-HKSCS' for traditional writing of Chinese,

        * `EUC-JP' for Japanese,

        * `EUC-KR' for Korean,

        * `TIS-620' for Thai,

        * `GEORGIAN-PS' for Georgian,

        * `UTF-8' for any language, including those listed above.

     When single quote characters or double quote characters are used in
     translations for your language, and your locale's encoding is one
     of the ISO-8859-* charsets, it is best if you create your PO files
     in UTF-8 encoding, instead of your locale's encoding.  This is
     because in UTF-8 the real quote characters can be represented
     (single quote characters: U+2018, U+2019, double quote characters:
     U+201C, U+201D), whereas none of ISO-8859-* charsets has them all.
     Users in UTF-8 locales will see the real quote characters,
     whereas users in ISO-8859-* locales will see the vertical
     apostrophe and the vertical double quote instead (because that's
     what the character set conversion will transliterate them to).

     To enter such quote characters under X11, you can change your
     keyboard mapping using the `xmodmap' program.  The X11 names of
     the quote characters are "leftsinglequotemark",
     "rightsinglequotemark", "leftdoublequotemark",
     "rightdoublequotemark", "singlelowquotemark", "doublelowquotemark".

     Note that only recent versions of GNU Emacs support the UTF-8
     encoding: Emacs 20 with Mule-UCS, and Emacs 21.  As of January
     2001, XEmacs doesn't support the UTF-8 encoding.

     The character encoding name can be written in either upper or
     lower case.  Usually upper case is preferred.

Content-Transfer-Encoding
     Set this to `8bit'.

Plural-Forms
     This field is optional.  It is only needed if the PO file has
     plural forms.  You can find them by searching for the
     `msgid_plural' keyword.  The format of the plural forms field is
     described in *Note Plural forms::.


File: gettext.info,  Node: Updating,  Next: Manipulating,  Prev: Creating,  Up: Top

6 Updating Existing PO Files
****************************

* Menu:

* msgmerge Invocation::         Invoking the `msgmerge' Program
* Translated Entries::          Translated Entries
* Fuzzy Entries::               Fuzzy Entries
* Untranslated Entries::        Untranslated Entries
* Obsolete Entries::            Obsolete Entries
* Modifying Translations::      Modifying Translations
* Modifying Comments::          Modifying Comments
* Subedit::                     Mode for Editing Translations
* C Sources Context::           C Sources Context
* Auxiliary::                   Consulting Auxiliary PO Files
* Compendium::                  Using Translation Compendia


File: gettext.info,  Node: msgmerge Invocation,  Next: Translated Entries,  Prev: Updating,  Up: Updating

6.1 Invoking the `msgmerge' Program
===================================

     msgmerge [OPTION] DEF.po REF.pot

   The `msgmerge' program merges two Uniforum style .po files together.
The DEF.po file is an existing PO file with translations which will be
taken over to the newly created file as long as they still match;
comments will be preserved, but extracted comments and file positions
will be discarded.  The REF.pot file is the last created PO file with
up-to-date source references but old translations, or a PO Template file
(generally created by `xgettext'); any translations or comments in the
file will be discarded, however dot comments and file positions will be
preserved.  Where an exact match cannot be found, fuzzy matching is
used to produce better results.

6.1.1 Input file location
-------------------------

`DEF.po'
     Translations referring to old sources.

`REF.pot'
     References to the new sources.

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.  The resulting `.po'
     file will be written relative to the current directory, though.

`-C FILE'
`--compendium=FILE'
     Specify an additional library of message translations.  *Note
     Compendium::.  This option may be specified more than once.


6.1.2 Operation mode
--------------------

`-U'
`--update'
     Update DEF.po.  Do nothing if DEF.po is already up to date.


6.1.3 Output file location
--------------------------

`-o FILE'
`--output-file=FILE'
     Write output to specified file.


   The results are written to standard output if no output file is
specified or if it is `-'.

6.1.4 Output file location in update mode
-----------------------------------------

The result is written back to DEF.po.

`--backup=CONTROL'
     Make a backup of DEF.po

`--suffix=SUFFIX'
     Override the usual backup suffix.


   The version control method may be selected via the `--backup' option
or through the `VERSION_CONTROL' environment variable.  Here are the
values:

`none'
`off'
     Never make backups (even if `--backup' is given).

`numbered'
`t'
     Make numbered backups.

`existing'
`nil'
     Make numbered backups if numbered backups for this file already
     exist, otherwise make simple backups.

`simple'
`never'
     Always make simple backups.


   The backup suffix is `~', unless set with `--suffix' or the
`SIMPLE_BACKUP_SUFFIX' environment variable.

6.1.5 Operation modifiers
-------------------------

`-m'
`--multi-domain'
     Apply REF.pot to each of the domains in DEF.po.

`-N'
`--no-fuzzy-matching'
     Do not use fuzzy matching when an exact match is not found.  This
     may speed up the operation considerably.

6.1.6 Input file syntax
-----------------------

`-P'
`--properties-input'
     Assume the input files are Java ResourceBundles in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input files are NeXTstep/GNUstep localized resource
     files in `.strings' syntax, not in PO file syntax.


6.1.7 Output details
--------------------

`--force-po'
     Always write an output file even if it contains no message.

`-i'
`--indent'
     Write the .po file using indented style.

`--no-location'
     Do not write `#: FILENAME:LINE' lines.

`--add-location'
     Generate `#: FILENAME:LINE' lines (default).

`--strict'
     Write out a strict Uniforum conforming PO file.  Note that this
     Uniforum format should be avoided because it doesn't support the
     GNU extensions.

`-p'
`--properties-output'
     Write out a Java ResourceBundle in Java `.properties' syntax.  Note
     that this file format doesn't support plural forms and silently
     drops obsolete messages.

`--stringtable-output'
     Write out a NeXTstep/GNUstep localized resource file in `.strings'
     syntax.  Note that this file format doesn't support plural forms.

`-w NUMBER'
`--width=NUMBER'
     Set the output page width.  Long strings in the output files will
     be split across multiple lines in order to ensure that each line's
     width (= number of screen columns) is less or equal to the given
     NUMBER.

`--no-wrap'
     Do not break long message lines.  Message lines whose width
     exceeds the output page width will not be split into several
     lines.  Only file reference lines which are wider than the output
     page width will be split.

`-s'
`--sort-output'
     Generate sorted output.  Note that using this option makes it much
     harder for the translator to understand each message's context.

`-F'
`--sort-by-file'
     Sort output by file location.


6.1.8 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.

`-v'
`--verbose'
     Increase verbosity level.

`-q'
`--quiet'
`--silent'
     Suppress progress indicators.



File: gettext.info,  Node: Translated Entries,  Next: Fuzzy Entries,  Prev: msgmerge Invocation,  Up: Updating

6.2 Translated Entries
======================

Each PO file entry for which the `msgstr' field has been filled with a
translation, and which is not marked as fuzzy (*note Fuzzy Entries::),
is said to be a "translated" entry.  Only translated entries will later
be compiled by GNU `msgfmt' and become usable in programs.  Other entry
types will be excluded; translation will not occur for them.

   Some commands are more specifically related to translated entry
processing.

`t'
     Find the next translated entry (`po-next-translated-entry').

`T'
     Find the previous translated entry
     (`po-previous-translated-entry').


   The commands `t' (`po-next-translated-entry') and `T'
(`po-previous-translated-entry') move forwards or backwards, chasing
for an translated entry.  If none is found, the search is extended and
wraps around in the PO file buffer.

   Translated entries usually result from the translator having edited
in a translation for them, *Note Modifying Translations::.  However, if
the variable `po-auto-fuzzy-on-edit' is not `nil', the entry having
received a new translation first becomes a fuzzy entry, which ought to
be later unfuzzied before becoming an official, genuine translated
entry.  *Note Fuzzy Entries::.


File: gettext.info,  Node: Fuzzy Entries,  Next: Untranslated Entries,  Prev: Translated Entries,  Up: Updating

6.3 Fuzzy Entries
=================

Each PO file entry may have a set of "attributes", which are qualities
given a name and explicitly associated with the translation, using a
special system comment.  One of these attributes has the name `fuzzy',
and entries having this attribute are said to have a fuzzy translation.
They are called fuzzy entries, for short.

   Fuzzy entries, even if they account for translated entries for most
other purposes, usually call for revision by the translator.  Those may
be produced by applying the program `msgmerge' to update an older
translated PO files according to a new PO template file, when this tool
hypothesises that some new `msgid' has been modified only slightly out
of an older one, and chooses to pair what it thinks to be the old
translation for the new modified entry.  The slight alteration in the
original string (the `msgid' string) should often be reflected in the
translated string, and this requires the intervention of the
translator.  For this reason, `msgmerge' might mark some entries as
being fuzzy.

   Also, the translator may decide herself to mark an entry as fuzzy
for her own convenience, when she wants to remember that the entry has
to be later revisited.  So, some commands are more specifically related
to fuzzy entry processing.

`z'
     Find the next fuzzy entry (`po-next-fuzzy-entry').

`Z'
     Find the previous fuzzy entry (`po-previous-fuzzy-entry').

`<TAB>'
     Remove the fuzzy attribute of the current entry (`po-unfuzzy').


   The commands `z' (`po-next-fuzzy-entry') and `Z'
(`po-previous-fuzzy-entry') move forwards or backwards, chasing for a
fuzzy entry.  If none is found, the search is extended and wraps around
in the PO file buffer.

   The command `<TAB>' (`po-unfuzzy') removes the fuzzy attribute
associated with an entry, usually leaving it translated.  Further, if
the variable `po-auto-select-on-unfuzzy' has not the `nil' value, the
`<TAB>' command will automatically chase for another interesting entry
to work on.  The initial value of `po-auto-select-on-unfuzzy' is `nil'.

   The initial value of `po-auto-fuzzy-on-edit' is `nil'.  However, if
the variable `po-auto-fuzzy-on-edit' is set to `t', any entry edited
through the `<RET>' command is marked fuzzy, as a way to ensure some
kind of double check, later.  In this case, the usual paradigm is that
an entry becomes fuzzy (if not already) whenever the translator
modifies it.  If she is satisfied with the translation, she then uses
`<TAB>' to pick another entry to work on, clearing the fuzzy attribute
on the same blow.  If she is not satisfied yet, she merely uses `<SPC>'
to chase another entry, leaving the entry fuzzy.

   The translator may also use the `<DEL>' command
(`po-fade-out-entry') over any translated entry to mark it as being
fuzzy, when she wants to easily leave a trace she wants to later return
working at this entry.

   Also, when time comes to quit working on a PO file buffer with the
`q' command, the translator is asked for confirmation, if fuzzy string
still exists.


File: gettext.info,  Node: Untranslated Entries,  Next: Obsolete Entries,  Prev: Fuzzy Entries,  Up: Updating

6.4 Untranslated Entries
========================

When `xgettext' originally creates a PO file, unless told otherwise, it
initializes the `msgid' field with the untranslated string, and leaves
the `msgstr' string to be empty.  Such entries, having an empty
translation, are said to be "untranslated" entries.  Later, when the
programmer slightly modifies some string right in the program, this
change is later reflected in the PO file by the appearance of a new
untranslated entry for the modified string.

   The usual commands moving from entry to entry consider untranslated
entries on the same level as active entries.  Untranslated entries are
easily recognizable by the fact they end with `msgstr ""'.

   The work of the translator might be (quite naively) seen as the
process of seeking for an untranslated entry, editing a translation for
it, and repeating these actions until no untranslated entries remain.
Some commands are more specifically related to untranslated entry
processing.

`u'
     Find the next untranslated entry (`po-next-untranslated-entry').

`U'
     Find the previous untranslated entry
     (`po-previous-untransted-entry').

`k'
     Turn the current entry into an untranslated one (`po-kill-msgstr').


   The commands `u' (`po-next-untranslated-entry') and `U'
(`po-previous-untransted-entry') move forwards or backwards, chasing
for an untranslated entry.  If none is found, the search is extended
and wraps around in the PO file buffer.

   An entry can be turned back into an untranslated entry by merely
emptying its translation, using the command `k' (`po-kill-msgstr').
*Note Modifying Translations::.

   Also, when time comes to quit working on a PO file buffer with the
`q' command, the translator is asked for confirmation, if some
untranslated string still exists.


File: gettext.info,  Node: Obsolete Entries,  Next: Modifying Translations,  Prev: Untranslated Entries,  Up: Updating

6.5 Obsolete Entries
====================

By "obsolete" PO file entries, we mean those entries which are
commented out, usually by `msgmerge' when it found that the translation
is not needed anymore by the package being localized.

   The usual commands moving from entry to entry consider obsolete
entries on the same level as active entries.  Obsolete entries are
easily recognizable by the fact that all their lines start with `#',
even those lines containing `msgid' or `msgstr'.

   Commands exist for emptying the translation or reinitializing it to
the original untranslated string.  Commands interfacing with the kill
ring may force some previously saved text into the translation.  The
user may interactively edit the translation.  All these commands may
apply to obsolete entries, carefully leaving the entry obsolete after
the fact.

   Moreover, some commands are more specifically related to obsolete
entry processing.

`o'
     Find the next obsolete entry (`po-next-obsolete-entry').

`O'
     Find the previous obsolete entry (`po-previous-obsolete-entry').

`<DEL>'
     Make an active entry obsolete, or zap out an obsolete entry
     (`po-fade-out-entry').


   The commands `o' (`po-next-obsolete-entry') and `O'
(`po-previous-obsolete-entry') move forwards or backwards, chasing for
an obsolete entry.  If none is found, the search is extended and wraps
around in the PO file buffer.

   PO mode does not provide ways for un-commenting an obsolete entry
and making it active, because this would reintroduce an original
untranslated string which does not correspond to any marked string in
the program sources.  This goes with the philosophy of never
introducing useless `msgid' values.

   However, it is possible to comment out an active entry, so making it
obsolete.  GNU `gettext' utilities will later react to the
disappearance of a translation by using the untranslated string.  The
command `<DEL>' (`po-fade-out-entry') pushes the current entry a little
further towards annihilation.  If the entry is active (it is a
translated entry), then it is first made fuzzy.  If it is already fuzzy,
then the entry is merely commented out, with confirmation.  If the entry
is already obsolete, then it is completely deleted from the PO file.
It is easy to recycle the translation so deleted into some other PO file
entry, usually one which is untranslated.  *Note Modifying
Translations::.

   Here is a quite interesting problem to solve for later development of
PO mode, for those nights you are not sleepy.  The idea would be that
PO mode might become bright enough, one of these days, to make good
guesses at retrieving the most probable candidate, among all obsolete
entries, for initializing the translation of a newly appeared string.
I think it might be a quite hard problem to do this algorithmically, as
we have to develop good and efficient measures of string similarity.
Right now, PO mode completely lets the decision to the translator, when
the time comes to find the adequate obsolete translation, it merely
tries to provide handy tools for helping her to do so.


File: gettext.info,  Node: Modifying Translations,  Next: Modifying Comments,  Prev: Obsolete Entries,  Up: Updating

6.6 Modifying Translations
==========================

PO mode prevents direct modification of the PO file, by the usual means
Emacs gives for altering a buffer's contents.  By doing so, it pretends
helping the translator to avoid little clerical errors about the
overall file format, or the proper quoting of strings, as those errors
would be easily made.  Other kinds of errors are still possible, but
some may be caught and diagnosed by the batch validation process, which
the translator may always trigger by the `V' command.  For all other
errors, the translator has to rely on her own judgment, and also on the
linguistic reports submitted to her by the users of the translated
package, having the same mother tongue.

   When the time comes to create a translation, correct an error
diagnosed mechanically or reported by a user, the translators have to
resort to using the following commands for modifying the translations.

`<RET>'
     Interactively edit the translation (`po-edit-msgstr').

`<LFD>'
`C-j'
     Reinitialize the translation with the original, untranslated string
     (`po-msgid-to-msgstr').

`k'
     Save the translation on the kill ring, and delete it
     (`po-kill-msgstr').

`w'
     Save the translation on the kill ring, without deleting it
     (`po-kill-ring-save-msgstr').

`y'
     Replace the translation, taking the new from the kill ring
     (`po-yank-msgstr').


   The command `<RET>' (`po-edit-msgstr') opens a new Emacs window
meant to edit in a new translation, or to modify an already existing
translation.  The new window contains a copy of the translation taken
from the current PO file entry, all ready for edition, expunged of all
quoting marks, fully modifiable and with the complete extent of Emacs
modifying commands.  When the translator is done with her
modifications, she may use `C-c C-c' to close the subedit window with
the automatically requoted results, or `C-c C-k' to abort her
modifications.  *Note Subedit::, for more information.

   The command `<LFD>' (`po-msgid-to-msgstr') initializes, or
reinitializes the translation with the original string.  This command is
normally used when the translator wants to redo a fresh translation of
the original string, disregarding any previous work.

   It is possible to arrange so, whenever editing an untranslated
entry, the `<LFD>' command be automatically executed.  If you set
`po-auto-edit-with-msgid' to `t', the translation gets initialised with
the original string, in case none exists already.  The default value
for `po-auto-edit-with-msgid' is `nil'.

   In fact, whether it is best to start a translation with an empty
string, or rather with a copy of the original string, is a matter of
taste or habit.  Sometimes, the source language and the target language
are so different that is simply best to start writing on an empty page.
At other times, the source and target languages are so close that it
would be a waste to retype a number of words already being written in
the original string.  A translator may also like having the original
string right under her eyes, as she will progressively overwrite the
original text with the translation, even if this requires some extra
editing work to get rid of the original.

   The command `k' (`po-kill-msgstr') merely empties the translation
string, so turning the entry into an untranslated one.  But while doing
so, its previous contents is put apart in a special place, known as the
kill ring.  The command `w' (`po-kill-ring-save-msgstr') has also the
effect of taking a copy of the translation onto the kill ring, but it
otherwise leaves the entry alone, and does _not_ remove the translation
from the entry.  Both commands use exactly the Emacs kill ring, which
is shared between buffers, and which is well known already to Emacs
lovers.

   The translator may use `k' or `w' many times in the course of her
work, as the kill ring may hold several saved translations.  From the
kill ring, strings may later be reinserted in various Emacs buffers.
In particular, the kill ring may be used for moving translation strings
between different entries of a single PO file buffer, or if the
translator is handling many such buffers at once, even between PO files.

   To facilitate exchanges with buffers which are not in PO mode, the
translation string put on the kill ring by the `k' command is fully
unquoted before being saved: external quotes are removed, multi-line
strings are concatenated, and backslash escaped sequences are turned
into their corresponding characters.  In the special case of obsolete
entries, the translation is also uncommented prior to saving.

   The command `y' (`po-yank-msgstr') completely replaces the
translation of the current entry by a string taken from the kill ring.
Following Emacs terminology, we then say that the replacement string is
"yanked" into the PO file buffer.  *Note Yanking: (emacs)Yanking.  The
first time `y' is used, the translation receives the value of the most
recent addition to the kill ring.  If `y' is typed once again,
immediately, without intervening keystrokes, the translation just
inserted is taken away and replaced by the second most recent addition
to the kill ring.  By repeating `y' many times in a row, the translator
may travel along the kill ring for saved strings, until she finds the
string she really wanted.

   When a string is yanked into a PO file entry, it is fully and
automatically requoted for complying with the format PO files should
have.  Further, if the entry is obsolete, PO mode then appropriately
push the inserted string inside comments.  Once again, translators
should not burden themselves with quoting considerations besides, of
course, the necessity of the translated string itself respective to the
program using it.

   Note that `k' or `w' are not the only commands pushing strings on
the kill ring, as almost any PO mode command replacing translation
strings (or the translator comments) automatically saves the old string
on the kill ring.  The main exceptions to this general rule are the
yanking commands themselves.

   To better illustrate the operation of killing and yanking, let's use
an actual example, taken from a common situation.  When the programmer
slightly modifies some string right in the program, his change is later
reflected in the PO file by the appearance of a new untranslated entry
for the modified string, and the fact that the entry translating the
original or unmodified string becomes obsolete.  In many cases, the
translator might spare herself some work by retrieving the unmodified
translation from the obsolete entry, then initializing the untranslated
entry `msgstr' field with this retrieved translation.  Once this done,
the obsolete entry is not wanted anymore, and may be safely deleted.

   When the translator finds an untranslated entry and suspects that a
slight variant of the translation exists, she immediately uses `m' to
mark the current entry location, then starts chasing obsolete entries
with `o', hoping to find some translation corresponding to the
unmodified string.  Once found, she uses the `<DEL>' command for
deleting the obsolete entry, knowing that `<DEL>' also _kills_ the
translation, that is, pushes the translation on the kill ring.  Then,
`r' returns to the initial untranslated entry, and `y' then _yanks_ the
saved translation right into the `msgstr' field.  The translator is
then free to use `<RET>' for fine tuning the translation contents, and
maybe to later use `u', then `m' again, for going on with the next
untranslated string.

   When some sequence of keys has to be typed over and over again, the
translator may find it useful to become better acquainted with the Emacs
capability of learning these sequences and playing them back under
request.  *Note Keyboard Macros: (emacs)Keyboard Macros.


File: gettext.info,  Node: Modifying Comments,  Next: Subedit,  Prev: Modifying Translations,  Up: Updating

6.7 Modifying Comments
======================

Any translation work done seriously will raise many linguistic
difficulties, for which decisions have to be made, and the choices
further documented.  These documents may be saved within the PO file in
form of translator comments, which the translator is free to create,
delete, or modify at will.  These comments may be useful to herself
when she returns to this PO file after a while.

   Comments not having whitespace after the initial `#', for example,
those beginning with `#.' or `#:', are _not_ translator comments, they
are exclusively created by other `gettext' tools.  So, the commands
below will never alter such system added comments, they are not meant
for the translator to modify.  *Note PO Files::.

   The following commands are somewhat similar to those modifying
translations, so the general indications given for those apply here.
*Note Modifying Translations::.

`#'
     Interactively edit the translator comments (`po-edit-comment').

`K'
     Save the translator comments on the kill ring, and delete it
     (`po-kill-comment').

`W'
     Save the translator comments on the kill ring, without deleting it
     (`po-kill-ring-save-comment').

`Y'
     Replace the translator comments, taking the new from the kill ring
     (`po-yank-comment').


   These commands parallel PO mode commands for modifying the
translation strings, and behave much the same way as they do, except
that they handle this part of PO file comments meant for translator
usage, rather than the translation strings.  So, if the descriptions
given below are slightly succinct, it is because the full details have
already been given.  *Note Modifying Translations::.

   The command `#' (`po-edit-comment') opens a new Emacs window
containing a copy of the translator comments on the current PO file
entry.  If there are no such comments, PO mode understands that the
translator wants to add a comment to the entry, and she is presented
with an empty screen.  Comment marks (`#') and the space following them
are automatically removed before edition, and reinstated after.  For
translator comments pertaining to obsolete entries, the uncommenting
and recommenting operations are done twice.  Once in the editing
window, the keys `C-c C-c' allow the translator to tell she is finished
with editing the comment.  *Note Subedit::, for further details.

   Functions found on `po-subedit-mode-hook', if any, are executed after
the string has been inserted in the edit buffer.

   The command `K' (`po-kill-comment') gets rid of all translator
comments, while saving those comments on the kill ring.  The command
`W' (`po-kill-ring-save-comment') takes a copy of the translator
comments on the kill ring, but leaves them undisturbed in the current
entry.  The command `Y' (`po-yank-comment') completely replaces the
translator comments by a string taken at the front of the kill ring.
When this command is immediately repeated, the comments just inserted
are withdrawn, and replaced by other strings taken along the kill ring.

   On the kill ring, all strings have the same nature.  There is no
distinction between _translation_ strings and _translator comments_
strings.  So, for example, let's presume the translator has just
finished editing a translation, and wants to create a new translator
comment to document why the previous translation was not good, just to
remember what was the problem.  Foreseeing that she will do that in her
documentation, the translator may want to quote the previous
translation in her translator comments.  To do so, she may initialize
the translator comments with the previous translation, still at the
head of the kill ring.  Because editing already pushed the previous
translation on the kill ring, she merely has to type `M-w' prior to
`#', and the previous translation will be right there, all ready for
being introduced by some explanatory text.

   On the other hand, presume there are some translator comments already
and that the translator wants to add to those comments, instead of
wholly replacing them.  Then, she should edit the comment right away
with `#'.  Once inside the editing window, she can use the regular
Emacs commands `C-y' (`yank') and `M-y' (`yank-pop') to get the
previous translation where she likes.


File: gettext.info,  Node: Subedit,  Next: C Sources Context,  Prev: Modifying Comments,  Up: Updating

6.8 Details of Sub Edition
==========================

The PO subedit minor mode has a few peculiarities worth being described
in fuller detail.  It installs a few commands over the usual editing set
of Emacs, which are described below.

`C-c C-c'
     Complete edition (`po-subedit-exit').

`C-c C-k'
     Abort edition (`po-subedit-abort').

`C-c C-a'
     Consult auxiliary PO files (`po-subedit-cycle-auxiliary').


   The window's contents represents a translation for a given message,
or a translator comment.  The translator may modify this window to her
heart's content.  Once this is done, the command `C-c C-c'
(`po-subedit-exit') may be used to return the edited translation into
the PO file, replacing the original translation, even if it moved out of
sight or if buffers were switched.

   If the translator becomes unsatisfied with her translation or
comment, to the extent she prefers keeping what was existent prior to
the `<RET>' or `#' command, she may use the command `C-c C-k'
(`po-subedit-abort') to merely get rid of edition, while preserving the
original translation or comment.  Another way would be for her to exit
normally with `C-c C-c', then type `U' once for undoing the whole
effect of last edition.

   The command `C-c C-a' (`po-subedit-cycle-auxiliary') allows for
glancing through translations already achieved in other languages,
directly while editing the current translation.  This may be quite
convenient when the translator is fluent at many languages, but of
course, only makes sense when such completed auxiliary PO files are
already available to her (*note Auxiliary::).

   Functions found on `po-subedit-mode-hook', if any, are executed after
the string has been inserted in the edit buffer.

   While editing her translation, the translator should pay attention
to not inserting unwanted `<RET>' (newline) characters at the end of
the translated string if those are not meant to be there, or to removing
such characters when they are required.  Since these characters are not
visible in the editing buffer, they are easily introduced by mistake.
To help her, `<RET>' automatically puts the character `<' at the end of
the string being edited, but this `<' is not really part of the string.
On exiting the editing window with `C-c C-c', PO mode automatically
removes such `<' and all whitespace added after it.  If the translator
adds characters after the terminating `<', it looses its delimiting
property and integrally becomes part of the string.  If she removes the
delimiting `<', then the edited string is taken _as is_, with all
trailing newlines, even if invisible.  Also, if the translated string
ought to end itself with a genuine `<', then the delimiting `<' may not
be removed; so the string should appear, in the editing window, as
ending with two `<' in a row.

   When a translation (or a comment) is being edited, the translator
may move the cursor back into the PO file buffer and freely move to
other entries, browsing at will.  If, with an edition pending, the
translator wanders in the PO file buffer, she may decide to start
modifying another entry.  Each entry being edited has its own subedit
buffer.  It is possible to simultaneously edit the translation _and_
the comment of a single entry, or to edit entries in different PO
files, all at once.  Typing `<RET>' on a field already being edited
merely resumes that particular edit.  Yet, the translator should better
be comfortable at handling many Emacs windows!

   Pending subedits may be completed or aborted in any order, regardless
of how or when they were started.  When many subedits are pending and
the translator asks for quitting the PO file (with the `q' command),
subedits are automatically resumed one at a time, so she may decide for
each of them.


File: gettext.info,  Node: C Sources Context,  Next: Auxiliary,  Prev: Subedit,  Up: Updating

6.9 C Sources Context
=====================

PO mode is particularly powerful when used with PO files created
through GNU `gettext' utilities, as those utilities insert special
comments in the PO files they generate.  Some of these special comments
relate the PO file entry to exactly where the untranslated string
appears in the program sources.

   When the translator gets to an untranslated entry, she is fairly
often faced with an original string which is not as informative as it
normally should be, being succinct, cryptic, or otherwise ambiguous.
Before choosing how to translate the string, she needs to understand
better what the string really means and how tight the translation has
to be.  Most of the time, when problems arise, the only way left to make
her judgment is looking at the true program sources from where this
string originated, searching for surrounding comments the programmer
might have put in there, and looking around for helping clues of _any_
kind.

   Surely, when looking at program sources, the translator will receive
more help if she is a fluent programmer.  However, even if she is not
versed in programming and feels a little lost in C code, the translator
should not be shy at taking a look, once in a while.  It is most
probable that she will still be able to find some of the hints she
needs.  She will learn quickly to not feel uncomfortable in program
code, paying more attention to programmer's comments, variable and
function names (if he dared choosing them well), and overall
organization, than to the program code itself.

   The following commands are meant to help the translator at getting
program source context for a PO file entry.

`s'
     Resume the display of a program source context, or cycle through
     them (`po-cycle-source-reference').

`M-s'
     Display of a program source context selected by menu
     (`po-select-source-reference').

`S'
     Add a directory to the search path for source files
     (`po-consider-source-path').

`M-S'
     Delete a directory from the search path for source files
     (`po-ignore-source-path').


   The commands `s' (`po-cycle-source-reference') and `M-s'
(`po-select-source-reference') both open another window displaying some
source program file, and already positioned in such a way that it shows
an actual use of the string to be translated.  By doing so, the command
gives source program context for the string.  But if the entry has no
source context references, or if all references are unresolved along
the search path for program sources, then the command diagnoses this as
an error.

   Even if `s' (or `M-s') opens a new window, the cursor stays in the
PO file window.  If the translator really wants to get into the program
source window, she ought to do it explicitly, maybe by using command
`O'.

   When `s' is typed for the first time, or for a PO file entry which
is different of the last one used for getting source context, then the
command reacts by giving the first context available for this entry, if
any.  If some context has already been recently displayed for the
current PO file entry, and the translator wandered off to do other
things, typing `s' again will merely resume, in another window, the
context last displayed.  In particular, if the translator moved the
cursor away from the context in the source file, the command will bring
the cursor back to the context.  By using `s' many times in a row, with
no other commands intervening, PO mode will cycle to the next available
contexts for this particular entry, getting back to the first context
once the last has been shown.

   The command `M-s' behaves differently.  Instead of cycling through
references, it lets the translator choose a particular reference among
many, and displays that reference.  It is best used with completion, if
the translator types `<TAB>' immediately after `M-s', in response to
the question, she will be offered a menu of all possible references, as
a reminder of which are the acceptable answers.  This command is useful
only where there are really many contexts available for a single string
to translate.

   Program source files are usually found relative to where the PO file
stands.  As a special provision, when this fails, the file is also
looked for, but relative to the directory immediately above it.  Those
two cases take proper care of most PO files.  However, it might happen
that a PO file has been moved, or is edited in a different place than
its normal location.  When this happens, the translator should tell PO
mode in which directory normally sits the genuine PO file.  Many such
directories may be specified, and all together, they constitute what is
called the "search path" for program sources.  The command `S'
(`po-consider-source-path') is used to interactively enter a new
directory at the front of the search path, and the command `M-S'
(`po-ignore-source-path') is used to select, with completion, one of
the directories she does not want anymore on the search path.


File: gettext.info,  Node: Auxiliary,  Next: Compendium,  Prev: C Sources Context,  Up: Updating

6.10 Consulting Auxiliary PO Files
==================================

PO mode is able to help the knowledgeable translator, being fluent in
many languages, at taking advantage of translations already achieved in
other languages she just happens to know.  It provides these other
language translations as additional context for her own work.  Moreover,
it has features to ease the production of translations for many
languages at once, for translators preferring to work in this way.

   An "auxiliary" PO file is an existing PO file meant for the same
package the translator is working on, but targeted to a different mother
tongue language.  Commands exist for declaring and handling auxiliary
PO files, and also for showing contexts for the entry under work.

   Here are the auxiliary file commands available in PO mode.

`a'
     Seek auxiliary files for another translation for the same entry
     (`po-cycle-auxiliary').

`C-c C-a'
     Switch to a particular auxiliary file (`po-select-auxiliary').

`A'
     Declare this PO file as an auxiliary file
     (`po-consider-as-auxiliary').

`M-A'
     Remove this PO file from the list of auxiliary files
     (`po-ignore-as-auxiliary').


   Command `A' (`po-consider-as-auxiliary') adds the current PO file to
the list of auxiliary files, while command `M-A'
(`po-ignore-as-auxiliary' just removes it.

   The command `a' (`po-cycle-auxiliary') seeks all auxiliary PO files,
round-robin, searching for a translated entry in some other language
having an `msgid' field identical as the one for the current entry.
The found PO file, if any, takes the place of the current PO file in
the display (its window gets on top).  Before doing so, the current PO
file is also made into an auxiliary file, if not already.  So, `a' in
this newly displayed PO file will seek another PO file, and so on, so
repeating `a' will eventually yield back the original PO file.

   The command `C-c C-a' (`po-select-auxiliary') asks the translator
for her choice of a particular auxiliary file, with completion, and
then switches to that selected PO file.  The command also checks if the
selected file has an `msgid' field identical as the one for the current
entry, and if yes, this entry becomes current.  Otherwise, the cursor
of the selected file is left undisturbed.

   For all this to work fully, auxiliary PO files will have to be
normalized, in that way that `msgid' fields should be written _exactly_
the same way.  It is possible to write `msgid' fields in various ways
for representing the same string, different writing would break the
proper behaviour of the auxiliary file commands of PO mode.  This is not
expected to be much a problem in practice, as most existing PO files
have their `msgid' entries written by the same GNU `gettext' tools.

   However, PO files initially created by PO mode itself, while marking
strings in source files, are normalised differently.  So are PO files
resulting of the the `M-x normalize' command.  Until these
discrepancies between PO mode and other GNU `gettext' tools get fully
resolved, the translator should stay aware of normalisation issues.


File: gettext.info,  Node: Compendium,  Prev: Auxiliary,  Up: Updating

6.11 Using Translation Compendia
================================

A "compendium" is a special PO file containing a set of translations
recurring in many different packages.  The translator can use gettext
tools to build a new compendium, to add entries to her compendium, and
to initialize untranslated entries, or to update already translated
entries, from translations kept in the compendium.

* Menu:

* Creating Compendia::          Merging translations for later use
* Using Compendia::             Using older translations if they fit


File: gettext.info,  Node: Creating Compendia,  Next: Using Compendia,  Prev: Compendium,  Up: Compendium

6.11.1 Creating Compendia
-------------------------

Basically every PO file consisting of translated entries only can be
declared as a valid compendium.  Often the translator wants to have
special compendia; let's consider two cases: `concatenating PO files'
and `extracting a message subset from a PO file'.

6.11.1.1 Concatenate PO Files
.............................

To concatenate several valid PO files into one compendium file you can
use `msgcomm' or `msgcat' (the latter preferred):

     msgcat -o compendium.po file1.po file2.po

   By default, `msgcat' will accumulate divergent translations for the
same string.  Those occurences will be marked as `fuzzy' and highly
visible decorated; calling `msgcat' on `file1.po':

     #: src/hello.c:200
     #, c-format
     msgid "Report bugs to <%s>.\n"
     msgstr "Comunicar `bugs' a <%s>.\n"

and `file2.po':

     #: src/bye.c:100
     #, c-format
     msgid "Report bugs to <%s>.\n"
     msgstr "Comunicar \"bugs\" a <%s>.\n"

will result in:

     #: src/hello.c:200 src/bye.c:100
     #, fuzzy, c-format
     msgid "Report bugs to <%s>.\n"
     msgstr ""
     "#-#-#-#-#  file1.po  #-#-#-#-#\n"
     "Comunicar `bugs' a <%s>.\n"
     "#-#-#-#-#  file2.po  #-#-#-#-#\n"
     "Comunicar \"bugs\" a <%s>.\n"

The translator will have to resolve this "conflict" manually; she has
to decide whether the first or the second version is appropriate (or
provide a new translation), to delete the "marker lines", and finally
to remove the `fuzzy' mark.

   If the translator knows in advance the first found translation of a
message is always the best translation she can make use to the
`--use-first' switch:

     msgcat --use-first -o compendium.po file1.po file2.po

   A good compendium file must not contain `fuzzy' or untranslated
entries.  If input files are "dirty" you must preprocess the input
files or postprocess the result using `msgattrib --translated
--no-fuzzy'.

6.11.1.2 Extract a Message Subset from a PO File
................................................

Nobody wants to translate the same messages again and again; thus you
may wish to have a compendium file containing `getopt.c' messages.

   To extract a message subset (e.g., all `getopt.c' messages) from an
existing PO file into one compendium file you can use `msggrep':

     msggrep --location src/getopt.c -o compendium.po file.po


File: gettext.info,  Node: Using Compendia,  Prev: Creating Compendia,  Up: Compendium

6.11.2 Using Compendia
----------------------

You can use a compendium file to initialize a translation from scratch
or to update an already existing translation.

6.11.2.1 Initialize a New Translation File
..........................................

Since a PO file with translations does not exist the translator can
merely use `/dev/null' to fake the "old" translation file.

     msgmerge --compendium compendium.po -o file.po /dev/null file.pot

6.11.2.2 Update an Existing Translation File
............................................

Concatenate the compendium file(s) and the existing PO, merge the
result with the POT file and remove the obsolete entries (optional,
here done using `sed'):

     msgcat --use-first -o update.po compendium1.po compendium2.po file.po
     msgmerge update.po file.pot | sed -e '/^#~/d' > file.po


File: gettext.info,  Node: Manipulating,  Next: Binaries,  Prev: Updating,  Up: Top

7 Manipulating PO Files
***********************

Sometimes it is necessary to manipulate PO files in a way that is better
performed automatically than by hand.  GNU `gettext' includes a
complete set of tools for this purpose.

   When merging two packages into a single package, the resulting POT
file will be the concatenation of the two packages' POT files.  Thus the
maintainer must concatenate the two existing package translations into
a single translation catalog, for each language.  This is best performed
using `msgcat'.  It is then the translators' duty to deal with any
possible conflicts that arose during the merge.

   When a translator takes over the translation job from another
translator, but she uses a different character encoding in her locale,
she will convert the catalog to her character encoding.  This is best
done through the `msgconv' program.

   When a maintainer takes a source file with tagged messages from
another package, he should also take the existing translations for this
source file (and not let the translators do the same job twice).  One
way to do this is through `msggrep', another is to create a POT file for
that source file and use `msgmerge'.

   When a translator wants to adjust some translation catalog for a
special dialect or orthography -- for example, German as written in
Switzerland versus German as written in Germany -- she needs to apply
some text processing to every message in the catalog.  The tool for
doing this is `msgfilter'.

   Another use of `msgfilter' is to produce approximately the POT file
for which a given PO file was made.  This can be done through a filter
command like `msgfilter sed -e d | sed -e '/^# /d''.  Note that the
original POT file may have had different comments and different plural
message counts, that's why it's better to use the original POT file if
available.

   When a translator wants to check her translations, for example
according to orthography rules or using a non-interactive spell
checker, she can do so using the `msgexec' program.

   When third party tools create PO or POT files, sometimes duplicates
cannot be avoided.  But the GNU `gettext' tools give an error when they
encounter duplicate msgids in the same file and in the same domain.  To
merge duplicates, the `msguniq' program can be used.

   `msgcomm' is a more general tool for keeping or throwing away
duplicates, occurring in different files.

   `msgcmp' can be used to check whether a translation catalog is
completely translated.

   `msgattrib' can be used to select and extract only the fuzzy or
untranslated messages of a translation catalog.

   `msgen' is useful as a first step for preparing English translation
catalogs.  It copies each message's msgid to its msgstr.

   Finally, for those applications where all these various programs are
not sufficient, a library `libgettextpo' is provided that can be used to
write other specialized programs that process PO files.

* Menu:

* msgcat Invocation::           Invoking the `msgcat' Program
* msgconv Invocation::          Invoking the `msgconv' Program
* msggrep Invocation::          Invoking the `msggrep' Program
* msgfilter Invocation::        Invoking the `msgfilter' Program
* msguniq Invocation::          Invoking the `msguniq' Program
* msgcomm Invocation::          Invoking the `msgcomm' Program
* msgcmp Invocation::           Invoking the `msgcmp' Program
* msgattrib Invocation::        Invoking the `msgattrib' Program
* msgen Invocation::            Invoking the `msgen' Program
* msgexec Invocation::          Invoking the `msgexec' Program
* libgettextpo::                Writing your own programs that process PO files


File: gettext.info,  Node: msgcat Invocation,  Next: msgconv Invocation,  Prev: Manipulating,  Up: Manipulating

7.1 Invoking the `msgcat' Program
=================================

     msgcat [OPTION] [INPUTFILE]...

   The `msgcat' program concatenates and merges the specified PO files.
It finds messages which are common to two or more of the specified PO
files.  By using the `--more-than' option, greater commonality may be
requested before messages are printed.  Conversely, the `--less-than'
option may be used to specify less commonality before messages are
printed (i.e.  `--less-than=2' will only print the unique messages).
Translations, comments and extract comments will be cumulated, except
that if `--use-first' is specified, they will be taken from the first
PO file to define them.  File positions from all PO files will be
cumulated.

7.1.1 Input file location
-------------------------

`INPUTFILE ...'
     Input files.

`-f FILE'
`--files-from=FILE'
     Read the names of the input files from FILE instead of getting
     them from the command line.

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.  The resulting `.po'
     file will be written relative to the current directory, though.


   If INPUTFILE is `-', standard input is read.

7.1.2 Output file location
--------------------------

`-o FILE'
`--output-file=FILE'
     Write output to specified file.


   The results are written to standard output if no output file is
specified or if it is `-'.

7.1.3 Message selection
-----------------------

`-< NUMBER'
`--less-than=NUMBER'
     Print messages with less than NUMBER definitions, defaults to
     infinite if not set.

`-> NUMBER'
`--more-than=NUMBER'
     Print messages with more than NUMBER definitions, defaults to 0 if
     not set.

`-u'
`--unique'
     Shorthand for `--less-than=2'.  Requests that only unique messages
     be printed.


7.1.4 Input file syntax
-----------------------

`-P'
`--properties-input'
     Assume the input files are Java ResourceBundles in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input files are NeXTstep/GNUstep localized resource
     files in `.strings' syntax, not in PO file syntax.


7.1.5 Output details
--------------------

`-t'
`--to-code=NAME'
     Specify encoding for output.

`--use-first'
     Use first available translation for each message.  Don't merge
     several translations into one.

`--force-po'
     Always write an output file even if it contains no message.

`-i'
`--indent'
     Write the .po file using indented style.

`--no-location'
     Do not write `#: FILENAME:LINE' lines.

`-n'
`--add-location'
     Generate `#: FILENAME:LINE' lines (default).

`--strict'
     Write out a strict Uniforum conforming PO file.  Note that this
     Uniforum format should be avoided because it doesn't support the
     GNU extensions.

`-p'
`--properties-output'
     Write out a Java ResourceBundle in Java `.properties' syntax.  Note
     that this file format doesn't support plural forms and silently
     drops obsolete messages.

`--stringtable-output'
     Write out a NeXTstep/GNUstep localized resource file in `.strings'
     syntax.  Note that this file format doesn't support plural forms.

`-w NUMBER'
`--width=NUMBER'
     Set the output page width.  Long strings in the output files will
     be split across multiple lines in order to ensure that each line's
     width (= number of screen columns) is less or equal to the given
     NUMBER.

`--no-wrap'
     Do not break long message lines.  Message lines whose width
     exceeds the output page width will not be split into several
     lines.  Only file reference lines which are wider than the output
     page width will be split.

`-s'
`--sort-output'
     Generate sorted output.  Note that using this option makes it much
     harder for the translator to understand each message's context.

`-F'
`--sort-by-file'
     Sort output by file location.


7.1.6 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.



File: gettext.info,  Node: msgconv Invocation,  Next: msggrep Invocation,  Prev: msgcat Invocation,  Up: Manipulating

7.2 Invoking the `msgconv' Program
==================================

     msgconv [OPTION] [INPUTFILE]

   The `msgconv' program converts a translation catalog to a different
character encoding.

7.2.1 Input file location
-------------------------

`INPUTFILE'
     Input PO file.

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.  The resulting `.po'
     file will be written relative to the current directory, though.


   If no INPUTFILE is given or if it is `-', standard input is read.

7.2.2 Output file location
--------------------------

`-o FILE'
`--output-file=FILE'
     Write output to specified file.


   The results are written to standard output if no output file is
specified or if it is `-'.

7.2.3 Conversion target
-----------------------

`-t'
`--to-code=NAME'
     Specify encoding for output.


   The default encoding is the current locale's encoding.

7.2.4 Input file syntax
-----------------------

`-P'
`--properties-input'
     Assume the input file is a Java ResourceBundle in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input file is a NeXTstep/GNUstep localized resource
     file in `.strings' syntax, not in PO file syntax.


7.2.5 Output details
--------------------

`--force-po'
     Always write an output file even if it contains no message.

`-i'
`--indent'
     Write the .po file using indented style.

`--no-location'
     Do not write `#: FILENAME:LINE' lines.

`--add-location'
     Generate `#: FILENAME:LINE' lines (default).

`--strict'
     Write out a strict Uniforum conforming PO file.  Note that this
     Uniforum format should be avoided because it doesn't support the
     GNU extensions.

`-p'
`--properties-output'
     Write out a Java ResourceBundle in Java `.properties' syntax.  Note
     that this file format doesn't support plural forms and silently
     drops obsolete messages.

`--stringtable-output'
     Write out a NeXTstep/GNUstep localized resource file in `.strings'
     syntax.  Note that this file format doesn't support plural forms.

`-w NUMBER'
`--width=NUMBER'
     Set the output page width.  Long strings in the output files will
     be split across multiple lines in order to ensure that each line's
     width (= number of screen columns) is less or equal to the given
     NUMBER.

`--no-wrap'
     Do not break long message lines.  Message lines whose width
     exceeds the output page width will not be split into several
     lines.  Only file reference lines which are wider than the output
     page width will be split.

`-s'
`--sort-output'
     Generate sorted output.  Note that using this option makes it much
     harder for the translator to understand each message's context.

`-F'
`--sort-by-file'
     Sort output by file location.


7.2.6 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.



File: gettext.info,  Node: msggrep Invocation,  Next: msgfilter Invocation,  Prev: msgconv Invocation,  Up: Manipulating

7.3 Invoking the `msggrep' Program
==================================

     msggrep [OPTION] [INPUTFILE]

   The `msggrep' program extracts all messages of a translation catalog
that match a given pattern or belong to some given source files.

7.3.1 Input file location
-------------------------

`INPUTFILE'
     Input PO file.

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.  The resulting `.po'
     file will be written relative to the current directory, though.


   If no INPUTFILE is given or if it is `-', standard input is read.

7.3.2 Output file location
--------------------------

`-o FILE'
`--output-file=FILE'
     Write output to specified file.


   The results are written to standard output if no output file is
specified or if it is `-'.

7.3.3 Message selection
-----------------------

       [-N SOURCEFILE]... [-M DOMAINNAME]...
       [-K MSGID-PATTERN] [-T MSGSTR-PATTERN] [-C COMMENT-PATTERN]

   A message is selected if
   * it comes from one of the specified source files,

   * or if it comes from one of the specified domains,

   * or if `-K' is given and its key (msgid or msgid_plural) matches
       MSGID-PATTERN,

   * or if `-T' is given and its translation (msgstr) matches
     MSGSTR-PATTERN,

   * or if `-C' is given and the translator's comment matches
     COMMENT-PATTERN.

   When more than one selection criterion is specified, the set of
selected messages is the union of the selected messages of each
criterion.

   MSGID-PATTERN or MSGSTR-PATTERN syntax:
       [-E | -F] [-e PATTERN | -f FILE]...
   PATTERNs are basic regular expressions by default, or extended
regular expressions if -E is given, or fixed strings if -F is given.

`-N SOURCEFILE'
`--location=SOURCEFILE'
     Select messages extracted from SOURCEFILE.  SOURCEFILE can be
     either a literal file name or a wildcard pattern.

`-M DOMAINNAME'
`--domain=DOMAINNAME'
     Select messages belonging to domain DOMAINNAME.

`-K'
`--msgid'
     Start of patterns for the msgid.

`-T'
`--msgstr'
     Start of patterns for the msgstr.

`-C'
`--comment'
     Start of patterns for the translator's comment.

`-E'
`--extended-regexp'
     Specify that PATTERN is an extended regular expression.

`-F'
`--fixed-strings'
     Specify that PATTERN is a set of newline-separated strings.

`-e PATTERN'
`--regexp=PATTERN'
     Use PATTERN as a regular expression.

`-f FILE'
`--file=FILE'
     Obtain PATTERN from FILE.

`-i'
`--ignore-case'
     Ignore case distinctions.


7.3.4 Input file syntax
-----------------------

`-P'
`--properties-input'
     Assume the input file is a Java ResourceBundle in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input file is a NeXTstep/GNUstep localized resource
     file in `.strings' syntax, not in PO file syntax.


7.3.5 Output details
--------------------

`--force-po'
     Always write an output file even if it contains no message.

`--indent'
     Write the .po file using indented style.

`--no-location'
     Do not write `#: FILENAME:LINE' lines.

`--add-location'
     Generate `#: FILENAME:LINE' lines (default).

`--strict'
     Write out a strict Uniforum conforming PO file.  Note that this
     Uniforum format should be avoided because it doesn't support the
     GNU extensions.

`-p'
`--properties-output'
     Write out a Java ResourceBundle in Java `.properties' syntax.  Note
     that this file format doesn't support plural forms and silently
     drops obsolete messages.

`--stringtable-output'
     Write out a NeXTstep/GNUstep localized resource file in `.strings'
     syntax.  Note that this file format doesn't support plural forms.

`-w NUMBER'
`--width=NUMBER'
     Set the output page width.  Long strings in the output files will
     be split across multiple lines in order to ensure that each line's
     width (= number of screen columns) is less or equal to the given
     NUMBER.

`--no-wrap'
     Do not break long message lines.  Message lines whose width
     exceeds the output page width will not be split into several
     lines.  Only file reference lines which are wider than the output
     page width will be split.

`--sort-output'
     Generate sorted output.  Note that using this option makes it much
     harder for the translator to understand each message's context.

`--sort-by-file'
     Sort output by file location.


7.3.6 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.



File: gettext.info,  Node: msgfilter Invocation,  Next: msguniq Invocation,  Prev: msggrep Invocation,  Up: Manipulating

7.4 Invoking the `msgfilter' Program
====================================

     msgfilter [OPTION] FILTER [FILTER-OPTION]

   The `msgfilter' program applies a filter to all translations of a
translation catalog.

7.4.1 Input file location
-------------------------

`-i INPUTFILE'
`--input=INPUTFILE'
     Input PO file.

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.  The resulting `.po'
     file will be written relative to the current directory, though.


   If no INPUTFILE is given or if it is `-', standard input is read.

7.4.2 Output file location
--------------------------

`-o FILE'
`--output-file=FILE'
     Write output to specified file.


   The results are written to standard output if no output file is
specified or if it is `-'.

7.4.3 The filter
----------------

The FILTER can be any program that reads a translation from standard
input and writes a modified translation to standard output.  A
frequently used filter is `sed'.

   Note: It is your responsibility to ensure that the FILTER can cope
with input encoded in the translation catalog's encoding.  If the
FILTER wants input in a particular encoding, you can in a first step
convert the translation catalog to that encoding using the `msgconv'
program, before invoking `msgfilter'.  If the FILTER wants input in the
locale's encoding, but you want to avoid the locale's encoding, then
you can first convert the translation catalog to UTF-8 using the
`msgconv' program and then make `msgfilter' work in an UTF-8 locale, by
using the `LC_ALL' environment variable.

   Note: Most translations in a translation catalog don't end with a
newline character.  For this reason, it is important that the FILTER
recognizes its last input line even if it ends without a newline, and
that it doesn't add an undesired trailing newline at the end.  The `sed'
program on some platforms is known to ignore the last line of input if
it is not terminated with a newline.  You can use GNU `sed' instead; it
does not have this limitation.

7.4.4 Useful FILTER-OPTIONs when the FILTER is `sed'
----------------------------------------------------

`-e SCRIPT'
`--expression=SCRIPT'
     Add SCRIPT to the commands to be executed.

`-f SCRIPTFILE'
`--file=SCRIPTFILE'
     Add the contents of SCRIPTFILE to the commands to be executed.

`-n'
`--quiet'
`--silent'
     Suppress automatic printing of pattern space.


7.4.5 Input file syntax
-----------------------

`-P'
`--properties-input'
     Assume the input file is a Java ResourceBundle in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input file is a NeXTstep/GNUstep localized resource
     file in `.strings' syntax, not in PO file syntax.


7.4.6 Output details
--------------------

`--force-po'
     Always write an output file even if it contains no message.

`--indent'
     Write the .po file using indented style.

`--keep-header'
     Keep the header entry, i.e. the message with `msgid ""',
     unmodified, instead of filtering it.  By default, the header entry
     is subject to filtering like any other message.

`--no-location'
     Do not write `#: FILENAME:LINE' lines.

`--add-location'
     Generate `#: FILENAME:LINE' lines (default).

`--strict'
     Write out a strict Uniforum conforming PO file.  Note that this
     Uniforum format should be avoided because it doesn't support the
     GNU extensions.

`-p'
`--properties-output'
     Write out a Java ResourceBundle in Java `.properties' syntax.  Note
     that this file format doesn't support plural forms and silently
     drops obsolete messages.

`--stringtable-output'
     Write out a NeXTstep/GNUstep localized resource file in `.strings'
     syntax.  Note that this file format doesn't support plural forms.

`-w NUMBER'
`--width=NUMBER'
     Set the output page width.  Long strings in the output files will
     be split across multiple lines in order to ensure that each line's
     width (= number of screen columns) is less or equal to the given
     NUMBER.

`--no-wrap'
     Do not break long message lines.  Message lines whose width
     exceeds the output page width will not be split into several
     lines.  Only file reference lines which are wider than the output
     page width will be split.

`-s'
`--sort-output'
     Generate sorted output.  Note that using this option makes it much
     harder for the translator to understand each message's context.

`-F'
`--sort-by-file'
     Sort output by file location.


7.4.7 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.



File: gettext.info,  Node: msguniq Invocation,  Next: msgcomm Invocation,  Prev: msgfilter Invocation,  Up: Manipulating

7.5 Invoking the `msguniq' Program
==================================

     msguniq [OPTION] [INPUTFILE]

   The `msguniq' program unifies duplicate translations in a translation
catalog.  It finds duplicate translations of the same message ID.  Such
duplicates are invalid input for other programs like `msgfmt',
`msgmerge' or `msgcat'.  By default, duplicates are merged together.
When using the `--repeated' option, only duplicates are output, and all
other messages are discarded.  Comments and extracted comments will be
cumulated, except that if `--use-first' is specified, they will be
taken from the first translation.  File positions will be cumulated.
When using the `--unique' option, duplicates are discarded.

7.5.1 Input file location
-------------------------

`INPUTFILE'
     Input PO file.

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.  The resulting `.po'
     file will be written relative to the current directory, though.


   If no INPUTFILE is given or if it is `-', standard input is read.

7.5.2 Output file location
--------------------------

`-o FILE'
`--output-file=FILE'
     Write output to specified file.


   The results are written to standard output if no output file is
specified or if it is `-'.

7.5.3 Message selection
-----------------------

`-d'
`--repeated'
     Print only duplicates.

`-u'
`--unique'
     Print only unique messages, discard duplicates.


7.5.4 Input file syntax
-----------------------

`-P'
`--properties-input'
     Assume the input file is a Java ResourceBundle in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input file is a NeXTstep/GNUstep localized resource
     file in `.strings' syntax, not in PO file syntax.


7.5.5 Output details
--------------------

`-t'
`--to-code=NAME'
     Specify encoding for output.

`--use-first'
     Use first available translation for each message.  Don't merge
     several translations into one.

`--force-po'
     Always write an output file even if it contains no message.

`-i'
`--indent'
     Write the .po file using indented style.

`--no-location'
     Do not write `#: FILENAME:LINE' lines.

`-n'
`--add-location'
     Generate `#: FILENAME:LINE' lines (default).

`--strict'
     Write out a strict Uniforum conforming PO file.  Note that this
     Uniforum format should be avoided because it doesn't support the
     GNU extensions.

`-p'
`--properties-output'
     Write out a Java ResourceBundle in Java `.properties' syntax.  Note
     that this file format doesn't support plural forms and silently
     drops obsolete messages.

`--stringtable-output'
     Write out a NeXTstep/GNUstep localized resource file in `.strings'
     syntax.  Note that this file format doesn't support plural forms.

`-w NUMBER'
`--width=NUMBER'
     Set the output page width.  Long strings in the output files will
     be split across multiple lines in order to ensure that each line's
     width (= number of screen columns) is less or equal to the given
     NUMBER.

`--no-wrap'
     Do not break long message lines.  Message lines whose width
     exceeds the output page width will not be split into several
     lines.  Only file reference lines which are wider than the output
     page width will be split.

`-s'
`--sort-output'
     Generate sorted output.  Note that using this option makes it much
     harder for the translator to understand each message's context.

`-F'
`--sort-by-file'
     Sort output by file location.


7.5.6 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.



File: gettext.info,  Node: msgcomm Invocation,  Next: msgcmp Invocation,  Prev: msguniq Invocation,  Up: Manipulating

7.6 Invoking the `msgcomm' Program
==================================

     msgcomm [OPTION] [INPUTFILE]...

   The `msgcomm' program finds messages which are common to two or more
of the specified PO files.  By using the `--more-than' option, greater
commonality may be requested before messages are printed.  Conversely,
the `--less-than' option may be used to specify less commonality before
messages are printed (i.e.  `--less-than=2' will only print the unique
messages).  Translations, comments and extract comments will be
preserved, but only from the first PO file to define them.  File
positions from all PO files will be cumulated.

7.6.1 Input file location
-------------------------

`INPUTFILE ...'
     Input files.

`-f FILE'
`--files-from=FILE'
     Read the names of the input files from FILE instead of getting
     them from the command line.

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.  The resulting `.po'
     file will be written relative to the current directory, though.


   If INPUTFILE is `-', standard input is read.

7.6.2 Output file location
--------------------------

`-o FILE'
`--output-file=FILE'
     Write output to specified file.


   The results are written to standard output if no output file is
specified or if it is `-'.

7.6.3 Message selection
-----------------------

`-< NUMBER'
`--less-than=NUMBER'
     Print messages with less than NUMBER definitions, defaults to
     infinite if not set.

`-> NUMBER'
`--more-than=NUMBER'
     Print messages with more than NUMBER definitions, defaults to 1 if
     not set.

`-u'
`--unique'
     Shorthand for `--less-than=2'.  Requests that only unique messages
     be printed.


7.6.4 Input file syntax
-----------------------

`-P'
`--properties-input'
     Assume the input files are Java ResourceBundles in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input files are NeXTstep/GNUstep localized resource
     files in `.strings' syntax, not in PO file syntax.


7.6.5 Output details
--------------------

`--force-po'
     Always write an output file even if it contains no message.

`-i'
`--indent'
     Write the .po file using indented style.

`--no-location'
     Do not write `#: FILENAME:LINE' lines.

`-n'
`--add-location'
     Generate `#: FILENAME:LINE' lines (default).

`--strict'
     Write out a strict Uniforum conforming PO file.  Note that this
     Uniforum format should be avoided because it doesn't support the
     GNU extensions.

`-p'
`--properties-output'
     Write out a Java ResourceBundle in Java `.properties' syntax.  Note
     that this file format doesn't support plural forms and silently
     drops obsolete messages.

`--stringtable-output'
     Write out a NeXTstep/GNUstep localized resource file in `.strings'
     syntax.  Note that this file format doesn't support plural forms.

`-w NUMBER'
`--width=NUMBER'
     Set the output page width.  Long strings in the output files will
     be split across multiple lines in order to ensure that each line's
     width (= number of screen columns) is less or equal to the given
     NUMBER.

`--no-wrap'
     Do not break long message lines.  Message lines whose width
     exceeds the output page width will not be split into several
     lines.  Only file reference lines which are wider than the output
     page width will be split.

`-s'
`--sort-output'
     Generate sorted output.  Note that using this option makes it much
     harder for the translator to understand each message's context.

`-F'
`--sort-by-file'
     Sort output by file location.

`--omit-header'
     Don't write header with `msgid ""' entry.


7.6.6 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.



File: gettext.info,  Node: msgcmp Invocation,  Next: msgattrib Invocation,  Prev: msgcomm Invocation,  Up: Manipulating

7.7 Invoking the `msgcmp' Program
=================================

     msgcmp [OPTION] DEF.po REF.pot

   The `msgcmp' program compares two Uniforum style .po files to check
that both contain the same set of msgid strings.  The DEF.po file is an
existing PO file with the translations.  The REF.pot file is the last
created PO file, or a PO Template file (generally created by
`xgettext').  This is useful for checking that you have translated each
and every message in your program.  Where an exact match cannot be
found, fuzzy matching is used to produce better diagnostics.

7.7.1 Input file location
-------------------------

`DEF.po'
     Translations.

`REF.pot'
     References to the sources.

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.


7.7.2 Operation modifiers
-------------------------

`-m'
`--multi-domain'
     Apply REF.pot to each of the domains in DEF.po.


7.7.3 Input file syntax
-----------------------

`-P'
`--properties-input'
     Assume the input files are Java ResourceBundles in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input files are NeXTstep/GNUstep localized resource
     files in `.strings' syntax, not in PO file syntax.


7.7.4 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.



File: gettext.info,  Node: msgattrib Invocation,  Next: msgen Invocation,  Prev: msgcmp Invocation,  Up: Manipulating

7.8 Invoking the `msgattrib' Program
====================================

     msgattrib [OPTION] [INPUTFILE]

   The `msgattrib' program filters the messages of a translation catalog
according to their attributes, and manipulates the attributes.

7.8.1 Input file location
-------------------------

`INPUTFILE'
     Input PO file.

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.  The resulting `.po'
     file will be written relative to the current directory, though.


   If no INPUTFILE is given or if it is `-', standard input is read.

7.8.2 Output file location
--------------------------

`-o FILE'
`--output-file=FILE'
     Write output to specified file.


   The results are written to standard output if no output file is
specified or if it is `-'.

7.8.3 Message selection
-----------------------

`--translated'
     Keep translated messages, remove untranslated messages.

`--untranslated'
     Keep untranslated messages, remove translated messages.

`--no-fuzzy'
     Remove `fuzzy' marked messages.

`--only-fuzzy'
     Keep `fuzzy' marked messages, remove all other messsages.

`--no-obsolete'
     Remove obsolete #~ messages.

`--only-obsolete'
     Keep obsolete #~ messages, remove all other messages.


7.8.4 Attribute manipulation
----------------------------

Attributes are modified after the message selection/removal has been
performed.  If the `--only-file' or `--ignore-file' option is
specified, the attribute modification is applied only to those messages
that are listed in the ONLY-FILE and not listed in the IGNORE-FILE.

`--set-fuzzy'
     Set all messages `fuzzy'.

`--clear-fuzzy'
     Set all messages non-`fuzzy'.

`--set-obsolete'
     Set all messages obsolete.

`--clear-obsolete'
     Set all messages non-obsolete.

`--only-file=FILE'
     Limit the attribute changes to entries that are listed in FILE.
     FILE should be a PO or POT file.

`--ignore-file=FILE'
     Limit the attribute changes to entries that are not listed in FILE.
     FILE should be a PO or POT file.

`--fuzzy'
     Synonym for `--only-fuzzy --clear-fuzzy': It keeps only the fuzzy
     messages and removes their `fuzzy' mark.

`--obsolete'
     Synonym for `--only-obsolete --clear-obsolete': It keeps only the
     obsolete messages and makes them non-obsolete.


7.8.5 Input file syntax
-----------------------

`-P'
`--properties-input'
     Assume the input file is a Java ResourceBundle in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input file is a NeXTstep/GNUstep localized resource
     file in `.strings' syntax, not in PO file syntax.


7.8.6 Output details
--------------------

`--force-po'
     Always write an output file even if it contains no message.

`-i'
`--indent'
     Write the .po file using indented style.

`--no-location'
     Do not write `#: FILENAME:LINE' lines.

`-n'
`--add-location'
     Generate `#: FILENAME:LINE' lines (default).

`--strict'
     Write out a strict Uniforum conforming PO file.  Note that this
     Uniforum format should be avoided because it doesn't support the
     GNU extensions.

`-p'
`--properties-output'
     Write out a Java ResourceBundle in Java `.properties' syntax.  Note
     that this file format doesn't support plural forms and silently
     drops obsolete messages.

`--stringtable-output'
     Write out a NeXTstep/GNUstep localized resource file in `.strings'
     syntax.  Note that this file format doesn't support plural forms.

`-w NUMBER'
`--width=NUMBER'
     Set the output page width.  Long strings in the output files will
     be split across multiple lines in order to ensure that each line's
     width (= number of screen columns) is less or equal to the given
     NUMBER.

`--no-wrap'
     Do not break long message lines.  Message lines whose width
     exceeds the output page width will not be split into several
     lines.  Only file reference lines which are wider than the output
     page width will be split.

`-s'
`--sort-output'
     Generate sorted output.  Note that using this option makes it much
     harder for the translator to understand each message's context.

`-F'
`--sort-by-file'
     Sort output by file location.


7.8.7 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.



File: gettext.info,  Node: msgen Invocation,  Next: msgexec Invocation,  Prev: msgattrib Invocation,  Up: Manipulating

7.9 Invoking the `msgen' Program
================================

     msgen [OPTION] INPUTFILE

   The `msgen' program creates an English translation catalog.  The
input file is the last created English PO file, or a PO Template file
(generally created by xgettext).  Untranslated entries are assigned a
translation that is identical to the msgid.

   Note: `msginit --no-translator --locale=en' performs a very similar
task.  The main difference is that `msginit' cares specially about the
header entry, whereas `msgen' doesn't.

7.9.1 Input file location
-------------------------

`INPUTFILE'
     Input PO or POT file.

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.  The resulting `.po'
     file will be written relative to the current directory, though.


   If INPUTFILE is `-', standard input is read.

7.9.2 Output file location
--------------------------

`-o FILE'
`--output-file=FILE'
     Write output to specified file.


   The results are written to standard output if no output file is
specified or if it is `-'.

7.9.3 Input file syntax
-----------------------

`-P'
`--properties-input'
     Assume the input file is a Java ResourceBundle in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input file is a NeXTstep/GNUstep localized resource
     file in `.strings' syntax, not in PO file syntax.


7.9.4 Output details
--------------------

`--force-po'
     Always write an output file even if it contains no message.

`-i'
`--indent'
     Write the .po file using indented style.

`--no-location'
     Do not write `#: FILENAME:LINE' lines.

`--add-location'
     Generate `#: FILENAME:LINE' lines (default).

`--strict'
     Write out a strict Uniforum conforming PO file.  Note that this
     Uniforum format should be avoided because it doesn't support the
     GNU extensions.

`-p'
`--properties-output'
     Write out a Java ResourceBundle in Java `.properties' syntax.  Note
     that this file format doesn't support plural forms and silently
     drops obsolete messages.

`--stringtable-output'
     Write out a NeXTstep/GNUstep localized resource file in `.strings'
     syntax.  Note that this file format doesn't support plural forms.

`-w NUMBER'
`--width=NUMBER'
     Set the output page width.  Long strings in the output files will
     be split across multiple lines in order to ensure that each line's
     width (= number of screen columns) is less or equal to the given
     NUMBER.

`--no-wrap'
     Do not break long message lines.  Message lines whose width
     exceeds the output page width will not be split into several
     lines.  Only file reference lines which are wider than the output
     page width will be split.

`-s'
`--sort-output'
     Generate sorted output.  Note that using this option makes it much
     harder for the translator to understand each message's context.

`-F'
`--sort-by-file'
     Sort output by file location.


7.9.5 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.



File: gettext.info,  Node: msgexec Invocation,  Next: libgettextpo,  Prev: msgen Invocation,  Up: Manipulating

7.10 Invoking the `msgexec' Program
===================================

     msgexec [OPTION] COMMAND [COMMAND-OPTION]

   The `msgexec' program applies a command to all translations of a
translation catalog.  The COMMAND can be any program that reads a
translation from standard input.  It is invoked once for each
translation.  Its output becomes msgexec's output.  `msgexec''s return
code is the maximum return code across all invocations.

   A special builtin command called `0' outputs the translation,
followed by a null byte.  The output of `msgexec 0' is suitable as
input for `xargs -0'.

   During each COMMAND invocation, the environment variable
`MSGEXEC_MSGID' is bound to the message's msgid, and the environment
variable `MSGEXEC_LOCATION' is bound to the location in the PO file of
the message.

   Note: It is your responsibility to ensure that the COMMAND can cope
with input encoded in the translation catalog's encoding.  If the
COMMAND wants input in a particular encoding, you can in a first step
convert the translation catalog to that encoding using the `msgconv'
program, before invoking `msgexec'.  If the COMMAND wants input in the
locale's encoding, but you want to avoid the locale's encoding, then
you can first convert the translation catalog to UTF-8 using the
`msgconv' program and then make `msgexec' work in an UTF-8 locale, by
using the `LC_ALL' environment variable.

7.10.1 Input file location
--------------------------

`-i INPUTFILE'
`--input=INPUTFILE'
     Input PO file.

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.  The resulting `.po'
     file will be written relative to the current directory, though.


   If no INPUTFILE is given or if it is `-', standard input is read.

7.10.2 Input file syntax
------------------------

`-P'
`--properties-input'
     Assume the input file is a Java ResourceBundle in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input file is a NeXTstep/GNUstep localized resource
     file in `.strings' syntax, not in PO file syntax.


7.10.3 Informative output
-------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.



File: gettext.info,  Node: libgettextpo,  Prev: msgexec Invocation,  Up: Manipulating

7.11 Writing your own programs that process PO files
====================================================

For the tasks for which a combination of `msgattrib', `msgcat' etc.  is
not sufficient, a set of C functions is provided in a library, to make
it possible to process PO files in your own programs.  When you use
this library, you don't need to write routines to parse the PO file;
instead, you retreive a pointer in memory to each of messages contained
in the PO file.  Functions for writing PO files are not provided at
this time.

   The functions are declared in the header file `<gettext-po.h>', and
are defined in a library called `libgettextpo'.

 -- Data Type: po_file_t
     This is a pointer type that refers to the contents of a PO file,
     after it has been read into memory.

 -- Data Type: po_message_iterator_t
     This is a pointer type that refers to an iterator that produces a
     sequence of messages.

 -- Data Type: po_message_t
     This is a pointer type that refers to a message of a PO file,
     including its translation.

 -- Function: po_file_t po_file_read (const char *FILENAME)
     The `po_file_read' function reads a PO file into memory.  The file
     name is given as argument.  The return value is a handle to the PO
     file's contents, valid until `po_file_free' is called on it.  In
     case of error, the return value is `NULL', and `errno' is set.

 -- Function: void po_file_free (po_file_t FILE)
     The `po_file_free' function frees a PO file's contents from memory,
     including all messages that are only implicitly accessible through
     iterators.

 -- Function: const char * const * po_file_domains (po_file_t FILE)
     The `po_file_domains' function returns the domains for which the
     given PO file has messages.  The return value is a `NULL'
     terminated array which is valid as long as the FILE handle is
     valid.  For PO files which contain no `domain' directive, the
     return value contains only one domain, namely the default domain
     `"messages"'.

 -- Function: po_message_iterator_t po_message_iterator (po_file_t
          FILE, const char *DOMAIN)
     The `po_message_iterator' returns an iterator that will produce the
     messages of FILE that belong to the given DOMAIN.  If DOMAIN is
     `NULL', the default domain is used instead.  To list the messages,
     use the function `po_next_message' repeatedly.

 -- Function: void po_message_iterator_free (po_message_iterator_t
          ITERATOR)
     The `po_message_iterator_free' function frees an iterator
     previously allocated through the `po_message_iterator' function.

 -- Function: po_message_t po_next_message (po_message_iterator_t
          ITERATOR)
     The `po_next_message' function returns the next message from
     ITERATOR and advances the iterator.  It returns `NULL' when the
     iterator has reached the end of its message list.

   The following functions returns details of a `po_message_t'.  Recall
that the results are valid as long as the FILE handle is valid.

 -- Function: const char * po_message_msgid (po_message_t MESSAGE)
     The `po_message_msgid' function returns the `msgid' (untranslated
     English string) of a message.  This is guaranteed to be non-`NULL'.

 -- Function: const char * po_message_msgid_plural (po_message_t
          MESSAGE)
     The `po_message_msgid_plural' function returns the `msgid_plural'
     (untranslated English plural string) of a message with plurals, or
     `NULL' for a message without plural.

 -- Function: const char * po_message_msgstr (po_message_t MESSAGE)
     The `po_message_msgstr' function returns the `msgstr' (translation)
     of a message.  For an untranslated message, the return value is an
     empty string.

 -- Function: const char * po_message_msgstr_plural (po_message_t
          MESSAGE, int INDEX)
     The `po_message_msgstr_plural' function returns the
     `msgstr[INDEX]' of a message with plurals, or `NULL' when the
     INDEX is out of range or for a message without plural.

   Here is an example code how these functions can be used.

     const char *filename = ...;
     po_file_t file = po_file_read (filename);

     if (file == NULL)
       error (EXIT_FAILURE, errno, "couldn't open the PO file %s", filename);
     {
       const char * const *domains = po_file_domains (file);
       const char * const *domainp;

       for (domainp = domains; *domainp; domainp++)
         {
           const char *domain = *domainp;
           po_message_iterator_t iterator = po_message_iterator (file, domain);

           for (;;)
             {
               po_message_t *message = po_next_message (iterator);

               if (message == NULL)
                 break;
               {
                 const char *msgid = po_message_msgid (message);
                 const char *msgstr = po_message_msgstr (message);

                 ...
               }
             }
           po_message_iterator_free (iterator);
         }
     }
     po_file_free (file);


File: gettext.info,  Node: Binaries,  Next: Users,  Prev: Manipulating,  Up: Top

8 Producing Binary MO Files
***************************

* Menu:

* msgfmt Invocation::           Invoking the `msgfmt' Program
* msgunfmt Invocation::         Invoking the `msgunfmt' Program
* MO Files::                    The Format of GNU MO Files


File: gettext.info,  Node: msgfmt Invocation,  Next: msgunfmt Invocation,  Prev: Binaries,  Up: Binaries

8.1 Invoking the `msgfmt' Program
=================================

     msgfmt [OPTION] FILENAME.po ...

   The `msgfmt' programs generates a binary message catalog from a
textual translation description.

8.1.1 Input file location
-------------------------

`FILENAME.po ...'

`-D DIRECTORY'
`--directory=DIRECTORY'
     Add DIRECTORY to the list of directories.  Source files are
     searched relative to this list of directories.  The resulting `.po'
     file will be written relative to the current directory, though.


   If an input file is `-', standard input is read.

8.1.2 Operation mode
--------------------

`-j'
`--java'
     Java mode: generate a Java `ResourceBundle' class.

`--java2'
     Like -java, and assume Java2 (JDK 1.2 or higher).

`--csharp'
     C# mode: generate a .NET .dll file containing a subclass of
     `GettextResourceSet'.

`--csharp-resources'
     C# resources mode: generate a .NET `.resources' file.

`--tcl'
     Tcl mode: generate a tcl/msgcat `.msg' file.

`--qt'
     Qt mode: generate a Qt `.qm' file.


8.1.3 Output file location
--------------------------

`-o FILE'
`--output-file=FILE'
     Write output to specified file.

`--strict'
     Direct the program to work strictly following the Uniforum/Sun
     implementation.  Currently this only affects the naming of the
     output file.  If this option is not given the name of the output
     file is the same as the domain name.  If the strict Uniforum mode
     is enabled the suffix `.mo' is added to the file name if it is not
     already present.

     We find this behaviour of Sun's implementation rather silly and so
     by default this mode is _not_ selected.


   If the output FILE is `-', output is written to standard output.

8.1.4 Output file location in Java mode
---------------------------------------

`-r RESOURCE'
`--resource=RESOURCE'
     Specify the resource name.

`-l LOCALE'
`--locale=LOCALE'
     Specify the locale name, either a language specification of the
     form LL or a combined language and country specification of the
     form LL_CC.

`-d DIRECTORY'
     Specify the base directory of classes directory hierarchy.


   The class name is determined by appending the locale name to the
resource name, separated with an underscore.  The `-d' option is
mandatory.  The class is written under the specified directory.

8.1.5 Output file location in C# mode
-------------------------------------

`-r RESOURCE'
`--resource=RESOURCE'
     Specify the resource name.

`-l LOCALE'
`--locale=LOCALE'
     Specify the locale name, either a language specification of the
     form LL or a combined language and country specification of the
     form LL_CC.

`-d DIRECTORY'
     Specify the base directory for locale dependent `.dll' files.


   The `-l' and `-d' options are mandatory.  The `.dll' file is written
in a subdirectory of the specified directory whose name depends on the
locale.

8.1.6 Output file location in Tcl mode
--------------------------------------

`-l LOCALE'
`--locale=LOCALE'
     Specify the locale name, either a language specification of the
     form LL or a combined language and country specification of the
     form LL_CC.

`-d DIRECTORY'
     Specify the base directory of `.msg' message catalogs.


   The `-l' and `-d' options are mandatory.  The `.msg' file is written
in the specified directory.

8.1.7 Input file syntax
-----------------------

`-P'
`--properties-input'
     Assume the input files are Java ResourceBundles in Java
     `.properties' syntax, not in PO file syntax.

`--stringtable-input'
     Assume the input files are NeXTstep/GNUstep localized resource
     files in `.strings' syntax, not in PO file syntax.


8.1.8 Input file interpretation
-------------------------------

`-c'
`--check'
     Perform all the checks implied by `--check-format',
     `--check-header', `--check-domain'.

`--check-format'
     Check language dependent format strings.

     If the string represents a format string used in a `printf'-like
     function both strings should have the same number of `%' format
     specifiers, with matching types.  If the flag `c-format' or
     `possible-c-format' appears in the special comment <#,> for this
     entry a check is performed.  For example, the check will diagnose
     using `%.*s' against `%s', or `%d' against `%s', or `%d' against
     `%x'.  It can even handle positional parameters.

     Normally the `xgettext' program automatically decides whether a
     string is a format string or not.  This algorithm is not perfect,
     though.  It might regard a string as a format string though it is
     not used in a `printf'-like function and so `msgfmt' might report
     errors where there are none.

     To solve this problem the programmer can dictate the decision to
     the `xgettext' program (*note c-format::).  The translator should
     not consider removing the flag from the <#,> line.  This "fix"
     would be reversed again as soon as `msgmerge' is called the next
     time.

`--check-header'
     Verify presence and contents of the header entry.  *Note Header
     Entry::, for a description of the various fields in the header
     entry.

`--check-domain'
     Check for conflicts between domain directives and the
     `--output-file' option

`-C'
`--check-compatibility'
     Check that GNU msgfmt behaves like X/Open msgfmt.  This will give
     an error when attempting to use the GNU extensions.

`--check-accelerators[=CHAR]'
     Check presence of keyboard accelerators for menu items.  This is
     based on the convention used in some GUIs that a keyboard
     accelerator in a menu item string is designated by an immediately
     preceding `&' character.  Sometimes a keyboard accelerator is also
     called "keyboard mnemonic".  This check verifies that if the
     untranslated string has exactly one `&' character, the translated
     string has exactly one `&' as well.  If this option is given with
     a CHAR argument, this CHAR should be a non-alphanumeric character
     and is used as keyboard accelerator mark instead of `&'.

`-f'
`--use-fuzzy'
     Use fuzzy entries in output.  Note that using this option is
     usually wrong, because fuzzy messages are exactly those which have
     not been validated by a human translator.


8.1.9 Output details
--------------------

`-a NUMBER'
`--alignment=NUMBER'
     Align strings to NUMBER bytes (default: 1).

`--no-hash'
     Don't include a hash table in the binary file.  Lookup will be
     more expensive at run time (binary search instead of hash table
     lookup).


8.1.10 Informative output
-------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.

`--statistics'
     Print statistics about translations.

`-v'
`--verbose'
     Increase verbosity level.



File: gettext.info,  Node: msgunfmt Invocation,  Next: MO Files,  Prev: msgfmt Invocation,  Up: Binaries

8.2 Invoking the `msgunfmt' Program
===================================

     msgunfmt [OPTION] [FILE]...

   The `msgunfmt' program converts a binary message catalog to a
Uniforum style .po file.

8.2.1 Operation mode
--------------------

`-j'
`--java'
     Java mode: input is a Java `ResourceBundle' class.

`--csharp'
     C# mode: input is a .NET .dll file containing a subclass of
     `GettextResourceSet'.

`--csharp-resources'
     C# resources mode: input is a .NET `.resources' file.

`--tcl'
     Tcl mode: input is a tcl/msgcat `.msg' file.


8.2.2 Input file location
-------------------------

`FILE ...'
     Input .mo files.


   If no input FILE is given or if it is `-', standard input is read.

8.2.3 Input file location in Java mode
--------------------------------------

`-r RESOURCE'
`--resource=RESOURCE'
     Specify the resource name.

`-l LOCALE'
`--locale=LOCALE'
     Specify the locale name, either a language specification of the
     form LL or a combined language and country specification of the
     form LL_CC.


   The class name is determined by appending the locale name to the
resource name, separated with an underscore.  The class is located
using the `CLASSPATH'.

8.2.4 Input file location in C# mode
------------------------------------

`-r RESOURCE'
`--resource=RESOURCE'
     Specify the resource name.

`-l LOCALE'
`--locale=LOCALE'
     Specify the locale name, either a language specification of the
     form LL or a combined language and country specification of the
     form LL_CC.

`-d DIRECTORY'
     Specify the base directory for locale dependent `.dll' files.


   The `-l' and `-d' options are mandatory.  The `.msg' file is located
in a subdirectory of the specified directory whose name depends on the
locale.

8.2.5 Input file location in Tcl mode
-------------------------------------

`-l LOCALE'
`--locale=LOCALE'
     Specify the locale name, either a language specification of the
     form LL or a combined language and country specification of the
     form LL_CC.

`-d DIRECTORY'
     Specify the base directory of `.msg' message catalogs.


   The `-l' and `-d' options are mandatory.  The `.msg' file is located
in the specified directory.

8.2.6 Output file location
--------------------------

`-o FILE'
`--output-file=FILE'
     Write output to specified file.


   The results are written to standard output if no output file is
specified or if it is `-'.

8.2.7 Output details
--------------------

`--force-po'
     Always write an output file even if it contains no message.

`-i'
`--indent'
     Write the .po file using indented style.

`--strict'
     Write out a strict Uniforum conforming PO file.  Note that this
     Uniforum format should be avoided because it doesn't support the
     GNU extensions.

`-p'
`--properties-output'
     Write out a Java ResourceBundle in Java `.properties' syntax.  Note
     that this file format doesn't support plural forms and silently
     drops obsolete messages.

`--stringtable-output'
     Write out a NeXTstep/GNUstep localized resource file in `.strings'
     syntax.  Note that this file format doesn't support plural forms.

`-w NUMBER'
`--width=NUMBER'
     Set the output page width.  Long strings in the output files will
     be split across multiple lines in order to ensure that each line's
     width (= number of screen columns) is less or equal to the given
     NUMBER.

`--no-wrap'
     Do not break long message lines.  Message lines whose width
     exceeds the output page width will not be split into several
     lines.  Only file reference lines which are wider than the output
     page width will be split.

`-s'
`--sort-output'
     Generate sorted output.  Note that using this option makes it much
     harder for the translator to understand each message's context.


8.2.8 Informative output
------------------------

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.

`-v'
`--verbose'
     Increase verbosity level.



File: gettext.info,  Node: MO Files,  Prev: msgunfmt Invocation,  Up: Binaries

8.3 The Format of GNU MO Files
==============================

The format of the generated MO files is best described by a picture,
which appears below.

   The first two words serve the identification of the file.  The magic
number will always signal GNU MO files.  The number is stored in the
byte order of the generating machine, so the magic number really is two
numbers: `0x950412de' and `0xde120495'.  The second word describes the
current revision of the file format.  For now the revision is 0.  This
might change in future versions, and ensures that the readers of MO
files can distinguish new formats from old ones, so that both can be
handled correctly.  The version is kept separate from the magic number,
instead of using different magic numbers for different formats, mainly
because `/etc/magic' is not updated often.  It might be better to have
magic separated from internal format version identification.

   Follow a number of pointers to later tables in the file, allowing
for the extension of the prefix part of MO files without having to
recompile programs reading them.  This might become useful for later
inserting a few flag bits, indication about the charset used, new
tables, or other things.

   Then, at offset O and offset T in the picture, two tables of string
descriptors can be found.  In both tables, each string descriptor uses
two 32 bits integers, one for the string length, another for the offset
of the string in the MO file, counting in bytes from the start of the
file.  The first table contains descriptors for the original strings,
and is sorted so the original strings are in increasing lexicographical
order.  The second table contains descriptors for the translated
strings, and is parallel to the first table: to find the corresponding
translation one has to access the array slot in the second array with
the same index.

   Having the original strings sorted enables the use of simple binary
search, for when the MO file does not contain an hashing table, or for
when it is not practical to use the hashing table provided in the MO
file.  This also has another advantage, as the empty string in a PO
file GNU `gettext' is usually _translated_ into some system information
attached to that particular MO file, and the empty string necessarily
becomes the first in both the original and translated tables, making
the system information very easy to find.

   The size S of the hash table can be zero.  In this case, the hash
table itself is not contained in the MO file.  Some people might prefer
this because a precomputed hashing table takes disk space, and does not
win _that_ much speed.  The hash table contains indices to the sorted
array of strings in the MO file.  Conflict resolution is done by double
hashing.  The precise hashing algorithm used is fairly dependent on GNU
`gettext' code, and is not documented here.

   As for the strings themselves, they follow the hash file, and each
is terminated with a <NUL>, and this <NUL> is not counted in the length
which appears in the string descriptor.  The `msgfmt' program has an
option selecting the alignment for MO file strings.  With this option,
each string is separately aligned so it starts at an offset which is a
multiple of the alignment value.  On some RISC machines, a correct
alignment will speed things up.

   Plural forms are stored by letting the plural of the original string
follow the singular of the original string, separated through a <NUL>
byte.  The length which appears in the string descriptor includes both.
However, only the singular of the original string takes part in the
hash table lookup.  The plural variants of the translation are all
stored consecutively, separated through a <NUL> byte.  Here also, the
length in the string descriptor includes all of them.

   Nothing prevents a MO file from having embedded <NUL>s in strings.
However, the program interface currently used already presumes that
strings are <NUL> terminated, so embedded <NUL>s are somewhat useless.
But the MO file format is general enough so other interfaces would be
later possible, if for example, we ever want to implement wide
characters right in MO files, where <NUL> bytes may accidently appear.
(No, we don't want to have wide characters in MO files.  They would
make the file unnecessarily large, and the `wchar_t' type being
platform dependent, MO files would be platform dependent as well.)

   This particular issue has been strongly debated in the GNU `gettext'
development forum, and it is expectable that MO file format will evolve
or change over time.  It is even possible that many formats may later
be supported concurrently.  But surely, we have to start somewhere, and
the MO file format described here is a good start.  Nothing is cast in
concrete, and the format may later evolve fairly easily, so we should
feel comfortable with the current approach.

             byte
                  +------------------------------------------+
               0  | magic number = 0x950412de                |
                  |                                          |
               4  | file format revision = 0                 |
                  |                                          |
               8  | number of strings                        |  == N
                  |                                          |
              12  | offset of table with original strings    |  == O
                  |                                          |
              16  | offset of table with translation strings |  == T
                  |                                          |
              20  | size of hashing table                    |  == S
                  |                                          |
              24  | offset of hashing table                  |  == H
                  |                                          |
                  .                                          .
                  .    (possibly more entries later)         .
                  .                                          .
                  |                                          |
               O  | length & offset 0th string  ----------------.
           O + 8  | length & offset 1st string  ------------------.
                   ...                                    ...   | |
     O + ((N-1)*8)| length & offset (N-1)th string           |  | |
                  |                                          |  | |
               T  | length & offset 0th translation  ---------------.
           T + 8  | length & offset 1st translation  -----------------.
                   ...                                    ...   | | | |
     T + ((N-1)*8)| length & offset (N-1)th translation      |  | | | |
                  |                                          |  | | | |
               H  | start hash table                         |  | | | |
                   ...                                    ...   | | | |
       H + S * 4  | end hash table                           |  | | | |
                  |                                          |  | | | |
                  | NUL terminated 0th string  <----------------' | | |
                  |                                          |    | | |
                  | NUL terminated 1st string  <------------------' | |
                  |                                          |      | |
                   ...                                    ...       | |
                  |                                          |      | |
                  | NUL terminated 0th translation  <---------------' |
                  |                                          |        |
                  | NUL terminated 1st translation  <-----------------'
                  |                                          |
                   ...                                    ...
                  |                                          |
                  +------------------------------------------+


File: gettext.info,  Node: Users,  Next: Programmers,  Prev: Binaries,  Up: Top

9 The User's View
*****************

When GNU `gettext' will truly have reached its goal, average users
should feel some kind of astonished pleasure, seeing the effect of that
strange kind of magic that just makes their own native language appear
everywhere on their screens.  As for naive users, they would ideally
have no special pleasure about it, merely taking their own language for
_granted_, and becoming rather unhappy otherwise.

   So, let's try to describe here how we would like the magic to
operate, as we want the users' view to be the simplest, among all ways
one could look at GNU `gettext'.  All other software engineers:
programmers, translators, maintainers, should work together in such a
way that the magic becomes possible.  This is a long and progressive
undertaking, and information is available about the progress of the
Translation Project.

   When a package is distributed, there are two kinds of users:
"installers" who fetch the distribution, unpack it, configure it,
compile it and install it for themselves or others to use; and "end
users" that call programs of the package, once these have been
installed at their site.  GNU `gettext' is offering magic for both
installers and end users.

* Menu:

* Matrix::                      The Current `ABOUT-NLS' Matrix
* Installers::                  Magic for Installers
* End Users::                   Magic for End Users


File: gettext.info,  Node: Matrix,  Next: Installers,  Prev: Users,  Up: Users

9.1 The Current `ABOUT-NLS' Matrix
==================================

Languages are not equally supported in all packages using GNU
`gettext'.  To know if some package uses GNU `gettext', one may check
the distribution for the `ABOUT-NLS' information file, for some `LL.po'
files, often kept together into some `po/' directory, or for an `intl/'
directory.  Internationalized packages have usually many `LL.po' files,
where LL represents the language.  *Note End Users:: for a complete
description of the format for LL.

   More generally, a matrix is available for showing the current state
of the Translation Project, listing which packages are prepared for
multi-lingual messages, and which languages are supported by each.
Because this information changes often, this matrix is not kept within
this GNU `gettext' manual.  This information is often found in file
`ABOUT-NLS' from various distributions, but is also as old as the
distribution itself.  A recent copy of this `ABOUT-NLS' file,
containing up-to-date information, should generally be found on the
Translation Project sites, and also on most GNU archive sites.


File: gettext.info,  Node: Installers,  Next: End Users,  Prev: Matrix,  Up: Users

9.2 Magic for Installers
========================

By default, packages fully using GNU `gettext', internally, are
installed in such a way that they to allow translation of messages.  At
_configuration_ time, those packages should automatically detect
whether the underlying host system already provides the GNU `gettext'
functions.  If not, the GNU `gettext' library should be automatically
prepared and used.  Installers may use special options at configuration
time for changing this behavior.  The command `./configure
--with-included-gettext' bypasses system `gettext' to use the included
GNU `gettext' instead, while `./configure --disable-nls' produces
programs totally unable to translate messages.

   Internationalized packages have usually many `LL.po' files.  Unless
translations are disabled, all those available are installed together
with the package.  However, the environment variable `LINGUAS' may be
set, prior to configuration, to limit the installed set.  `LINGUAS'
should then contain a space separated list of two-letter codes, stating
which languages are allowed.


File: gettext.info,  Node: End Users,  Prev: Installers,  Up: Users

9.3 Magic for End Users
=======================

We consider here those packages using GNU `gettext' internally, and for
which the installers did not disable translation at _configure_ time.
Then, users only have to set the `LANG' environment variable to the
appropriate `LL_CC' combination prior to using the programs in the
package.  *Note Matrix::.  For example, let's presume a German site.
At the shell prompt, users merely have to execute `setenv LANG de_DE'
(in `csh') or `export LANG; LANG=de_DE' (in `sh').  They could even do
this from their `.login' or `.profile' file.


File: gettext.info,  Node: Programmers,  Next: Translators,  Prev: Users,  Up: Top

10 The Programmer's View
************************

One aim of the current message catalog implementation provided by GNU
`gettext' was to use the system's message catalog handling, if the
installer wishes to do so.  So we perhaps should first take a look at
the solutions we know about.  The people in the POSIX committee did not
manage to agree on one of the semi-official standards which we'll
describe below.  In fact they couldn't agree on anything, so they
decided only to include an example of an interface.  The major Unix
vendors are split in the usage of the two most important
specifications: X/Open's catgets vs. Uniforum's gettext interface.
We'll describe them both and later explain our solution of this dilemma.

* Menu:

* catgets::                     About `catgets'
* gettext::                     About `gettext'
* Comparison::                  Comparing the two interfaces
* Using libintl.a::             Using libintl.a in own programs
* gettext grok::                Being a `gettext' grok
* Temp Programmers::            Temporary Notes for the Programmers Chapter


File: gettext.info,  Node: catgets,  Next: gettext,  Prev: Programmers,  Up: Programmers

10.1 About `catgets'
====================

The `catgets' implementation is defined in the X/Open Portability
Guide, Volume 3, XSI Supplementary Definitions, Chapter 5.  But the
process of creating this standard seemed to be too slow for some of the
Unix vendors so they created their implementations on preliminary
versions of the standard.  Of course this leads again to problems while
writing platform independent programs: even the usage of `catgets' does
not guarantee a unique interface.

   Another, personal comment on this that only a bunch of committee
members could have made this interface.  They never really tried to
program using this interface.  It is a fast, memory-saving
implementation, an user can happily live with it.  But programmers hate
it (at least I and some others do...)

   But we must not forget one point: after all the trouble with
transfering the rights on Unix(tm) they at last came to X/Open, the
very same who published this specification.  This leads me to making
the prediction that this interface will be in future Unix standards
(e.g. Spec1170) and therefore part of all Unix implementation
(implementations, which are _allowed_ to wear this name).

* Menu:

* Interface to catgets::        The interface
* Problems with catgets::       Problems with the `catgets' interface?!


File: gettext.info,  Node: Interface to catgets,  Next: Problems with catgets,  Prev: catgets,  Up: catgets

10.1.1 The Interface
--------------------

The interface to the `catgets' implementation consists of three
functions which correspond to those used in file access: `catopen' to
open the catalog for using, `catgets' for accessing the message tables,
and `catclose' for closing after work is done.  Prototypes for the
functions and the needed definitions are in the `<nl_types.h>' header
file.

   `catopen' is used like in this:

     nl_catd catd = catopen ("catalog_name", 0);

   The function takes as the argument the name of the catalog.  This
usual refers to the name of the program or the package.  The second
parameter is not further specified in the standard.  I don't even know
whether it is implemented consistently among various systems.  So the
common advice is to use `0' as the value.  The return value is a handle
to the message catalog, equivalent to handles to file returned by
`open'.

   This handle is of course used in the `catgets' function which can be
used like this:

     char *translation = catgets (catd, set_no, msg_id, "original string");

   The first parameter is this catalog descriptor.  The second parameter
specifies the set of messages in this catalog, in which the message
described by `msg_id' is obtained.  `catgets' therefore uses a
three-stage addressing:

     catalog name => set number => message ID => translation

   The fourth argument is not used to address the translation.  It is
given as a default value in case when one of the addressing stages
fail.  One important thing to remember is that although the return type
of catgets is `char *' the resulting string _must not_ be changed.  It
should better be `const char *', but the standard is published in 1988,
one year before ANSI C.

The last of these functions is used and behaves as expected:

     catclose (catd);

   After this no `catgets' call using the descriptor is legal anymore.


File: gettext.info,  Node: Problems with catgets,  Prev: Interface to catgets,  Up: catgets

10.1.2 Problems with the `catgets' Interface?!
----------------------------------------------

Now that this description seemed to be really easy -- where are the
problems we speak of?  In fact the interface could be used in a
reasonable way, but constructing the message catalogs is a pain.  The
reason for this lies in the third argument of `catgets': the unique
message ID.  This has to be a numeric value for all messages in a single
set.  Perhaps you could imagine the problems keeping such a list while
changing the source code.  Add a new message here, remove one there.  Of
course there have been developed a lot of tools helping to organize this
chaos but one as the other fails in one aspect or the other.  We don't
want to say that the other approach has no problems but they are far
more easy to manage.


File: gettext.info,  Node: gettext,  Next: Comparison,  Prev: catgets,  Up: Programmers

10.2 About `gettext'
====================

The definition of the `gettext' interface comes from a Uniforum
proposal.  It was submitted there by Sun, who had implemented the
`gettext' function in SunOS 4, around 1990.  Nowadays, the `gettext'
interface is specified by the OpenI18N standard.

   The main point about this solution is that it does not follow the
method of normal file handling (open-use-close) and that it does not
burden the programmer with so many tasks, especially the unique key
handling.  Of course here also a unique key is needed, but this key is
the message itself (how long or short it is).  See *Note Comparison::
for a more detailed comparison of the two methods.

   The following section contains a rather detailed description of the
interface.  We make it that detailed because this is the interface we
chose for the GNU `gettext' Library.  Programmers interested in using
this library will be interested in this description.

* Menu:

* Interface to gettext::        The interface
* Ambiguities::                 Solving ambiguities
* Locating Catalogs::           Locating message catalog files
* Charset conversion::          How to request conversion to Unicode
* Plural forms::                Additional functions for handling plurals
* GUI program problems::        Another technique for solving ambiguities
* Optimized gettext::           Optimization of the *gettext functions


File: gettext.info,  Node: Interface to gettext,  Next: Ambiguities,  Prev: gettext,  Up: gettext

10.2.1 The Interface
--------------------

The minimal functionality an interface must have is a) to select a
domain the strings are coming from (a single domain for all programs is
not reasonable because its construction and maintenance is difficult,
perhaps impossible) and b) to access a string in a selected domain.

   This is principally the description of the `gettext' interface.  It
has a global domain which unqualified usages reference.  Of course this
domain is selectable by the user.

     char *textdomain (const char *domain_name);

   This provides the possibility to change or query the current status
of the current global domain of the `LC_MESSAGE' category.  The
argument is a null-terminated string, whose characters must be legal in
the use in filenames.  If the DOMAIN_NAME argument is `NULL', the
function returns the current value.  If no value has been set before,
the name of the default domain is returned: _messages_.  Please note
that although the return value of `textdomain' is of type `char *' no
changing is allowed.  It is also important to know that no checks of
the availability are made.  If the name is not available you will see
this by the fact that no translations are provided.

To use a domain set by `textdomain' the function

     char *gettext (const char *msgid);

is to be used.  This is the simplest reasonable form one can imagine.
The translation of the string MSGID is returned if it is available in
the current domain.  If it is not available, the argument itself is
returned.  If the argument is `NULL' the result is undefined.

   One thing which should come into mind is that no explicit dependency
to the used domain is given.  The current value of the domain for the
`LC_MESSAGES' locale is used.  If this changes between two executions
of the same `gettext' call in the program, both calls reference a
different message catalog.

   For the easiest case, which is normally used in internationalized
packages, once at the beginning of execution a call to `textdomain' is
issued, setting the domain to a unique name, normally the package name.
In the following code all strings which have to be translated are
filtered through the gettext function.  That's all, the package speaks
your language.


File: gettext.info,  Node: Ambiguities,  Next: Locating Catalogs,  Prev: Interface to gettext,  Up: gettext

10.2.2 Solving Ambiguities
--------------------------

While this single name domain works well for most applications there
might be the need to get translations from more than one domain.  Of
course one could switch between different domains with calls to
`textdomain', but this is really not convenient nor is it fast.  A
possible situation could be one case subject to discussion during this
writing:  all error messages of functions in the set of common used
functions should go into a separate domain `error'.  By this mean we
would only need to translate them once.  Another case are messages from
a library, as these _have_ to be independent of the current domain set
by the application.

For this reasons there are two more functions to retrieve strings:

     char *dgettext (const char *domain_name, const char *msgid);
     char *dcgettext (const char *domain_name, const char *msgid,
                      int category);

   Both take an additional argument at the first place, which
corresponds to the argument of `textdomain'.  The third argument of
`dcgettext' allows to use another locale but `LC_MESSAGES'.  But I
really don't know where this can be useful.  If the DOMAIN_NAME is
`NULL' or CATEGORY has an value beside the known ones, the result is
undefined.  It should also be noted that this function is not part of
the second known implementation of this function family, the one found
in Solaris.

   A second ambiguity can arise by the fact, that perhaps more than one
domain has the same name.  This can be solved by specifying where the
needed message catalog files can be found.

     char *bindtextdomain (const char *domain_name,
                           const char *dir_name);

   Calling this function binds the given domain to a file in the
specified directory (how this file is determined follows below).
Especially a file in the systems default place is not favored against
the specified file anymore (as it would be by solely using
`textdomain').  A `NULL' pointer for the DIR_NAME parameter returns the
binding associated with DOMAIN_NAME.  If DOMAIN_NAME itself is `NULL'
nothing happens and a `NULL' pointer is returned.  Here again as for
all the other functions is true that none of the return value must be
changed!

   It is important to remember that relative path names for the
DIR_NAME parameter can be trouble.  Since the path is always computed
relative to the current directory different results will be achieved
when the program executes a `chdir' command.  Relative paths should
always be avoided to avoid dependencies and unreliabilities.


File: gettext.info,  Node: Locating Catalogs,  Next: Charset conversion,  Prev: Ambiguities,  Up: gettext

10.2.3 Locating Message Catalog Files
-------------------------------------

Because many different languages for many different packages have to be
stored we need some way to add these information to file message catalog
files.  The way usually used in Unix environments is have this encoding
in the file name.  This is also done here.  The directory name given in
`bindtextdomain's second argument (or the default directory), followed
by the value and name of the locale and the domain name are
concatenated:

     DIR_NAME/LOCALE/LC_CATEGORY/DOMAIN_NAME.mo

   The default value for DIR_NAME is system specific.  For the GNU
library, and for packages adhering to its conventions, it's:
     /usr/local/share/locale

LOCALE is the value of the locale whose name is this `LC_CATEGORY'.
For `gettext' and `dgettext' this `LC_CATEGORY' is always
`LC_MESSAGES'.(1) The value of the locale is determined through
`setlocale (LC_CATEGORY, NULL)'.  (2) `dcgettext' specifies the locale
category by the third argument.

   ---------- Footnotes ----------

   (1) Some system, eg Ultrix, don't have `LC_MESSAGES'.  Here we use a
more or less arbitrary value for it, namely 1729, the smallest positive
integer which can be represented in two different ways as the sum of
two cubes.

   (2) When the system does not support `setlocale' its behavior in
setting the locale values is simulated by looking at the environment
variables.


File: gettext.info,  Node: Charset conversion,  Next: Plural forms,  Prev: Locating Catalogs,  Up: gettext

10.2.4 How to specify the output character set `gettext' uses
-------------------------------------------------------------

`gettext' not only looks up a translation in a message catalog.  It
also converts the translation on the fly to the desired output character
set.  This is useful if the user is working in a different character set
than the translator who created the message catalog, because it avoids
distributing variants of message catalogs which differ only in the
character set.

   The output character set is, by default, the value of `nl_langinfo
(CODESET)', which depends on the `LC_CTYPE' part of the current locale.
But programs which store strings in a locale independent way (e.g.
UTF-8) can request that `gettext' and related functions return the
translations in that encoding, by use of the `bind_textdomain_codeset'
function.

   Note that the MSGID argument to `gettext' is not subject to
character set conversion.  Also, when `gettext' does not find a
translation for MSGID, it returns MSGID unchanged - independently of
the current output character set.  It is therefore recommended that all
MSGIDs be US-ASCII strings.

 -- Function: char * bind_textdomain_codeset (const char *DOMAINNAME,
          const char *CODESET)
     The `bind_textdomain_codeset' function can be used to specify the
     output character set for message catalogs for domain DOMAINNAME.
     The CODESET argument must be a valid codeset name which can be used
     for the `iconv_open' function, or a null pointer.

     If the CODESET parameter is the null pointer,
     `bind_textdomain_codeset' returns the currently selected codeset
     for the domain with the name DOMAINNAME.  It returns `NULL' if no
     codeset has yet been selected.

     The `bind_textdomain_codeset' function can be used several times.
     If used multiple times with the same DOMAINNAME argument, the
     later call overrides the settings made by the earlier one.

     The `bind_textdomain_codeset' function returns a pointer to a
     string containing the name of the selected codeset.  The string is
     allocated internally in the function and must not be changed by the
     user.  If the system went out of core during the execution of
     `bind_textdomain_codeset', the return value is `NULL' and the
     global variable ERRNO is set accordingly.


File: gettext.info,  Node: Plural forms,  Next: GUI program problems,  Prev: Charset conversion,  Up: gettext

10.2.5 Additional functions for plural forms
--------------------------------------------

The functions of the `gettext' family described so far (and all the
`catgets' functions as well) have one problem in the real world which
have been neglected completely in all existing approaches.  What is
meant here is the handling of plural forms.

   Looking through Unix source code before the time anybody thought
about internationalization (and, sadly, even afterwards) one can often
find code similar to the following:

        printf ("%d file%s deleted", n, n == 1 ? "" : "s");

After the first complaints from people internationalizing the code
people either completely avoided formulations like this or used strings
like `"file(s)"'.  Both look unnatural and should be avoided.  First
tries to solve the problem correctly looked like this:

        if (n == 1)
          printf ("%d file deleted", n);
        else
          printf ("%d files deleted", n);

   But this does not solve the problem.  It helps languages where the
plural form of a noun is not simply constructed by adding an `s' but
that is all.  Once again people fell into the trap of believing the
rules their language is using are universal.  But the handling of plural
forms differs widely between the language families.  For example, Rafal
Maszkowski `<rzm@mat.uni.torun.pl>' reports:

     In Polish we use e.g. plik (file) this way:
          1 plik
          2,3,4 pliki
          5-21 pliko'w
          22-24 pliki
          25-31 pliko'w
     and so on (o' means 8859-2 oacute which should be rather okreska,
     similar to aogonek).

   There are two things which can differ between languages (and even
inside language families);

   * The form how plural forms are built differs.  This is a problem
     with languages which have many irregularities.  German, for
     instance, is a drastic case.  Though English and German are part
     of the same language family (Germanic), the almost regular forming
     of plural noun forms (appending an `s') is hardly found in German.

   * The number of plural forms differ.  This is somewhat surprising for
     those who only have experiences with Romanic and Germanic languages
     since here the number is the same (there are two).

     But other language families have only one form or many forms.  More
     information on this in an extra section.

   The consequence of this is that application writers should not try to
solve the problem in their code.  This would be localization since it is
only usable for certain, hardcoded language environments.  Instead the
extended `gettext' interface should be used.

   These extra functions are taking instead of the one key string two
strings and a numerical argument.  The idea behind this is that using
the numerical argument and the first string as a key, the implementation
can select using rules specified by the translator the right plural
form.  The two string arguments then will be used to provide a return
value in case no message catalog is found (similar to the normal
`gettext' behavior).  In this case the rules for Germanic language is
used and it is assumed that the first string argument is the singular
form, the second the plural form.

   This has the consequence that programs without language catalogs can
display the correct strings only if the program itself is written using
a Germanic language.  This is a limitation but since the GNU C library
(as well as the GNU `gettext' package) are written as part of the GNU
package and the coding standards for the GNU project require program
being written in English, this solution nevertheless fulfills its
purpose.

 -- Function: char * ngettext (const char *MSGID1, const char *MSGID2,
          unsigned long int N)
     The `ngettext' function is similar to the `gettext' function as it
     finds the message catalogs in the same way.  But it takes two
     extra arguments.  The MSGID1 parameter must contain the singular
     form of the string to be converted.  It is also used as the key
     for the search in the catalog.  The MSGID2 parameter is the plural
     form.  The parameter N is used to determine the plural form.  If no
     message catalog is found MSGID1 is returned if `n == 1', otherwise
     `msgid2'.

     An example for the use of this function is:

          printf (ngettext ("%d file removed", "%d files removed", n), n);

     Please note that the numeric value N has to be passed to the
     `printf' function as well.  It is not sufficient to pass it only to
     `ngettext'.

 -- Function: char * dngettext (const char *DOMAIN, const char *MSGID1,
          const char *MSGID2, unsigned long int N)
     The `dngettext' is similar to the `dgettext' function in the way
     the message catalog is selected.  The difference is that it takes
     two extra parameter to provide the correct plural form.  These two
     parameters are handled in the same way `ngettext' handles them.

 -- Function: char * dcngettext (const char *DOMAIN, const char
          *MSGID1, const char *MSGID2, unsigned long int N, int
          CATEGORY)
     The `dcngettext' is similar to the `dcgettext' function in the way
     the message catalog is selected.  The difference is that it takes
     two extra parameter to provide the correct plural form.  These two
     parameters are handled in the same way `ngettext' handles them.

   Now, how do these functions solve the problem of the plural forms?
Without the input of linguists (which was not available) it was not
possible to determine whether there are only a few different forms in
which plural forms are formed or whether the number can increase with
every new supported language.

   Therefore the solution implemented is to allow the translator to
specify the rules of how to select the plural form.  Since the formula
varies with every language this is the only viable solution except for
hardcoding the information in the code (which still would require the
possibility of extensions to not prevent the use of new languages).

   The information about the plural form selection has to be stored in
the header entry of the PO file (the one with the empty `msgid' string).
The plural form information looks like this:

     Plural-Forms: nplurals=2; plural=n == 1 ? 0 : 1;

   The `nplurals' value must be a decimal number which specifies how
many different plural forms exist for this language.  The string
following `plural' is an expression which is using the C language
syntax.  Exceptions are that no negative numbers are allowed, numbers
must be decimal, and the only variable allowed is `n'.  This expression
will be evaluated whenever one of the functions `ngettext',
`dngettext', or `dcngettext' is called.  The numeric value passed to
these functions is then substituted for all uses of the variable `n' in
the expression.  The resulting value then must be greater or equal to
zero and smaller than the value given as the value of `nplurals'.

The following rules are known at this point.  The language with families
are listed.  But this does not necessarily mean the information can be
generalized for the whole family (as can be easily seen in the table
below).(1)

Only one form:
     Some languages only require one single form.  There is no
     distinction between the singular and plural form.  An appropriate
     header entry would look like this:

          Plural-Forms: nplurals=1; plural=0;

     Languages with this property include:

    Finno-Ugric family
          Hungarian

    Asian family
          Japanese, Korean, Vietnamese

    Turkic/Altaic family
          Turkish

Two forms, singular used for one only
     This is the form used in most existing programs since it is what
     English is using.  A header entry would look like this:

          Plural-Forms: nplurals=2; plural=n != 1;

     (Note: this uses the feature of C expressions that boolean
     expressions have to value zero or one.)

     Languages with this property include:

    Germanic family
          Danish, Dutch, English, Faroese, German, Norwegian, Swedish

    Finno-Ugric family
          Estonian, Finnish

    Latin/Greek family
          Greek

    Semitic family
          Hebrew

    Romanic family
          Italian, Portuguese, Spanish

    Artificial
          Esperanto

Two forms, singular used for zero and one
     Exceptional case in the language family.  The header entry would
     be:

          Plural-Forms: nplurals=2; plural=n>1;

     Languages with this property include:

    Romanic family
          French, Brazilian Portuguese

Three forms, special case for zero
     The header entry would be:

          Plural-Forms: nplurals=3; plural=n%10==1 && n%100!=11 ? 0 : n != 0 ? 1 : 2;

     Languages with this property include:

    Baltic family
          Latvian

Three forms, special cases for one and two
     The header entry would be:

          Plural-Forms: nplurals=3; plural=n==1 ? 0 : n==2 ? 1 : 2;

     Languages with this property include:

    Celtic
          Gaeilge (Irish)

Three forms, special case for numbers ending in 1[2-9]
     The header entry would look like this:

          Plural-Forms: nplurals=3; \
              plural=n%10==1 && n%100!=11 ? 0 : \
                     n%10>=2 && (n%100<10 || n%100>=20) ? 1 : 2;

     Languages with this property include:

    Baltic family
          Lithuanian

Three forms, special cases for numbers ending in 1 and 2, 3, 4, except those ending in 1[1-4]
     The header entry would look like this:

          Plural-Forms: nplurals=3; \
              plural=n%10==1 && n%100!=11 ? 0 : \
                     n%10>=2 && n%10<=4 && (n%100<10 || n%100>=20) ? 1 : 2;

     Languages with this property include:

    Slavic family
          Croatian, Serbian, Russian, Ukrainian

Three forms, special cases for 1 and 2, 3, 4
     The header entry would look like this:

          Plural-Forms: nplurals=3; \
              plural=(n==1) ? 0 : (n>=2 && n<=4) ? 1 : 2;

     Languages with this property include:

    Slavic family
          Slovak, Czech

Three forms, special case for one and some numbers ending in 2, 3, or 4
     The header entry would look like this:

          Plural-Forms: nplurals=3; \
              plural=n==1 ? 0 : \
                     n%10>=2 && n%10<=4 && (n%100<10 || n%100>=20) ? 1 : 2;

     Languages with this property include:

    Slavic family
          Polish

Four forms, special case for one and all numbers ending in 02, 03, or 04
     The header entry would look like this:

          Plural-Forms: nplurals=4; \
              plural=n%100==1 ? 0 : n%100==2 ? 1 : n%100==3 || n%100==4 ? 2 : 3;

     Languages with this property include:

    Slavic family
          Slovenian

   ---------- Footnotes ----------

   (1) Additions are welcome.  Send appropriate information to
<bug-glibc-manual@gnu.org>.


File: gettext.info,  Node: GUI program problems,  Next: Optimized gettext,  Prev: Plural forms,  Up: gettext

10.2.6 How to use `gettext' in GUI programs
-------------------------------------------

One place where the `gettext' functions, if used normally, have big
problems is within programs with graphical user interfaces (GUIs).  The
problem is that many of the strings which have to be translated are very
short.  They have to appear in pull-down menus which restricts the
length.  But strings which are not containing entire sentences or at
least large fragments of a sentence may appear in more than one
situation in the program but might have different translations.  This is
especially true for the one-word strings which are frequently used in
GUI programs.

   As a consequence many people say that the `gettext' approach is
wrong and instead `catgets' should be used which indeed does not have
this problem.  But there is a very simple and powerful method to handle
these kind of problems with the `gettext' functions.

As as example consider the following fictional situation.  A GUI program
has a menu bar with the following entries:

     +------------+------------+--------------------------------------+
     | File       | Printer    |                                      |
     +------------+------------+--------------------------------------+
     | Open     | | Select   |
     | New      | | Open     |
     +----------+ | Connect  |
                  +----------+

   To have the strings `File', `Printer', `Open', `New', `Select', and
`Connect' translated there has to be at some point in the code a call
to a function of the `gettext' family.  But in two places the string
passed into the function would be `Open'.  The translations might not
be the same and therefore we are in the dilemma described above.

   One solution to this problem is to artificially enlengthen the
strings to make them unambiguous.  But what would the program do if no
translation is available?  The enlengthened string is not what should be
printed.  So we should use a little bit modified version of the
functions.

   To enlengthen the strings a uniform method should be used.  E.g., in
the example above the strings could be chosen as

     Menu|File
     Menu|Printer
     Menu|File|Open
     Menu|File|New
     Menu|Printer|Select
     Menu|Printer|Open
     Menu|Printer|Connect

   Now all the strings are different and if now instead of `gettext'
the following little wrapper function is used, everything works just
fine:

       char *
       sgettext (const char *msgid)
       {
         char *msgval = gettext (msgid);
         if (msgval == msgid)
           msgval = strrchr (msgid, '|') + 1;
         return msgval;
       }

   What this little function does is to recognize the case when no
translation is available.  This can be done very efficiently by a
pointer comparison since the return value is the input value.  If there
is no translation we know that the input string is in the format we used
for the Menu entries and therefore contains a `|' character.  We simply
search for the last occurrence of this character and return a pointer
to the character following it.  That's it!

   If one now consistently uses the enlengthened string form and
replaces the `gettext' calls with calls to `sgettext' (this is normally
limited to very few places in the GUI implementation) then it is
possible to produce a program which can be internationalized.

   The other `gettext' functions (`dgettext', `dcgettext' and the
`ngettext' equivalents) can and should have corresponding functions as
well which look almost identical, except for the parameters and the
call to the underlying function.

   Now there is of course the question why such functions do not exist
in the GNU gettext package?  There are two parts of the answer to this
question.

   * They are easy to write and therefore can be provided by the
     project they are used in.  This is not an answer by itself and
     must be seen together with the second part which is:

   * There is no way the gettext package can contain a version which
     can work everywhere.  The problem is the selection of the
     character to separate the prefix from the actual string in the
     enlenghtened string.  The examples above used `|' which is a quite
     good choice because it resembles a notation frequently used in
     this context and it also is a character not often used in message
     strings.

     But what if the character is used in message strings?  Or if the
     chose character is not available in the character set on the
     machine one compiles (e.g., `|' is not required to exist for
     ISO C; this is why the `iso646.h' file exists in ISO C programming
     environments).

   There is only one more comment to be said.  The wrapper function
above requires that the translations strings are not enlengthened
themselves.  This is only logical.  There is no need to disambiguate
the strings (since they are never used as keys for a search) and one
also saves quite some memory and disk space by doing this.


File: gettext.info,  Node: Optimized gettext,  Prev: GUI program problems,  Up: gettext

10.2.7 Optimization of the *gettext functions
---------------------------------------------

At this point of the discussion we should talk about an advantage of the
GNU `gettext' implementation.  Some readers might have pointed out that
an internationalized program might have a poor performance if some
string has to be translated in an inner loop.  While this is unavoidable
when the string varies from one run of the loop to the other it is
simply a waste of time when the string is always the same.  Take the
following example:

     {
       while (...)
         {
           puts (gettext ("Hello world"));
         }
     }

When the locale selection does not change between two runs the resulting
string is always the same.  One way to use this is:

     {
       str = gettext ("Hello world");
       while (...)
         {
           puts (str);
         }
     }

But this solution is not usable in all situation (e.g. when the locale
selection changes) nor does it lead to legible code.

   For this reason, GNU `gettext' caches previous translation results.
When the same translation is requested twice, with no new message
catalogs being loaded in between, `gettext' will, the second time, find
the result through a single cache lookup.


File: gettext.info,  Node: Comparison,  Next: Using libintl.a,  Prev: gettext,  Up: Programmers

10.3 Comparing the Two Interfaces
=================================

The following discussion is perhaps a little bit colored.  As said
above we implemented GNU `gettext' following the Uniforum proposal and
this surely has its reasons.  But it should show how we came to this
decision.

   First we take a look at the developing process.  When we write an
application using NLS provided by `gettext' we proceed as always.  Only
when we come to a string which might be seen by the users and thus has
to be translated we use `gettext("...")' instead of `"..."'.  At the
beginning of each source file (or in a central header file) we define

     #define gettext(String) (String)

   Even this definition can be avoided when the system supports the
`gettext' function in its C library.  When we compile this code the
result is the same as if no NLS code is used.  When  you take a look at
the GNU `gettext' code you will see that we use `_("...")' instead of
`gettext("...")'.  This reduces the number of additional characters per
translatable string to _3_ (in words: three).

   When now a production version of the program is needed we simply
replace the definition

     #define _(String) (String)

by

     #include <libintl.h>
     #define _(String) gettext (String)

Additionally we run the program `xgettext' on all source code file
which contain translatable strings and that's it: we have a running
program which does not depend on translations to be available, but which
can use any that becomes available.

   The same procedure can be done for the `gettext_noop' invocations
(*note Special cases::).  One usually defines `gettext_noop' as a no-op
macro.  So you should consider the following code for your project:

     #define gettext_noop(String) String
     #define N_(String) gettext_noop (String)

   `N_' is a short form similar to `_'.  The `Makefile' in the `po/'
directory of GNU `gettext' knows by default both of the mentioned short
forms so you are invited to follow this proposal for your own ease.

   Now to `catgets'.  The main problem is the work for the programmer.
Every time he comes to a translatable string he has to define a number
(or a symbolic constant) which has also be defined in the message
catalog file.  He also has to take care for duplicate entries,
duplicate message IDs etc.  If he wants to have the same quality in the
message catalog as the GNU `gettext' program provides he also has to
put the descriptive comments for the strings and the location in all
source code files in the message catalog.  This is nearly a Mission:
Impossible.

   But there are also some points people might call advantages speaking
for `catgets'.  If you have a single word in a string and this string
is used in different contexts it is likely that in one or the other
language the word has different translations.  Example:

     printf ("%s: %d", gettext ("number"), number_of_errors)

     printf ("you should see %d %s", number_count,
             number_count == 1 ? gettext ("number") : gettext ("numbers"))

   Here we have to translate two times the string `"number"'.  Even if
you do not speak a language beside English it might be possible to
recognize that the two words have a different meaning.  In German the
first appearance has to be translated to `"Anzahl"' and the second to
`"Zahl"'.

   Now you can say that this example is really esoteric.  And you are
right!  This is exactly how we felt about this problem and decide that
it does not weight that much.  The solution for the above problem could
be very easy:

     printf ("%s %d", gettext ("number:"), number_of_errors)

     printf (number_count == 1 ? gettext ("you should see %d number")
                               : gettext ("you should see %d numbers"),
             number_count)

   We believe that we can solve all conflicts with this method.  If it
is difficult one can also consider changing one of the conflicting
string a little bit.  But it is not impossible to overcome.

   `catgets' allows same original entry to have different translations,
but `gettext' has another, scalable approach for solving ambiguities of
this kind: *Note Ambiguities::.


File: gettext.info,  Node: Using libintl.a,  Next: gettext grok,  Prev: Comparison,  Up: Programmers

10.4 Using libintl.a in own programs
====================================

Starting with version 0.9.4 the library `libintl.h' should be
self-contained.  I.e., you can use it in your own programs without
providing additional functions.  The `Makefile' will put the header and
the library in directories selected using the `$(prefix)'.


File: gettext.info,  Node: gettext grok,  Next: Temp Programmers,  Prev: Using libintl.a,  Up: Programmers

10.5 Being a `gettext' grok
===========================

To fully exploit the functionality of the GNU `gettext' library it is
surely helpful to read the source code.  But for those who don't want
to spend that much time in reading the (sometimes complicated) code here
is a list comments:

   * Changing the language at runtime 

     For interactive programs it might be useful to offer a selection
     of the used language at runtime.  To understand how to do this one
     need to know how the used language is determined while executing
     the `gettext' function.  The method which is presented here only
     works correctly with the GNU implementation of the `gettext'
     functions.

     In the function `dcgettext' at every call the current setting of
     the highest priority environment variable is determined and used.
     Highest priority means here the following list with decreasing
     priority:

       1. `LANGUAGE' 

       2. `LC_ALL' 

       3. `LC_xxx', according to selected locale 

       4. `LANG'

     Afterwards the path is constructed using the found value and the
     translation file is loaded if available.

     What happens now when the value for, say, `LANGUAGE' changes?
     According to the process explained above the new value of this
     variable is found as soon as the `dcgettext' function is called.
     But this also means the (perhaps) different message catalog file
     is loaded.  In other words: the used language is changed.

     But there is one little hook.  The code for gcc-2.7.0 and up
     provides some optimization.  This optimization normally prevents
     the calling of the `dcgettext' function as long as no new catalog
     is loaded.  But if `dcgettext' is not called the program also
     cannot find the `LANGUAGE' variable be changed (*note Optimized
     gettext::).  A solution for this is very easy.  Include the
     following code in the language switching function.

            /* Change language.  */
            setenv ("LANGUAGE", "fr", 1);

            /* Make change known.  */
            {
              extern int  _nl_msg_cat_cntr;
              ++_nl_msg_cat_cntr;
            }

     The variable `_nl_msg_cat_cntr' is defined in `loadmsgcat.c'.  You
     don't need to know what this is for.  But it can be used to detect
     whether a `gettext' implementation is GNU gettext and not non-GNU
     system's native gettext implementation.



File: gettext.info,  Node: Temp Programmers,  Prev: gettext grok,  Up: Programmers

10.6 Temporary Notes for the Programmers Chapter
================================================

* Menu:

* Temp Implementations::        Temporary - Two Possible Implementations
* Temp catgets::                Temporary - About `catgets'
* Temp WSI::                    Temporary - Why a single implementation
* Temp Notes::                  Temporary - Notes


File: gettext.info,  Node: Temp Implementations,  Next: Temp catgets,  Prev: Temp Programmers,  Up: Temp Programmers

10.6.1 Temporary - Two Possible Implementations
-----------------------------------------------

There are two competing methods for language independent messages: the
X/Open `catgets' method, and the Uniforum `gettext' method.  The
`catgets' method indexes messages by integers; the `gettext' method
indexes them by their English translations.  The `catgets' method has
been around longer and is supported by more vendors.  The `gettext'
method is supported by Sun, and it has been heard that the COSE
multi-vendor initiative is supporting it.  Neither method is a POSIX
standard; the POSIX.1 committee had a lot of disagreement in this area.

   Neither one is in the POSIX standard.  There was much disagreement
in the POSIX.1 committee about using the `gettext' routines vs.
`catgets' (XPG).  In the end the committee couldn't agree on anything,
so no messaging system was included as part of the standard.  I believe
the informative annex of the standard includes the XPG3 messaging
interfaces, "...as an example of a messaging system that has been
implemented..."

   They were very careful not to say anywhere that you should use one
set of interfaces over the other.  For more on this topic please see
the Programming for Internationalization FAQ.


File: gettext.info,  Node: Temp catgets,  Next: Temp WSI,  Prev: Temp Implementations,  Up: Temp Programmers

10.6.2 Temporary - About `catgets'
----------------------------------

There have been a few discussions of late on the use of `catgets' as a
base.  I think it important to present both sides of the argument and
hence am opting to play devil's advocate for a little bit.

   I'll not deny the fact that `catgets' could have been designed a lot
better.  It currently has quite a number of limitations and these have
already been pointed out.

   However there is a great deal to be said for consistency and
standardization.  A common recurring problem when writing Unix software
is the myriad portability problems across Unix platforms.  It seems as
if every Unix vendor had a look at the operating system and found parts
they could improve upon.  Undoubtedly, these modifications are probably
innovative and solve real problems.  However, software developers have
a hard time keeping up with all these changes across so many platforms.

   And this has prompted the Unix vendors to begin to standardize their
systems.  Hence the impetus for Spec1170.  Every major Unix vendor has
committed to supporting this standard and every Unix software developer
waits with glee the day they can write software to this standard and
simply recompile (without having to use autoconf) across different
platforms.

   As I understand it, Spec1170 is roughly based upon version 4 of the
X/Open Portability Guidelines (XPG4).  Because `catgets' and friends
are defined in XPG4, I'm led to believe that `catgets' is a part of
Spec1170 and hence will become a standardized component of all Unix
systems.


File: gettext.info,  Node: Temp WSI,  Next: Temp Notes,  Prev: Temp catgets,  Up: Temp Programmers

10.6.3 Temporary - Why a single implementation
----------------------------------------------

Now it seems kind of wasteful to me to have two different systems
installed for accessing message catalogs.  If we do want to remedy
`catgets' deficiencies why don't we try to expand `catgets' (in a
compatible manner) rather than implement an entirely new system.
Otherwise, we'll end up with two message catalog access systems
installed with an operating system - one set of routines for packages
using GNU `gettext' for their internationalization, and another set of
routines (catgets) for all other software.  Bloated?

   Supposing another catalog access system is implemented.  Which do we
recommend?  At least for Linux, we need to attract as many software
developers as possible.  Hence we need to make it as easy for them to
port their software as possible.  Which means supporting `catgets'.  We
will be implementing the `libintl' code within our `libc', but does
this mean we also have to incorporate another message catalog access
scheme within our `libc' as well?  And what about people who are going
to be using the `libintl' + non-`catgets' routines.  When they port
their software to other platforms, they're now going to have to include
the front-end (`libintl') code plus the back-end code (the non-`catgets'
access routines) with their software instead of just including the
`libintl' code with their software.

   Message catalog support is however only the tip of the iceberg.
What about the data for the other locale categories.  They also have a
number of deficiencies.  Are we going to abandon them as well and
develop another duplicate set of routines (should `libintl' expand
beyond message catalog support)?

   Like many parts of Unix that can be improved upon, we're stuck with
balancing compatibility with the past with useful improvements and
innovations for the future.


File: gettext.info,  Node: Temp Notes,  Prev: Temp WSI,  Up: Temp Programmers

10.6.4 Temporary - Notes
------------------------

X/Open agreed very late on the standard form so that many
implementations differ from the final form.  Both of my system (old
Linux catgets and Ultrix-4) have a strange variation.

   OK.  After incorporating the last changes I have to spend some time
on making the GNU/Linux `libc' `gettext' functions.  So in future
Solaris is not the only system having `gettext'.


File: gettext.info,  Node: Translators,  Next: Maintainers,  Prev: Programmers,  Up: Top

11 The Translator's View
************************

* Menu:

* Trans Intro 0::               Introduction 0
* Trans Intro 1::               Introduction 1
* Discussions::                 Discussions
* Organization::                Organization
* Information Flow::            Information Flow
* Prioritizing messages::       How to find which messages to translate first


File: gettext.info,  Node: Trans Intro 0,  Next: Trans Intro 1,  Prev: Translators,  Up: Translators

11.1 Introduction 0
===================

Free software is going international!  The Translation Project is a way
to get maintainers, translators and users all together, so free software
will gradually become able to speak many native languages.

   The GNU `gettext' tool set contains _everything_ maintainers need
for internationalizing their packages for messages.  It also contains
quite useful tools for helping translators at localizing messages to
their native language, once a package has already been
internationalized.

   To achieve the Translation Project, we need many interested people
who like their own language and write it well, and who are also able to
synergize with other translators speaking the same language.  If you'd
like to volunteer to _work_ at translating messages, please send mail
to your translating team.

   Each team has its own mailing list, courtesy of Linux International.
You may reach your translating team at the address `LL@li.org',
replacing LL by the two-letter ISO 639 code for your language.
Language codes are _not_ the same as country codes given in ISO 3166.
The following translating teams exist:

     Chinese `zh', Czech `cs', Danish `da', Dutch `nl', Esperanto `eo',
     Finnish `fi', French `fr', Irish `ga', German `de', Greek `el',
     Italian `it', Japanese `ja', Indonesian `in', Norwegian `no',
     Polish `pl', Portuguese `pt', Russian `ru', Spanish `es', Swedish
     `sv' and Turkish `tr'.

For example, you may reach the Chinese translating team by writing to
`zh@li.org'.  When you become a member of the translating team for your
own language, you may subscribe to its list.  For example, Swedish
people can send a message to `sv-request@li.org', having this message
body:

     subscribe

   Keep in mind that team members should be interested in _working_ at
translations, or at solving translational difficulties, rather than
merely lurking around.  If your team does not exist yet and you want to
start one, please write to `translation@iro.umontreal.ca'; you will
then reach the coordinator for all translator teams.

   A handful of GNU packages have already been adapted and provided
with message translations for several languages.  Translation teams
have begun to organize, using these packages as a starting point.  But
there are many more packages and many languages for which we have no
volunteer translators.  If you would like to volunteer to work at
translating messages, please send mail to
`translation@iro.umontreal.ca' indicating what language(s) you can work
on.


File: gettext.info,  Node: Trans Intro 1,  Next: Discussions,  Prev: Trans Intro 0,  Up: Translators

11.2 Introduction 1
===================

This is now official, GNU is going international!  Here is the
announcement submitted for the January 1995 GNU Bulletin:

     A handful of GNU packages have already been adapted and provided
     with message translations for several languages.  Translation
     teams have begun to organize, using these packages as a starting
     point.  But there are many more packages and many languages for
     which we have no volunteer translators.  If you'd like to
     volunteer to work at translating messages, please send mail to
     `translation@iro.umontreal.ca' indicating what language(s) you can
     work on.

   This document should answer many questions for those who are curious
about the process or would like to contribute.  Please at least skim
over it, hoping to cut down a little of the high volume of e-mail
generated by this collective effort towards internationalization of
free software.

   Most free programming which is widely shared is done in English, and
currently, English is used as the main communicating language between
national communities collaborating to free software.  This very document
is written in English.  This will not change in the foreseeable future.

   However, there is a strong appetite from national communities for
having more software able to write using national language and habits,
and there is an on-going effort to modify free software in such a way
that it becomes able to do so.  The experiments driven so far raised an
enthusiastic response from pretesters, so we believe that
internationalization of free software is dedicated to succeed.

   For suggestion clarifications, additions or corrections to this
document, please e-mail to `translation@iro.umontreal.ca'.


File: gettext.info,  Node: Discussions,  Next: Organization,  Prev: Trans Intro 1,  Up: Translators

11.3 Discussions
================

Facing this internationalization effort, a few users expressed their
concerns.  Some of these doubts are presented and discussed, here.

   * Smaller groups

     Some languages are not spoken by a very large number of people, so
     people speaking them sometimes consider that there may not be all
     that much demand such versions of free software packages.
     Moreover, many people being _into computers_, in some countries,
     generally seem to prefer English versions of their software.

     On the other end, people might enjoy their own language a lot, and
     be very motivated at providing to themselves the pleasure of
     having their beloved free software speaking their mother tongue.
     They do themselves a personal favor, and do not pay that much
     attention to the number of people benefiting of their work.

   * Misinterpretation

     Other users are shy to push forward their own language, seeing in
     this some kind of misplaced propaganda.  Someone thought there
     must be some users of the language over the networks pestering
     other people with it.

     But any spoken language is worth localization, because there are
     people behind the language for whom the language is important and
     dear to their hearts.

   * Odd translations

     The biggest problem is to find the right translations so that
     everybody can understand the messages.  Translations are usually a
     little odd.  Some people get used to English, to the extent they
     may find translations into their own language "rather pushy,
     obnoxious and sometimes even hilarious."  As a French speaking
     man, I have the experience of those instruction manuals for goods,
     so poorly translated in French in Korea or Taiwan...

     The fact is that we sometimes have to create a kind of national
     computer culture, and this is not easy without the collaboration of
     many people liking their mother tongue.  This is why translations
     are better achieved by people knowing and loving their own
     language, and ready to work together at improving the results they
     obtain.

   * Dependencies over the GPL or LGPL

     Some people wonder if using GNU `gettext' necessarily brings their
     package under the protective wing of the GNU General Public
     License or the GNU Library General Public License, when they do
     not want to make their program free, or want other kinds of
     freedom.  The simplest answer is "normally not".

     The `gettext-runtime' part of GNU `gettext', i.e. the contents of
     `libintl', is covered by the GNU Library General Public License.
     The `gettext-tools' part of GNU `gettext', i.e. the rest of the
     GNU `gettext' package, is covered by the GNU General Public
     License.

     The mere marking of localizable strings in a package, or
     conditional inclusion of a few lines for initialization, is not
     really including GPL'ed or LGPL'ed code.  However, since the
     localization routines in `libintl' are under the LGPL, the LGPL
     needs to be considered.  It gives the right to distribute the
     complete unmodified source of `libintl' even with non-free
     programs.  It also gives the right to use `libintl' as a shared
     library, even for non-free programs.  But it gives the right to
     use `libintl' as a static library or to incorporate `libintl' into
     another library only to free software.



File: gettext.info,  Node: Organization,  Next: Information Flow,  Prev: Discussions,  Up: Translators

11.4 Organization
=================

On a larger scale, the true solution would be to organize some kind of
fairly precise set up in which volunteers could participate.  I gave
some thought to this idea lately, and realize there will be some touchy
points.  I thought of writing to Richard Stallman to launch such a
project, but feel it might be good to shake out the ideas between
ourselves first.  Most probably that Linux International has some
experience in the field already, or would like to orchestrate the
volunteer work, maybe.  Food for thought, in any case!

   I guess we have to setup something early, somehow, that will help
many possible contributors of the same language to interlock and avoid
work duplication, and further be put in contact for solving together
problems particular to their tongue (in most languages, there are many
difficulties peculiar to translating technical English).  My Swedish
contributor acknowledged these difficulties, and I'm well aware of them
for French.

   This is surely not a technical issue, but we should manage so the
effort of locale contributors be maximally useful, despite the national
team layer interface between contributors and maintainers.

   The Translation Project needs some setup for coordinating language
coordinators.  Localizing evolving programs will surely become a
permanent and continuous activity in the free software community, once
well started.  The setup should be minimally completed and tested
before GNU `gettext' becomes an official reality.  The e-mail address
`translation@iro.umontreal.ca' has been setup for receiving offers from
volunteers and general e-mail on these topics.  This address reaches
the Translation Project coordinator.

* Menu:

* Central Coordination::        Central Coordination
* National Teams::              National Teams
* Mailing Lists::               Mailing Lists


File: gettext.info,  Node: Central Coordination,  Next: National Teams,  Prev: Organization,  Up: Organization

11.4.1 Central Coordination
---------------------------

I also think GNU will need sooner than it thinks, that someone setup a
way to organize and coordinate these groups.  Some kind of group of
groups.  My opinion is that it would be good that GNU delegates this
task to a small group of collaborating volunteers, shortly.  Perhaps in
`gnu.announce' a list of this national committee's can be published.

   My role as coordinator would simply be to refer to Ulrich any German
speaking volunteer interested to localization of free software
packages, and maybe helping national groups to initially organize,
while maintaining national registries for until national groups are
ready to take over.  In fact, the coordinator should ease volunteers to
get in contact with one another for creating national teams, which
should then select one coordinator per language, or country
(regionalized language).  If well done, the coordination should be
useful without being an overwhelming task, the time to put delegations
in place.


File: gettext.info,  Node: National Teams,  Next: Mailing Lists,  Prev: Central Coordination,  Up: Organization

11.4.2 National Teams
---------------------

I suggest we look for volunteer coordinators/editors for individual
languages.  These people will scan contributions of translation files
for various programs, for their own languages, and will ensure high and
uniform standards of diction.

   From my current experience with other people in these days, those who
provide localizations are very enthusiastic about the process, and are
more interested in the localization process than in the program they
localize, and want to do many programs, not just one.  This seems to
confirm that having a coordinator/editor for each language is a good
idea.

   We need to choose someone who is good at writing clear and concise
prose in the language in question.  That is hard--we can't check it
ourselves.  So we need to ask a few people to judge each others'
writing and select the one who is best.

   I announce my prerelease to a few dozen people, and you would not
believe all the discussions it generated already.  I shudder to think
what will happen when this will be launched, for true, officially,
world wide.  Who am I to arbitrate between two Czekolsovak users
contradicting each other, for example?

   I assume that your German is not much better than my French so that
I would not be able to judge about these formulations.  What I would
suggest is that for each language there is a group for people who
maintain the PO files and judge about changes.  I suspect there will be
cultural differences between how such groups of people will behave.
Some will have relaxed ways, reach consensus easily, and have anyone of
the group relate to the maintainers, while others will fight to death,
organize heavy administrations up to national standards, and use strict
channels.

   The German team is putting out a good example.  Right now, they are
maybe half a dozen people revising translations of each other and
discussing the linguistic issues.  I do not even have all the names.
Ulrich Drepper is taking care of coordinating the German team.  He
subscribed to all my pretest lists, so I do not even have to warn him
specifically of incoming releases.

   I'm sure, that is a good idea to get teams for each language working
on translations.  That will make the translations better and more
consistent.

* Menu:

* Sub-Cultures::                Sub-Cultures
* Organizational Ideas::        Organizational Ideas


File: gettext.info,  Node: Sub-Cultures,  Next: Organizational Ideas,  Prev: National Teams,  Up: National Teams

11.4.2.1 Sub-Cultures
.....................

Taking French for example, there are a few sub-cultures around computers
which developed diverging vocabularies.  Picking volunteers here and
there without addressing this problem in an organized way, soon in the
project, might produce a distasteful mix of internationalized programs,
and possibly trigger endless quarrels among those who really care.

   Keeping some kind of unity in the way French localization of
internationalized programs is achieved is a difficult (and delicate)
job.  Knowing the latin character of French people (:-), if we take this
the wrong way, we could end up nowhere, or spoil a lot of energies.
Maybe we should begin to address this problem seriously _before_ GNU
`gettext' become officially published.  And I suspect that this means
soon!


File: gettext.info,  Node: Organizational Ideas,  Prev: Sub-Cultures,  Up: National Teams

11.4.2.2 Organizational Ideas
.............................

I expect the next big changes after the official release.  Please note
that I use the German translation of the short GPL message.  We need to
set a few good examples before the localization goes out for true in
the free software community.  Here are a few points to discuss:

   * Each group should have one FTP server (at least one master).

   * The files on the server should reflect the latest version (of
     course!) and it should also contain a RCS directory with the
     corresponding archives (I don't have this now).

   * There should also be a ChangeLog file (this is more useful than the
     RCS archive but can be generated automatically from the later by
     Emacs).

   * A "core group" should judge about questionable changes (for now
     this group consists solely by me but I ask some others
     occasionally; this also seems to work).



File: gettext.info,  Node: Mailing Lists,  Prev: National Teams,  Up: Organization

11.4.3 Mailing Lists
--------------------

If we get any inquiries about GNU `gettext', send them on to:

     `translation@iro.umontreal.ca'

   The `*-pretest' lists are quite useful to me, maybe the idea could
be generalized to many GNU, and non-GNU packages.  But each maintainer
his/her way!

   Franc,ois, we have a mechanism in place here at `gnu.ai.mit.edu' to
track teams, support mailing lists for them and log members.  We have a
slight preference that you use it.  If this is OK with you, I can get
you clued in.

   Things are changing!  A few years ago, when Daniel Fekete and I
asked for a mailing list for GNU localization, nested at the FSF, we
were politely invited to organize it anywhere else, and so did we.  For
communicating with my pretesters, I later made a handful of mailing
lists located at iro.umontreal.ca and administrated by `majordomo'.
These lists have been _very_ dependable so far...

   I suspect that the German team will organize itself a mailing list
located in Germany, and so forth for other countries.  But before they
organize for true, it could surely be useful to offer mailing lists
located at the FSF to each national team.  So yes, please explain me
how I should proceed to create and handle them.

   We should create temporary mailing lists, one per country, to help
people organize.  Temporary, because once regrouped and structured, it
would be fair the volunteers from country bring back _their_ list in
there and manage it as they want.  My feeling is that, in the long run,
each team should run its own list, from within their country.  There
also should be some central list to which all teams could subscribe as
they see fit, as long as each team is represented in it.


File: gettext.info,  Node: Information Flow,  Next: Prioritizing messages,  Prev: Organization,  Up: Translators

11.5 Information Flow
=====================

There will surely be some discussion about this messages after the
packages are finally released.  If people now send you some proposals
for better messages, how do you proceed?  Jim, please note that right
now, as I put forward nearly a dozen of localizable programs, I receive
both the translations and the coordination concerns about them.

   If I put one of my things to pretest, Ulrich receives the
announcement and passes it on to the German team, who make last minute
revisions.  Then he submits the translation files to me _as the
maintainer_.  For free packages I do not maintain, I would not even
hear about it.  This scheme could be made to work for the whole
Translation Project, I think.  For security reasons, maybe Ulrich
(national coordinators, in fact) should update central registry kept at
the Translation Project (Jim, me, or Len's recruits) once in a while.

   In December/January, I was aggressively ready to internationalize
all of GNU, giving myself the duty of one small GNU package per week or
so, taking many weeks or months for bigger packages.  But it does not
work this way.  I first did all the things I'm responsible for.  I've
nothing against some missionary work on other maintainers, but I'm also
loosing a lot of energy over it--same debates over again.

   And when the first localized packages are released we'll get a lot of
responses about ugly translations :-).  Surely, and we need to have
beforehand a fairly good idea about how to handle the information flow
between the national teams and the package maintainers.

   Please start saving somewhere a quick history of each PO file.  I
know for sure that the file format will change, allowing for comments.
It would be nice that each file has a kind of log, and references for
those who want to submit comments or gripes, or otherwise contribute.
I sent a proposal for a fast and flexible format, but it is not
receiving acceptance yet by the GNU deciders.  I'll tell you when I
have more information about this.


File: gettext.info,  Node: Prioritizing messages,  Prev: Information Flow,  Up: Translators

11.6 Prioritizing messages: How to determine which messages to translate first
==============================================================================

A translator sometimes has only a limited amount of time per week to
spend on a package, and some packages have quite large message catalogs
(over 1000 messages).  Therefore she wishes to translate the messages
first that are the most visible to the user, or that occur most
frequently.  This section describes how to determine these "most
urgent" messages.  It also applies to determine the "next most urgent"
messages after the message catalog has already been partially
translated.

   In a first step, she uses the programs like a user would do.  While
she does this, the GNU `gettext' library logs into a file the not yet
translated messages for which a translation was requested from the
program.

   In a second step, she uses the PO mode to translate precisely this
set of messages.

   Here a more details.  The GNU `libintl' library (but not the
corresponding functions in GNU `libc') supports an environment variable
`GETTEXT_LOG_UNTRANSLATED'.  The GNU `libintl' library will log into
this file the messages for which `gettext()' and related functions
couldn't find the translation.  If the file doesn't exist, it will be
created as needed.  On systems with GNU `libc' a shared library
`preloadable_libintl.so' is provided that can be used with the ELF
`LD_PRELOAD' mechanism.

   So, in the first step, the translator uses these commands on systems
with GNU `libc':

     $ LD_PRELOAD=/usr/local/lib/preloadable_libintl.so
     $ export LD_PRELOAD
     $ GETTEXT_LOG_UNTRANSLATED=$HOME/gettextlogused
     $ export GETTEXT_LOG_UNTRANSLATED

and these commands on other systems:

     $ GETTEXT_LOG_UNTRANSLATED=$HOME/gettextlogused
     $ export GETTEXT_LOG_UNTRANSLATED

   Then she uses and peruses the programs.  (It is a good and
recommended practice to use the programs for which you provide
translations: it gives you the needed context.)  When done, she removes
the environment variables:

     $ unset LD_PRELOAD
     $ unset GETTEXT_LOG_UNTRANSLATED

   The second step starts with removing duplicates:

     $ msguniq $HOME/gettextlogused > missing.po

   The result is a PO file, but needs some preprocessing before the
Emacs PO mode can be used with it.  First, it is a multi-domain PO
file, containing messages from many translation domains.  Second, it
lacks all translator comments and source references.  Here is how to
get a list of the affected translation domains:

     $ sed -n -e 's,^domain "\(.*\)"$,\1,p' < missing.po | sort | uniq

   Then the translator can handle the domains one by one.  For
simplicity, let's use environment variables to denote the language,
domain and source package.

     $ lang=nl             # your language
     $ domain=coreutils    # the name of the domain to be handled
     $ package=/usr/src/gnu/coreutils-4.5.4   # the package where it comes from

   She takes the latest copy of `$lang.po' from the Translation Project,
or from the package (in most cases, `$package/po/$lang.po'), or creates
a fresh one if she's the first translator (see *Note Creating::).  She
then uses the following commands to mark the not urgent messages as
"obsolete".  (This doesn't mean that these messages - translated and
untranslated ones - will go away.  It simply means that Emacs PO mode
will ignore them in the following editing session.)

     $ msggrep --domain=$domain missing.po | grep -v '^domain' \
       > $domain-missing.po
     $ msgattrib --set-obsolete --ignore-file $domain-missing.po $domain.$lang.po \
       > $domain.$lang-urgent.po

   The she translates `$domain.$lang-urgent.po' by use of Emacs PO mode.
(FIXME: I don't know whether `KBabel' and `gtranslator' also preserve
obsolete messages, as they should.)  Finally she restores the not
urgent messages (with their earlier translations, for those which were
already translated) through this command:

     $ msgmerge --no-fuzzy-matching $domain.$lang-urgent.po $package/po/$domain.pot \
       > $domain.$lang.po

   Then she can submit `$domain.$lang.po' and proceed to the next
domain.


File: gettext.info,  Node: Maintainers,  Next: Programming Languages,  Prev: Translators,  Up: Top

12 The Maintainer's View
************************

The maintainer of a package has many responsibilities.  One of them is
ensuring that the package will install easily on many platforms, and
that the magic we described earlier (*note Users::) will work for
installers and end users.

   Of course, there are many possible ways by which GNU `gettext' might
be integrated in a distribution, and this chapter does not cover them
in all generality.  Instead, it details one possible approach which is
especially adequate for many free software distributions following GNU
standards, or even better, Gnits standards, because GNU `gettext' is
purposely for helping the internationalization of the whole GNU
project, and as many other good free packages as possible.  So, the
maintainer's view presented here presumes that the package already has
a `configure.in' file and uses GNU Autoconf.

   Nevertheless, GNU `gettext' may surely be useful for free packages
not following GNU standards and conventions, but the maintainers of such
packages might have to show imagination and initiative in organizing
their distributions so `gettext' work for them in all situations.
There are surely many, out there.

   Even if `gettext' methods are now stabilizing, slight adjustments
might be needed between successive `gettext' versions, so you should
ideally revise this chapter in subsequent releases, looking for changes.

* Menu:

* Flat and Non-Flat::           Flat or Non-Flat Directory Structures
* Prerequisites::               Prerequisite Works
* gettextize Invocation::       Invoking the `gettextize' Program
* Adjusting Files::             Files You Must Create or Alter
* autoconf macros::             Autoconf macros for use in `configure.in'
* CVS Issues::                  Integrating with CVS
* Release Management::          Creating a Distribution Tarball


File: gettext.info,  Node: Flat and Non-Flat,  Next: Prerequisites,  Prev: Maintainers,  Up: Maintainers

12.1 Flat or Non-Flat Directory Structures
==========================================

Some free software packages are distributed as `tar' files which unpack
in a single directory, these are said to be "flat" distributions.
Other free software packages have a one level hierarchy of
subdirectories, using for example a subdirectory named `doc/' for the
Texinfo manual and man pages, another called `lib/' for holding
functions meant to replace or complement C libraries, and a
subdirectory `src/' for holding the proper sources for the package.
These other distributions are said to be "non-flat".

   We cannot say much about flat distributions.  A flat directory
structure has the disadvantage of increasing the difficulty of updating
to a new version of GNU `gettext'.  Also, if you have many PO files,
this could somewhat pollute your single directory.  Also, GNU
`gettext''s libintl sources consist of C sources, shell scripts, `sed'
scripts and complicated Makefile rules, which don't fit well into an
existing flat structure.  For these reasons, we recommend to use
non-flat approach in this case as well.

   Maybe because GNU `gettext' itself has a non-flat structure, we have
more experience with this approach, and this is what will be described
in the remaining of this chapter.  Some maintainers might use this as
an opportunity to unflatten their package structure.


File: gettext.info,  Node: Prerequisites,  Next: gettextize Invocation,  Prev: Flat and Non-Flat,  Up: Maintainers

12.2 Prerequisite Works
=======================

There are some works which are required for using GNU `gettext' in one
of your package.  These works have some kind of generality that escape
the point by point descriptions used in the remainder of this chapter.
So, we describe them here.

   * Before attempting to use `gettextize' you should install some
     other packages first.  Ensure that recent versions of GNU `m4',
     GNU Autoconf and GNU `gettext' are already installed at your site,
     and if not, proceed to do this first.  If you get to install these
     things, beware that GNU `m4' must be fully installed before GNU
     Autoconf is even _configured_.

     To further ease the task of a package maintainer the `automake'
     package was designed and implemented.  GNU `gettext' now uses this
     tool and the `Makefile's in the `intl/' and `po/' therefore know
     about all the goals necessary for using `automake' and `libintl'
     in one project.

     Those four packages are only needed by you, as a maintainer; the
     installers of your own package and end users do not really need
     any of GNU `m4', GNU Autoconf, GNU `gettext', or GNU `automake'
     for successfully installing and running your package, with messages
     properly translated.  But this is not completely true if you
     provide internationalized shell scripts within your own package:
     GNU `gettext' shall then be installed at the user site if the end
     users want to see the translation of shell script messages.

   * Your package should use Autoconf and have a `configure.in' or
     `configure.ac' file.  If it does not, you have to learn how.  The
     Autoconf documentation is quite well written, it is a good idea
     that you print it and get familiar with it.

   * Your C sources should have already been modified according to
     instructions given earlier in this manual.  *Note Sources::.

   * Your `po/' directory should receive all PO files submitted to you
     by the translator teams, each having `LL.po' as a name.  This is
     not usually easy to get translation work done before your package
     gets internationalized and available!  Since the cycle has to
     start somewhere, the easiest for the maintainer is to start with
     absolutely no PO files, and wait until various translator teams
     get interested in your package, and submit PO files.


   It is worth adding here a few words about how the maintainer should
ideally behave with PO files submissions.  As a maintainer, your role is
to authenticate the origin of the submission as being the representative
of the appropriate translating teams of the Translation Project (forward
the submission to `translation@iro.umontreal.ca' in case of doubt), to
ensure that the PO file format is not severely broken and does not
prevent successful installation, and for the rest, to merely put these
PO files in `po/' for distribution.

   As a maintainer, you do not have to take on your shoulders the
responsibility of checking if the translations are adequate or
complete, and should avoid diving into linguistic matters.  Translation
teams drive themselves and are fully responsible of their linguistic
choices for the Translation Project.  Keep in mind that translator
teams are _not_ driven by maintainers.  You can help by carefully
redirecting all communications and reports from users about linguistic
matters to the appropriate translation team, or explain users how to
reach or join their team.  The simplest might be to send them the
`ABOUT-NLS' file.

   Maintainers should _never ever_ apply PO file bug reports
themselves, short-cutting translation teams.  If some translator has
difficulty to get some of her points through her team, it should not be
an option for her to directly negotiate translations with maintainers.
Teams ought to settle their problems themselves, if any.  If you, as a
maintainer, ever think there is a real problem with a team, please
never try to _solve_ a team's problem on your own.


File: gettext.info,  Node: gettextize Invocation,  Next: Adjusting Files,  Prev: Prerequisites,  Up: Maintainers

12.3 Invoking the `gettextize' Program
======================================

The `gettextize' program is an interactive tool that helps the
maintainer of a package internationalized through GNU `gettext'.  It is
used for two purposes:

   * As a wizard, when a package is modified to use GNU `gettext' for
     the first time.

   * As a migration tool, for upgrading the GNU `gettext' support in a
     package from a previous to a newer version of GNU `gettext'.

   This program performs the following tasks:

   * It copies into the package some files that are consistently and
     identically needed in every package internationalized through GNU
     `gettext'.

   * It performs as many of the tasks mentioned in the next section
     *Note Adjusting Files:: as can be performed automatically.

   * It removes obsolete files and idioms used for previous GNU
     `gettext' versions to the form recommended for the current GNU
     `gettext' version.

   * It prints a summary of the tasks that ought to be done manually
     and could not be done automatically by `gettextize'.

   It can be invoked as follows:

     gettextize [ OPTION... ] [ DIRECTORY ]

and accepts the following options:

`-c'
`--copy'
     Copy the needed files instead of making symbolic links.  Using
     links would allow the package to always use the latest `gettext'
     code available on the system, but it might disturb some mechanism
     the maintainer is used to apply to the sources.  Because running
     `gettextize' is easy there shouldn't be problems with using copies.

`-f'
`--force'
     Force replacement of files which already exist.

`--intl'
     Install the libintl sources in a subdirectory named `intl/'.  This
     libintl will be used to provide internationalization on systems
     that don't have GNU libintl installed.  If this option is omitted,
     the call to `AM_GNU_GETTEXT' in `configure.in' should read:
     `AM_GNU_GETTEXT([external])', and internationalization will not be
     enabled on systems lacking GNU gettext.

`--no-changelog'
     Don't update or create ChangeLog files.  By default, `gettextize'
     logs all changes (file additions, modifications and removals) in a
     file called `ChangeLog' in each affected directory.

`-n'
`--dry-run'
     Print modifications but don't perform them.  All actions that
     `gettextize' would normally execute are inhibited and instead only
     listed on standard output.

`--help'
     Display this help and exit.

`--version'
     Output version information and exit.


   If DIRECTORY is given, this is the top level directory of a package
to prepare for using GNU `gettext'.  If not given, it is assumed that
the current directory is the top level directory of such a package.

   The program `gettextize' provides the following files.  However, no
existing file will be replaced unless the option `--force' (`-f') is
specified.

  1. The `ABOUT-NLS' file is copied in the main directory of your
     package, the one being at the top level.  This file gives the main
     indications about how to install and use the Native Language
     Support features of your program.  You might elect to use a more
     recent copy of this `ABOUT-NLS' file than the one provided through
     `gettextize', if you have one handy.  You may also fetch a more
     recent copy of file `ABOUT-NLS' from Translation Project sites,
     and from most GNU archive sites.

  2. A `po/' directory is created for eventually holding all
     translation files, but initially only containing the file
     `po/Makefile.in.in' from the GNU `gettext' distribution (beware
     the double `.in' in the file name) and a few auxiliary files.  If
     the `po/' directory already exists, it will be preserved along
     with the files it contains, and only `Makefile.in.in' and the
     auxiliary files will be overwritten.

  3. Only if `--intl' has been specified: A `intl/' directory is
     created and filled with most of the files originally in the
     `intl/' directory of the GNU `gettext' distribution.  Also, if
     option `--force' (`-f') is given, the `intl/' directory is emptied
     first.

  4. The files `config.rpath' and `mkinstalldirs' are copied into the
     directory containing configuration support files.  It is needed by
     the `AM_GNU_GETTEXT' autoconf macro.

  5. Only if the project is using GNU `automake': A set of `autoconf'
     macro files is copied into the package's `autoconf' macro
     repository, usually in a directory called `m4/'.

   If your site support symbolic links, `gettextize' will not actually
copy the files into your package, but establish symbolic links instead.
This avoids duplicating the disk space needed in all packages.  Merely
using the `-h' option while creating the `tar' archive of your
distribution will resolve each link by an actual copy in the
distribution archive.  So, to insist, you really should use `-h' option
with `tar' within your `dist' goal of your main `Makefile.in'.

   Furthermore, `gettextize' will update all `Makefile.am' files in
each affected directory, as well as the top level `configure.in' or
`configure.ac' file.

   It is interesting to understand that most new files for supporting
GNU `gettext' facilities in one package go in `intl/', `po/' and `m4/'
subdirectories.  One distinction between `intl/' and the two other
directories is that `intl/' is meant to be completely identical in all
packages using GNU `gettext', while the other directories will mostly
contain package dependent files.

   The `gettextize' program makes backup files for all files it
replaces or changes, and also write ChangeLog entries about these
changes.  This way, the careful maintainer can check after running
`gettextize' whether its changes are acceptable to him, and possibly
adjust them.  An exception to this rule is the `intl/' directory, which
is added or replaced or removed as a whole.

   It is important to understand that `gettextize' can not do the
entire job of adapting a package for using GNU `gettext'.  The amount
of remaining work depends on whether the package uses GNU `automake' or
not.  But in any case, the maintainer should still read the section
*Note Adjusting Files:: after invoking `gettextize'.

   It is also important to understand that `gettextize' is not part of
the GNU build system, in the sense that it should not be invoked
automatically, and not be invoked by someone who doesn't assume the
responsibilities of a package maintainer.  For the latter purpose, a
separate tool is provided, see *Note autopoint Invocation::.


File: gettext.info,  Node: Adjusting Files,  Next: autoconf macros,  Prev: gettextize Invocation,  Up: Maintainers

12.4 Files You Must Create or Alter
===================================

Besides files which are automatically added through `gettextize', there
are many files needing revision for properly interacting with GNU
`gettext'.  If you are closely following GNU standards for Makefile
engineering and auto-configuration, the adaptations should be easier to
achieve.  Here is a point by point description of the changes needed in
each.

   So, here comes a list of files, each one followed by a description of
all alterations it needs.  Many examples are taken out from the GNU
`gettext' 0.14.4 distribution itself, or from the GNU `hello'
distribution (`http://www.franken.de/users/gnu/ke/hello' or
`http://www.gnu.franken.de/ke/hello/')  You may indeed refer to the
source code of the GNU `gettext' and GNU `hello' packages, as they are
intended to be good examples for using GNU gettext functionality.

* Menu:

* po/POTFILES.in::              `POTFILES.in' in `po/'
* po/LINGUAS::                  `LINGUAS' in `po/'
* po/Makevars::                 `Makevars' in `po/'
* configure.in::                `configure.in' at top level
* config.guess::                `config.guess', `config.sub' at top level
* mkinstalldirs::               `mkinstalldirs' at top level
* aclocal::                     `aclocal.m4' at top level
* acconfig::                    `acconfig.h' at top level
* config.h.in::                 `config.h.in' at top level
* Makefile::                    `Makefile.in' at top level
* src/Makefile::                `Makefile.in' in `src/'
* lib/gettext.h::               `gettext.h' in `lib/'


File: gettext.info,  Node: po/POTFILES.in,  Next: po/LINGUAS,  Prev: Adjusting Files,  Up: Adjusting Files

12.4.1 `POTFILES.in' in `po/'
-----------------------------

The `po/' directory should receive a file named `POTFILES.in'.  This
file tells which files, among all program sources, have marked strings
needing translation.  Here is an example of such a file:

     # List of source files containing translatable strings.
     # Copyright (C) 1995 Free Software Foundation, Inc.

     # Common library files
     lib/error.c
     lib/getopt.c
     lib/xmalloc.c

     # Package source files
     src/gettext.c
     src/msgfmt.c
     src/xgettext.c

Hash-marked comments and white lines are ignored.  All other lines list
those source files containing strings marked for translation (*note
Mark Keywords::), in a notation relative to the top level of your whole
distribution, rather than the location of the `POTFILES.in' file itself.

   When a C file is automatically generated by a tool, like `flex' or
`bison', that doesn't introduce translatable strings by itself, it is
recommended to list in `po/POTFILES.in' the real source file (ending in
`.l' in the case of `flex', or in `.y' in the case of `bison'), not the
generated C file.


File: gettext.info,  Node: po/LINGUAS,  Next: po/Makevars,  Prev: po/POTFILES.in,  Up: Adjusting Files

12.4.2 `LINGUAS' in `po/'
-------------------------

The `po/' directory should also receive a file named `LINGUAS'.  This
file contains the list of available translations.  It is a whitespace
separated list.  Hash-marked comments and white lines are ignored.
Here is an example file:

     # Set of available languages.
     de fr

This example means that German and French PO files are available, so
that these languages are currently supported by your package.  If you
want to further restrict, at installation time, the set of installed
languages, this should not be done by modifying the `LINGUAS' file, but
rather by using the `LINGUAS' environment variable (*note Installers::).

   It is recommended that you add the "languages" `en@quot' and
`en@boldquot' to the `LINGUAS' file.  `en@quot' is a variant of English
message catalogs (`en') which uses real quotation marks instead of the
ugly looking asymmetric ASCII substitutes ``' and `''.  `en@boldquot'
is a variant of `en@quot' that additionally outputs quoted pieces of
text in a bold font, when used in a terminal emulator which supports
the VT100 escape sequences (such as `xterm' or the Linux console, but
not Emacs in `M-x shell' mode).

   These extra message catalogs `en@quot' and `en@boldquot' are
constructed automatically, not by translators; to support them, you
need the files `Rules-quot', `quot.sed', `boldquot.sed',
`en@quot.header', `en@boldquot.header', `insert-header.sin' in the
`po/' directory.  You can copy them from GNU gettext's `po/' directory;
they are also installed by running `gettextize'.


File: gettext.info,  Node: po/Makevars,  Next: configure.in,  Prev: po/LINGUAS,  Up: Adjusting Files

12.4.3 `Makevars' in `po/'
--------------------------

The `po/' directory also has a file named `Makevars'.  It can be left
unmodified if your package has a single message domain and,
accordingly, a single `po/' directory.  Only packages which have
multiple `po/' directories at different locations need to adjust the
three variables defined in `Makevars'.

   `po/Makevars' gets inserted into the `po/Makefile' when the latter
is created.  At the same time, all files called `Rules-*' in the `po/'
directory get appended to the `po/Makefile'.  They present an
opportunity to add rules for special PO files to the Makefile, without
needing to mess with `po/Makefile.in.in'.

   GNU gettext comes with a `Rules-quot' file, containing rules for
building catalogs `en@quot.po' and `en@boldquot.po'.  The effect of
`en@quot.po' is that people who set their `LANGUAGE' environment
variable to `en@quot' will get messages with proper looking symmetric
Unicode quotation marks instead of abusing the ASCII grave accent and
the ASCII apostrophe for indicating quotations.  To enable this
catalog, simply add `en@quot' to the `po/LINGUAS' file.  The effect of
`en@boldquot.po' is that people who set `LANGUAGE' to `en@boldquot'
will get not only proper quotation marks, but also the quoted text will
be shown in a bold font on terminals and consoles.  This catalog is
useful only for command-line programs, not GUI programs.  To enable it,
similarly add `en@boldquot' to the `po/LINGUAS' file.


File: gettext.info,  Node: configure.in,  Next: config.guess,  Prev: po/Makevars,  Up: Adjusting Files

12.4.4 `configure.in' at top level
----------------------------------

`configure.in' or `configure.ac' - this is the source from which
`autoconf' generates the `configure' script.

  1. Declare the package and version.  

     This is done by a set of lines like these:

          PACKAGE=gettext
          VERSION=0.14.4
          AC_DEFINE_UNQUOTED(PACKAGE, "$PACKAGE")
          AC_DEFINE_UNQUOTED(VERSION, "$VERSION")
          AC_SUBST(PACKAGE)
          AC_SUBST(VERSION)

     or, if you are using GNU `automake', by a line like this:

          AM_INIT_AUTOMAKE(gettext, 0.14.4)

     Of course, you replace `gettext' with the name of your package,
     and `0.14.4' by its version numbers, exactly as they should appear
     in the packaged `tar' file name of your distribution
     (`gettext-0.14.4.tar.gz', here).

  2. Check for internationalization support.

     Here is the main `m4' macro for triggering internationalization
     support.  Just add this line to `configure.in':

          AM_GNU_GETTEXT

     This call is purposely simple, even if it generates a lot of
     configure time checking and actions.

     If you have suppressed the `intl/' subdirectory by calling
     `gettextize' without `--intl' option, this call should read

          AM_GNU_GETTEXT([external])

  3. Have output files created.

     The `AC_OUTPUT' directive, at the end of your `configure.in' file,
     needs to be modified in two ways:

          AC_OUTPUT([EXISTING CONFIGURATION FILES intl/Makefile po/Makefile.in],
          [EXISTING ADDITIONAL ACTIONS])

     The modification to the first argument to `AC_OUTPUT' asks for
     substitution in the `intl/' and `po/' directories.  Note the `.in'
     suffix used for `po/' only.  This is because the distributed file
     is really `po/Makefile.in.in'.

     If you have suppressed the `intl/' subdirectory by calling
     `gettextize' without `--intl' option, then you don't need to add
     `intl/Makefile' to the `AC_OUTPUT' line.



File: gettext.info,  Node: config.guess,  Next: mkinstalldirs,  Prev: configure.in,  Up: Adjusting Files

12.4.5 `config.guess', `config.sub' at top level
------------------------------------------------

If you haven't suppressed the `intl/' subdirectory, you need to add the
GNU `config.guess' and `config.sub' files to your distribution.  They
are needed because the `intl/' directory has platform dependent support
for determining the locale's character encoding and therefore needs to
identify the platform.

   You can obtain the newest version of `config.guess' and `config.sub'
from the CVS of the `config' project at `http://savannah.gnu.org/'. The
commands to fetch them are
     $ wget 'http://savannah.gnu.org/cgi-bin/viewcvs/*checkout*/config/config/config.guess'
     $ wget 'http://savannah.gnu.org/cgi-bin/viewcvs/*checkout*/config/config/config.sub'
   Less recent versions are also contained in the GNU `automake' and
GNU `libtool' packages.

   Normally, `config.guess' and `config.sub' are put at the top level
of a distribution.  But it is also possible to put them in a
subdirectory, altogether with other configuration support files like
`install-sh', `ltconfig', `ltmain.sh', `mkinstalldirs' or `missing'.
All you need to do, other than moving the files, is to add the
following line to your `configure.in'.

     AC_CONFIG_AUX_DIR([SUBDIR])


File: gettext.info,  Node: mkinstalldirs,  Next: aclocal,  Prev: config.guess,  Up: Adjusting Files

12.4.6 `mkinstalldirs' at top level
-----------------------------------

If `gettextize' has not already done it, you need to add the GNU
`mkinstalldirs' script to your distribution.  It is needed because
`mkdir -p' is not portable enough.  You find this script in the GNU
`automake' distribution.

   Normally, `mkinstalldirs' is put at the top level of a distribution.
But it is also possible to put it in a subdirectory, altogether with
other configuration support files like `install-sh', `ltconfig',
`ltmain.sh' or `missing'.  All you need to do, other than moving the
files, is to add the following line to your `configure.in'.

     AC_CONFIG_AUX_DIR([SUBDIR])


File: gettext.info,  Node: aclocal,  Next: acconfig,  Prev: mkinstalldirs,  Up: Adjusting Files

12.4.7 `aclocal.m4' at top level
--------------------------------

If you do not have an `aclocal.m4' file in your distribution, the
simplest is to concatenate the files `codeset.m4', `gettext.m4',
`glibc2.m4', `glibc21.m4', `iconv.m4', `intdiv0.m4', `intmax.m4',
`inttypes.m4', `inttypes_h.m4', `inttypes-pri.m4', `isc-posix.m4',
`lcmessage.m4', `lib-ld.m4', `lib-link.m4', `lib-prefix.m4',
`longdouble.m4', `longlong.m4', `printf-posix.m4', `progtest.m4',
`signed.m4', `size_max.m4', `stdint_h.m4', `uintmax_t.m4',
`ulonglong.m4', `wchar_t.m4', `wint_t.m4', `xsize.m4' from GNU
`gettext''s `m4/' directory into a single file.  If you have suppressed
the `intl/' directory, only `gettext.m4', `iconv.m4', `lib-ld.m4',
`lib-link.m4', `lib-prefix.m4', `progtest.m4' need to be concatenated.

   If you already have an `aclocal.m4' file, then you will have to
merge the said macro files into your `aclocal.m4'.  Note that if you
are upgrading from a previous release of GNU `gettext', you should most
probably _replace_ the macros (`AM_GNU_GETTEXT', etc.), as they usually
change a little from one release of GNU `gettext' to the next.  Their
contents may vary as we get more experience with strange systems out
there.

   If you are using GNU `automake' 1.5 or newer, it is enough to put
these macro files into a subdirectory named `m4/' and add the line

     ACLOCAL_AMFLAGS = -I m4

to your top level `Makefile.am'.

   These macros check for the internationalization support functions
and related informations.  Hopefully, once stabilized, these macros
might be integrated in the standard Autoconf set, because this piece of
`m4' code will be the same for all projects using GNU `gettext'.


File: gettext.info,  Node: acconfig,  Next: config.h.in,  Prev: aclocal,  Up: Adjusting Files

12.4.8 `acconfig.h' at top level
--------------------------------

Earlier GNU `gettext' releases required to put definitions for
`ENABLE_NLS', `HAVE_GETTEXT' and `HAVE_LC_MESSAGES', `HAVE_STPCPY',
`PACKAGE' and `VERSION' into an `acconfig.h' file.  This is not needed
any more; you can remove them from your `acconfig.h' file unless your
package uses them independently from the `intl/' directory.


File: gettext.info,  Node: config.h.in,  Next: Makefile,  Prev: acconfig,  Up: Adjusting Files

12.4.9 `config.h.in' at top level
---------------------------------

The include file template that holds the C macros to be defined by
`configure' is usually called `config.h.in' and may be maintained
either manually or automatically.

   If `gettextize' has created an `intl/' directory, this file must be
called `config.h.in' and must be at the top level.  If, however, you
have suppressed the `intl/' directory by calling `gettextize' without
`--intl' option, then you can choose the name of this file and its
location freely.

   If it is maintained automatically, by use of the `autoheader'
program, you need to do nothing about it.  This is the case in
particular if you are using GNU `automake'.

   If it is maintained manually, and if `gettextize' has created an
`intl/' directory, you should switch to using `autoheader'.  The list
of C macros to be added for the sake of the `intl/' directory is just
too long to be maintained manually; it also changes between different
versions of GNU `gettext'.

   If it is maintained manually, and if on the other hand you have
suppressed the `intl/' directory by calling `gettextize' without
`--intl' option, then you can get away by adding the following lines to
`config.h.in':

     /* Define to 1 if translation of program messages to the user's
        native language is requested. */
     #undef ENABLE_NLS


File: gettext.info,  Node: Makefile,  Next: src/Makefile,  Prev: config.h.in,  Up: Adjusting Files

12.4.10 `Makefile.in' at top level
----------------------------------

Here are a few modifications you need to make to your main, top-level
`Makefile.in' file.

  1. Add the following lines near the beginning of your `Makefile.in',
     so the `dist:' goal will work properly (as explained further down):

          PACKAGE = @PACKAGE@
          VERSION = @VERSION@

  2. Add file `ABOUT-NLS' to the `DISTFILES' definition, so the file
     gets distributed.

  3. Wherever you process subdirectories in your `Makefile.in', be sure
     you also process the subdirectories `intl' and `po'.  Special
     rules in the `Makefiles' take care for the case where no
     internationalization is wanted.

     If you are using Makefiles, either generated by automake, or
     hand-written so they carefully follow the GNU coding standards,
     the effected goals for which the new subdirectories must be
     handled include `installdirs', `install', `uninstall', `clean',
     `distclean'.

     Here is an example of a canonical order of processing.  In this
     example, we also define `SUBDIRS' in `Makefile.in' for it to be
     further used in the `dist:' goal.

          SUBDIRS = doc intl lib src po

     Note that you must arrange for `make' to descend into the `intl'
     directory before descending into other directories containing code
     which make use of the `libintl.h' header file.  For this reason,
     here we mention `intl' before `lib' and `src'.

  4. A delicate point is the `dist:' goal, as both `intl/Makefile' and
     `po/Makefile' will later assume that the proper directory has been
     set up from the main `Makefile'.  Here is an example at what the
     `dist:' goal might look like:

          distdir = $(PACKAGE)-$(VERSION)
          dist: Makefile
          	rm -fr $(distdir)
          	mkdir $(distdir)
          	chmod 777 $(distdir)
          	for file in $(DISTFILES); do \
          	  ln $$file $(distdir) 2>/dev/null || cp -p $$file $(distdir); \
          	done
          	for subdir in $(SUBDIRS); do \
          	  mkdir $(distdir)/$$subdir || exit 1; \
          	  chmod 777 $(distdir)/$$subdir; \
          	  (cd $$subdir && $(MAKE) $@) || exit 1; \
          	done
          	tar chozf $(distdir).tar.gz $(distdir)
          	rm -fr $(distdir)


   Note that if you are using GNU `automake', `Makefile.in' is
automatically generated from `Makefile.am', and all needed changes to
`Makefile.am' are already made by running `gettextize'.


File: gettext.info,  Node: src/Makefile,  Next: lib/gettext.h,  Prev: Makefile,  Up: Adjusting Files

12.4.11 `Makefile.in' in `src/'
-------------------------------

Some of the modifications made in the main `Makefile.in' will also be
needed in the `Makefile.in' from your package sources, which we assume
here to be in the `src/' subdirectory.  Here are all the modifications
needed in `src/Makefile.in':

  1. In view of the `dist:' goal, you should have these lines near the
     beginning of `src/Makefile.in':

          PACKAGE = @PACKAGE@
          VERSION = @VERSION@

  2. If not done already, you should guarantee that `top_srcdir' gets
     defined.  This will serve for `cpp' include files.  Just add the
     line:

          top_srcdir = @top_srcdir@

  3. You might also want to define `subdir' as `src', later allowing
     for almost uniform `dist:' goals in all your `Makefile.in'.  At
     list, the `dist:' goal below assume that you used:

          subdir = src

  4. The `main' function of your program will normally call
     `bindtextdomain' (see *note Triggering::), like this:

          bindtextdomain (PACKAGE, LOCALEDIR);
          textdomain (PACKAGE);

     To make LOCALEDIR known to the program, add the following lines to
     `Makefile.in':

          datadir = @datadir@
          localedir = $(datadir)/locale
          DEFS = -DLOCALEDIR=\"$(localedir)\" @DEFS@

     Note that `@datadir@' defaults to `$(prefix)/share', thus
     `$(localedir)' defaults to `$(prefix)/share/locale'.

  5. You should ensure that the final linking will use `@LIBINTL@' or
     `@LTLIBINTL@' as a library.  `@LIBINTL@' is for use without
     `libtool', `@LTLIBINTL@' is for use with `libtool'.  An easy way
     to achieve this is to manage that it gets into `LIBS', like this:

          LIBS = @LIBINTL@ @LIBS@

     In most packages internationalized with GNU `gettext', one will
     find a directory `lib/' in which a library containing some helper
     functions will be build.  (You need at least the few functions
     which the GNU `gettext' Library itself needs.)  However some of
     the functions in the `lib/' also give messages to the user which
     of course should be translated, too.  Taking care of this, the
     support library (say `libsupport.a') should be placed before
     `@LIBINTL@' and `@LIBS@' in the above example.  So one has to
     write this:

          LIBS = ../lib/libsupport.a @LIBINTL@ @LIBS@

  6. You should also ensure that directory `intl/' will be searched for
     C preprocessor include files in all circumstances.  So, you have to
     manage so both `-I../intl' and `-I$(top_srcdir)/intl' will be
     given to the C compiler.

  7. Your `dist:' goal has to conform with others.  Here is a
     reasonable definition for it:

          distdir = ../$(PACKAGE)-$(VERSION)/$(subdir)
          dist: Makefile $(DISTFILES)
          	for file in $(DISTFILES); do \
          	  ln $$file $(distdir) 2>/dev/null || cp -p $$file $(distdir) || exit 1; \
          	done


   Note that if you are using GNU `automake', `Makefile.in' is
automatically generated from `Makefile.am', and the first three changes
and the last change are not necessary.  The remaining needed
`Makefile.am' modifications are the following:

  1. To make LOCALEDIR known to the program, add the following to
     `Makefile.am':

          <module>_CPPFLAGS = -DLOCALEDIR=\"$(localedir)\"

     for each specific module or compilation unit, or

          AM_CPPFLAGS = -DLOCALEDIR=\"$(localedir)\"

     for all modules and compilation units together.  Furthermore, add
     this line to define `localedir':

          localedir = $(datadir)/locale

  2. To ensure that the final linking will use `@LIBINTL@' or
     `@LTLIBINTL@' as a library, add the following to `Makefile.am':

          <program>_LDADD = @LIBINTL@

     for each specific program, or

          LDADD = @LIBINTL@

     for all programs together.  Remember that when you use `libtool'
     to link a program, you need to use @LTLIBINTL@ instead of @LIBINTL@
     for that program.

  3. If you have an `intl/' directory, whose contents is created by
     `gettextize', then to ensure that it will be searched for C
     preprocessor include files in all circumstances, add something like
     this to `Makefile.am':

          AM_CPPFLAGS = -I../intl -I$(top_srcdir)/intl



File: gettext.info,  Node: lib/gettext.h,  Prev: src/Makefile,  Up: Adjusting Files

12.4.12 `gettext.h' in `lib/'
-----------------------------

Internationalization of packages, as provided by GNU `gettext', is
optional.  It can be turned off in two situations:

   * When the installer has specified `./configure --disable-nls'.  This
     can be useful when small binaries are more important than
     features, for example when building utilities for boot diskettes.
     It can also be useful in order to get some specific C compiler
     warnings about code quality with some older versions of GCC (older
     than 3.0).

   * When the package does not include the `intl/' subdirectory, and the
     libintl.h header (with its associated libintl library, if any) is
     not already installed on the system, it is preferrable that the
     package builds without internationalization support, rather than
     to give a compilation error.

   A C preprocessor macro can be used to detect these two cases.
Usually, when `libintl.h' was found and not explicitly disabled, the
`ENABLE_NLS' macro will be defined to 1 in the autoconf generated
configuration file (usually called `config.h').  In the two negative
situations, however, this macro will not be defined, thus it will
evaluate to 0 in C preprocessor expressions.

   `gettext.h' is a convenience header file for conditional use of
`<libintl.h>', depending on the `ENABLE_NLS' macro.  If `ENABLE_NLS' is
set, it includes `<libintl.h>'; otherwise it defines no-op substitutes
for the libintl.h functions.  We recommend the use of `"gettext.h"'
over direct use of `<libintl.h>', so that portability to older systems
is guaranteed and installers can turn off internationalization if they
want to.  In the C code, you will then write

     #include "gettext.h"

instead of

     #include <libintl.h>

   The location of `gettext.h' is usually in a directory containing
auxiliary include files.  In many GNU packages, there is a directory
`lib/' containing helper functions; `gettext.h' fits there.  In other
packages, it can go into the `src' directory.

   Do not install the `gettext.h' file in public locations.  Every
package that needs it should contain a copy of it on its own.


File: gettext.info,  Node: autoconf macros,  Next: CVS Issues,  Prev: Adjusting Files,  Up: Maintainers

12.5 Autoconf macros for use in `configure.in'
==============================================

GNU `gettext' installs macros for use in a package's `configure.in' or
`configure.ac'.  *Note Introduction: (autoconf)Top.  The primary macro
is, of course, `AM_GNU_GETTEXT'.

* Menu:

* AM_GNU_GETTEXT::              AM_GNU_GETTEXT in `gettext.m4'
* AM_GNU_GETTEXT_VERSION::      AM_GNU_GETTEXT_VERSION in `gettext.m4'
* AM_PO_SUBDIRS::               AM_PO_SUBDIRS in `po.m4'
* AM_ICONV::                    AM_ICONV in `iconv.m4'


File: gettext.info,  Node: AM_GNU_GETTEXT,  Next: AM_GNU_GETTEXT_VERSION,  Prev: autoconf macros,  Up: autoconf macros

12.5.1 AM_GNU_GETTEXT in `gettext.m4'
-------------------------------------

The `AM_GNU_GETTEXT' macro tests for the presence of the GNU gettext
function family in either the C library or a separate `libintl' library
(shared or static libraries are both supported) or in the package's
`intl/' directory.  It also invokes `AM_PO_SUBDIRS', thus preparing the
`po/' directories of the package for building.

   `AM_GNU_GETTEXT' accepts up to three optional arguments.  The general
syntax is

     AM_GNU_GETTEXT([INTLSYMBOL], [NEEDSYMBOL], [INTLDIR])

   INTLSYMBOL can be `external' or `no-libtool'.  The default (if it is
not specified or empty) is `no-libtool'.  INTLSYMBOL should be
`external' for packages with no `intl/' directory, and `no-libtool' for
packages with an `intl/' directory.  In the latter case, a static
library `$(top_builddir)/intl/libintl.a' will be created.

   If NEEDSYMBOL is specified and is `need-ngettext', then GNU gettext
implementations (in libc or libintl) without the `ngettext()' function
will be ignored.  If NEEDSYMBOL is specified and is
`need-formatstring-macros', then GNU gettext implementations that don't
support the ISO C 99 `<inttypes.h>' formatstring macros will be ignored.
Only one NEEDSYMBOL can be specified.  To specify more than one
requirement, just specify the strongest one among them.  The hierarchy
among the various alternatives is as follows: `need-formatstring-macros'
implies `need-ngettext'.

   INTLDIR is used to find the intl libraries.  If empty, the value
`$(top_builddir)/intl/' is used.

   The `AM_GNU_GETTEXT' macro determines whether GNU gettext is
available and should be used.  If so, it sets the `USE_NLS' variable to
`yes'; it defines `ENABLE_NLS' to 1 in the autoconf generated
configuration file (usually called `config.h'); it sets the variables
`LIBINTL' and `LTLIBINTL' to the linker options for use in a Makefile
(`LIBINTL' for use without libtool, `LTLIBINTL' for use with libtool);
it adds an `-I' option to `CPPFLAGS' if necessary.  In the negative
case, it sets `USE_NLS' to `no'; it sets `LIBINTL' and `LTLIBINTL' to
empty and doesn't change `CPPFLAGS'.

   The complexities that `AM_GNU_GETTEXT' deals with are the following:

   * Some operating systems have `gettext' in the C library, for example
     glibc.  Some have it in a separate library `libintl'.  GNU
     `libintl' might have been installed as part of the GNU `gettext'
     package.

   * GNU `libintl', if installed, is not necessarily already in the
     search path (`CPPFLAGS' for the include file search path,
     `LDFLAGS' for the library search path).

   * Except for glibc, the operating system's native `gettext' cannot
     exploit the GNU mo files, doesn't have the necessary locale
     dependency features, and cannot convert messages from the
     catalog's text encoding to the user's locale encoding.

   * GNU `libintl', if installed, is not necessarily already in the run
     time library search path.  To avoid the need for setting an
     environment variable like `LD_LIBRARY_PATH', the macro adds the
     appropriate run time search path options to the `LIBINTL' and
     `LTLIBINTL' variables.  This works on most systems, but not on
     some operating systems with limited shared library support, like
     SCO.

   * GNU `libintl' relies on POSIX/XSI `iconv'.  The macro checks for
     linker options needed to use iconv and appends them to the
     `LIBINTL' and `LTLIBINTL' variables.


File: gettext.info,  Node: AM_GNU_GETTEXT_VERSION,  Next: AM_PO_SUBDIRS,  Prev: AM_GNU_GETTEXT,  Up: autoconf macros

12.5.2 AM_GNU_GETTEXT_VERSION in `gettext.m4'
---------------------------------------------

The `AM_GNU_GETTEXT_VERSION' macro declares the version number of the
GNU gettext infrastructure that is used by the package.

   The use of this macro is optional; only the `autopoint' program makes
use of it (*note CVS Issues::).


File: gettext.info,  Node: AM_PO_SUBDIRS,  Next: AM_ICONV,  Prev: AM_GNU_GETTEXT_VERSION,  Up: autoconf macros

12.5.3 AM_PO_SUBDIRS in `po.m4'
-------------------------------

The `AM_PO_SUBDIRS' macro prepares the `po/' directories of the package
for building.  This macro should be used in internationalized programs
written in other programming languages than C, C++, Objective C, for
example `sh', `Python', `Lisp'.  See *Note Programming Languages:: for
a list of programming languages that support localization through PO
files.

   The `AM_PO_SUBDIRS' macro determines whether internationalization
should be used.  If so, it sets the `USE_NLS' variable to `yes',
otherwise to `no'.  It also determines the right values for Makefile
variables in each `po/' directory.


File: gettext.info,  Node: AM_ICONV,  Prev: AM_PO_SUBDIRS,  Up: autoconf macros

12.5.4 AM_ICONV in `iconv.m4'
-----------------------------

The `AM_ICONV' macro tests for the presence of the POSIX/XSI `iconv'
function family in either the C library or a separate `libiconv'
library.  If found, it sets the `am_cv_func_iconv' variable to `yes';
it defines `HAVE_ICONV' to 1 in the autoconf generated configuration
file (usually called `config.h'); it defines `ICONV_CONST' to `const'
or to empty, depending on whether the second argument of `iconv()' is
of type `const char **' or `char **'; it sets the variables `LIBICONV'
and `LTLIBICONV' to the linker options for use in a Makefile
(`LIBICONV' for use without libtool, `LTLIBICONV' for use with
libtool); it adds an `-I' option to `CPPFLAGS' if necessary.  If not
found, it sets `LIBICONV' and `LTLIBICONV' to empty and doesn't change
`CPPFLAGS'.

   The complexities that `AM_ICONV' deals with are the following:

   * Some operating systems have `iconv' in the C library, for example
     glibc.  Some have it in a separate library `libiconv', for example
     OSF/1 or FreeBSD.  Regardless of the operating system, GNU
     `libiconv' might have been installed.  In that case, it should be
     used instead of the operating system's native `iconv'.

   * GNU `libiconv', if installed, is not necessarily already in the
     search path (`CPPFLAGS' for the include file search path,
     `LDFLAGS' for the library search path).

   * GNU `libiconv' is binary incompatible with some operating system's
     native `iconv', for example on FreeBSD.  Use of an `iconv.h' and
     `libiconv.so' that don't fit together would produce program
     crashes.

   * GNU `libiconv', if installed, is not necessarily already in the
     run time library search path.  To avoid the need for setting an
     environment variable like `LD_LIBRARY_PATH', the macro adds the
     appropriate run time search path options to the `LIBICONV'
     variable.  This works on most systems, but not on some operating
     systems with limited shared library support, like SCO.

   `iconv.m4' is distributed with the GNU gettext package because
`gettext.m4' relies on it.


File: gettext.info,  Node: CVS Issues,  Next: Release Management,  Prev: autoconf macros,  Up: Maintainers

12.6 Integrating with CVS
=========================

Many projects use CVS for distributed development, version control and
source backup.  This section gives some advice how to manage the uses
of `cvs', `gettextize', `autopoint' and `autoconf'.

* Menu:

* Distributed CVS::             Avoiding version mismatch in distributed development
* Files under CVS::             Files to put under CVS version control
* autopoint Invocation::        Invoking the `autopoint' Program


File: gettext.info,  Node: Distributed CVS,  Next: Files under CVS,  Prev: CVS Issues,  Up: CVS Issues

12.6.1 Avoiding version mismatch in distributed development
-----------------------------------------------------------

In a project development with multiple developers, using CVS, there
should be a single developer who occasionally - when there is desire to
upgrade to a new `gettext' version - runs `gettextize' and performs the
changes listed in *Note Adjusting Files::, and then commits his changes
to the CVS.

   It is highly recommended that all developers on a project use the
same version of GNU `gettext' in the package.  In other words, if a
developer runs `gettextize', he should go the whole way, make the
necessary remaining changes and commit his changes to the CVS.
Otherwise the following damages will likely occur:

   * Apparent version mismatch between developers.  Since some `gettext'
     specific portions in `configure.in', `configure.ac' and
     `Makefile.am', `Makefile.in' files depend on the `gettext'
     version, the use of infrastructure files belonging to different
     `gettext' versions can easily lead to build errors.

   * Hidden version mismatch.  Such version mismatch can also lead to
     malfunctioning of the package, that may be undiscovered by the
     developers.  The worst case of hidden version mismatch is that
     internationalization of the package doesn't work at all.

   * Release risks.  All developers implicitly perform constant testing
     on a package.  This is important in the days and weeks before a
     release.  If the guy who makes the release tar files uses a
     different version of GNU `gettext' than the other developers, the
     distribution will be less well tested than if all had been using
     the same `gettext' version.  For example, it is possible that a
     platform specific bug goes undiscovered due to this constellation.


File: gettext.info,  Node: Files under CVS,  Next: autopoint Invocation,  Prev: Distributed CVS,  Up: CVS Issues

12.6.2 Files to put under CVS version control
---------------------------------------------

There are basically three ways to deal with generated files in the
context of a CVS repository, such as `configure' generated from
`configure.in', `PARSER.c' generated from `PARSER.y', or
`po/Makefile.in.in' autoinstalled by `gettextize' or `autopoint'.

  1. All generated files are always committed into the repository.

  2. All generated files are committed into the repository occasionally,
     for example each time a release is made.

  3. Generated files are never committed into the repository.

   Each of these three approaches has different advantages and
drawbacks.

  1. The advantage is that anyone can check out the CVS at any moment
     and gets a working build.  The drawbacks are:  1a. It requires
     some frequent "cvs commit" actions by the maintainers.  1b. The
     repository grows in size quite fast.

  2. The advantage is that anyone can check out the CVS, and the usual
     "./configure; make" will work.  The drawbacks are:  2a. The one who
     checks out the repository needs tools like GNU `automake', GNU
     `autoconf', GNU `m4' installed in his PATH; sometimes he even
     needs particular versions of them.  2b. When a release is made and
     a commit is made on the generated files, the other developers get
     conflicts on the generated files after doing "cvs update".
     Although these conflicts are easy to resolve, they are annoying.

  3. The advantage is less work for the maintainers.  The drawback is
     that anyone who checks out the CVS not only needs tools like GNU
     `automake', GNU `autoconf', GNU `m4' installed in his PATH, but
     also that he needs to perform a package specific pre-build step
     before being able to "./configure; make".

   For the first and second approach, all files modified or brought in
by the occasional `gettextize' invocation and update should be
committed into the CVS.

   For the third approach, the maintainer can omit from the CVS
repository all the files that `gettextize' mentions as "copy".
Instead, he adds to the `configure.in' or `configure.ac' a line of the
form

     AM_GNU_GETTEXT_VERSION(0.14.4)

and adds to the package's pre-build script an invocation of
`autopoint'.  For everyone who checks out the CVS, this `autopoint'
invocation will copy into the right place the `gettext' infrastructure
files that have been omitted from the CVS.

   The version number used as argument to `AM_GNU_GETTEXT_VERSION' is
the version of the `gettext' infrastructure that the package wants to
use.  It is also the minimum version number of the `autopoint' program.
So, if you write `AM_GNU_GETTEXT_VERSION(0.11.5)' then the developers
can have any version >= 0.11.5 installed; the package will work with
the 0.11.5 infrastructure in all developers' builds.  When the
maintainer then runs gettextize from, say, version 0.12.1 on the
package, the occurrence of `AM_GNU_GETTEXT_VERSION(0.11.5)' will be
changed into `AM_GNU_GETTEXT_VERSION(0.12.1)', and all other developers
that use the CVS will henceforth need to have GNU `gettext' 0.12.1 or
newer installed.


File: gettext.info,  Node: autopoint Invocation,  Prev: Files under CVS,  Up: CVS Issues

12.6.3 Invoking the `autopoint' Program
---------------------------------------

     autopoint [OPTION]...

   The `autopoint' program copies standard gettext infrastructure files
into a source package.  It extracts from a macro call of the form
`AM_GNU_GETTEXT_VERSION(VERSION)', found in the package's
`configure.in' or `configure.ac' file, the gettext version used by the
package, and copies the infrastructure files belonging to this version
into the package.

12.6.3.1 Options
................

`-f'
`--force'
     Force overwriting of files that already exist.

`-n'
`--dry-run'
     Print modifications but don't perform them.  All file copying
     actions that `autopoint' would normally execute are inhibited and
     instead only listed on standard output.


12.6.3.2 Informative output
...........................

`--help'
     Display this help and exit.

`--version'
     Output version information and exit.


   `autopoint' supports the GNU `gettext' versions from 0.10.35 to the
current one, 0.14.4.  In order to apply `autopoint' to a package using
a `gettext' version newer than 0.14.4, you need to install this same
version of GNU `gettext' at least.

   In packages using GNU `automake', an invocation of `autopoint'
should be followed by invocations of `aclocal' and then `autoconf' and
`autoheader'.  The reason is that `autopoint' installs some autoconf
macro files, which are used by `aclocal' to create `aclocal.m4', and
the latter is used by `autoconf' to create the package's `configure'
script and by `autoheader' to create the package's `config.h.in'
include file template.

   The name `autopoint' is an abbreviation of `auto-po-intl-m4'; the
tool copies or updates mostly files in the `po', `intl', `m4'
directories.


File: gettext.info,  Node: Release Management,  Prev: CVS Issues,  Up: Maintainers

12.7 Creating a Distribution Tarball
====================================

In projects that use GNU `automake', the usual commands for creating a
distribution tarball, `make dist' or `make distcheck', automatically
update the PO files as needed.

   If GNU `automake' is not used, the maintainer needs to perform this
update before making a release:

     $ ./configure
     $ (cd po; make update-po)
     $ make distclean


File: gettext.info,  Node: Programming Languages,  Next: Conclusion,  Prev: Maintainers,  Up: Top

13 Other Programming Languages
******************************

While the presentation of `gettext' focuses mostly on C and implicitly
applies to C++ as well, its scope is far broader than that: Many
programming languages, scripting languages and other textual data like
GUI resources or package descriptions can make use of the gettext
approach.

* Menu:

* Language Implementors::       The Language Implementor's View
* Programmers for other Languages::  The Programmer's View
* Translators for other Languages::  The Translator's View
* Maintainers for other Languages::  The Maintainer's View
* List of Programming Languages::  Individual Programming Languages
* List of Data Formats::        Internationalizable Data


File: gettext.info,  Node: Language Implementors,  Next: Programmers for other Languages,  Prev: Programming Languages,  Up: Programming Languages

13.1 The Language Implementor's View
====================================

All programming and scripting languages that have the notion of strings
are eligible to supporting `gettext'.  Supporting `gettext' means the
following:

  1. You should add to the language a syntax for translatable strings.
     In principle, a function call of `gettext' would do, but a
     shorthand syntax helps keeping the legibility of internationalized
     programs.  For example, in C we use the syntax `_("string")', and
     in GNU awk we use the shorthand `_"string"'.

  2. You should arrange that evaluation of such a translatable string at
     runtime calls the `gettext' function, or performs equivalent
     processing.

  3. Similarly, you should make the functions `ngettext', `dcgettext',
     `dcngettext' available from within the language.  These functions
     are less often used, but are nevertheless necessary for particular
     purposes: `ngettext' for correct plural handling, and `dcgettext'
     and `dcngettext' for obeying other locale environment variables
     than `LC_MESSAGES', such as `LC_TIME' or `LC_MONETARY'.  For these
     latter functions, you need to make the `LC_*' constants, available
     in the C header `<locale.h>', referenceable from within the
     language, usually either as enumeration values or as strings.

  4. You should allow the programmer to designate a message domain,
     either by making the `textdomain' function available from within
     the language, or by introducing a magic variable called
     `TEXTDOMAIN'.  Similarly, you should allow the programmer to
     designate where to search for message catalogs, by providing
     access to the `bindtextdomain' function.

  5. You should either perform a `setlocale (LC_ALL, "")' call during
     the startup of your language runtime, or allow the programmer to
     do so.  Remember that gettext will act as a no-op if the
     `LC_MESSAGES' and `LC_CTYPE' locale facets are not both set.

  6. A programmer should have a way to extract translatable strings
     from a program into a PO file.  The GNU `xgettext' program is being
     extended to support very different programming languages.  Please
     contact the GNU `gettext' maintainers to help them doing this.  If
     the string extractor is best integrated into your language's
     parser, GNU `xgettext' can function as a front end to your string
     extractor.

  7. The language's library should have a string formatting facility
     where the arguments of a format string are denoted by a positional
     number or a name.  This is needed because for some languages and
     some messages with more than one substitutable argument, the
     translation will need to output the substituted arguments in
     different order.  *Note c-format Flag::.

  8. If the language has more than one implementation, and not all of
     the implementations use `gettext', but the programs should be
     portable across implementations, you should provide a no-i18n
     emulation, that makes the other implementations accept programs
     written for yours, without actually translating the strings.

  9. To help the programmer in the task of marking translatable strings,
     which is usually performed using the Emacs PO mode, you are
     welcome to contact the GNU `gettext' maintainers, so they can add
     support for your language to `po-mode.el'.

   On the implementation side, three approaches are possible, with
different effects on portability and copyright:

   * You may integrate the GNU `gettext''s `intl/' directory in your
     package, as described in *Note Maintainers::.  This allows you to
     have internationalization on all kinds of platforms.  Note that
     when you then distribute your package, it legally falls under the
     GNU General Public License, and the GNU project will be glad about
     your contribution to the Free Software pool.

   * You may link against GNU `gettext' functions if they are found in
     the C library.  For example, an autoconf test for `gettext()' and
     `ngettext()' will detect this situation.  For the moment, this test
     will succeed on GNU systems and not on other platforms.  No severe
     copyright restrictions apply.

   * You may emulate or reimplement the GNU `gettext' functionality.
     This has the advantage of full portability and no copyright
     restrictions, but also the drawback that you have to reimplement
     the GNU `gettext' features (such as the `LANGUAGE' environment
     variable, the locale aliases database, the automatic charset
     conversion, and plural handling).


File: gettext.info,  Node: Programmers for other Languages,  Next: Translators for other Languages,  Prev: Language Implementors,  Up: Programming Languages

13.2 The Programmer's View
==========================

For the programmer, the general procedure is the same as for the C
language.  The Emacs PO mode supports other languages, and the GNU
`xgettext' string extractor recognizes other languages based on the
file extension or a command-line option.  In some languages,
`setlocale' is not needed because it is already performed by the
underlying language runtime.


File: gettext.info,  Node: Translators for other Languages,  Next: Maintainers for other Languages,  Prev: Programmers for other Languages,  Up: Programming Languages

13.3 The Translator's View
==========================

The translator works exactly as in the C language case.  The only
difference is that when translating format strings, she has to be aware
of the language's particular syntax for positional arguments in format
strings.

* Menu:

* c-format::                    C Format Strings
* objc-format::                 Objective C Format Strings
* sh-format::                   Shell Format Strings
* python-format::               Python Format Strings
* lisp-format::                 Lisp Format Strings
* elisp-format::                Emacs Lisp Format Strings
* librep-format::               librep Format Strings
* scheme-format::               Scheme Format Strings
* smalltalk-format::            Smalltalk Format Strings
* java-format::                 Java Format Strings
* csharp-format::               C# Format Strings
* awk-format::                  awk Format Strings
* object-pascal-format::        Object Pascal Format Strings
* ycp-format::                  YCP Format Strings
* tcl-format::                  Tcl Format Strings
* perl-format::                 Perl Format Strings
* php-format::                  PHP Format Strings
* gcc-internal-format::         GCC internal Format Strings
* qt-format::                   Qt Format Strings


File: gettext.info,  Node: c-format,  Next: objc-format,  Prev: Translators for other Languages,  Up: Translators for other Languages

13.3.1 C Format Strings
-----------------------

C format strings are described in POSIX (IEEE P1003.1 2001), section
XSH 3 fprintf(),
`http://www.opengroup.org/onlinepubs/007904975/functions/fprintf.html'.
See also the fprintf(3) manual page,
`http://www.linuxvalley.it/encyclopedia/ldp/manpage/man3/printf.3.php',
`http://informatik.fh-wuerzburg.de/student/i510/man/printf.html'.

   Although format strings with positions that reorder arguments, such
as

     "Only %2$d bytes free on '%1$s'."

which is semantically equivalent to

     "'%s' has only %d bytes free."

are a POSIX/XSI feature and not specified by ISO C 99, translators can
rely on this reordering ability: On the few platforms where `printf()',
`fprintf()' etc. don't support this feature natively, `libintl.a' or
`libintl.so' provides replacement functions, and GNU `<libintl.h>'
activates these replacement functions automatically.

   As a special feature for Farsi (Persian) and maybe Arabic,
translators can insert an `I' flag into numeric format directives.  For
example, the translation of `"%d"' can be `"%Id"'.  The effect of this
flag, on systems with GNU `libc', is that in the output, the ASCII
digits are replaced with the `outdigits' defined in the `LC_CTYPE'
locale facet.  On other systems, the `gettext' function removes this
flag, so that it has no effect.

   Note that the programmer should _not_ put this flag into the
untranslated string.  (Putting the `I' format directive flag into an
MSGID string would lead to undefined behaviour on platforms without
glibc when NLS is disabled.)


File: gettext.info,  Node: objc-format,  Next: sh-format,  Prev: c-format,  Up: Translators for other Languages

13.3.2 Objective C Format Strings
---------------------------------

Objective C format strings are like C format strings.  They support an
additional format directive: "$@", which when executed consumes an
argument of type `Object *'.


File: gettext.info,  Node: sh-format,  Next: python-format,  Prev: objc-format,  Up: Translators for other Languages

13.3.3 Shell Format Strings
---------------------------

Shell format strings, as supported by GNU gettext and the `envsubst'
program, are strings with references to shell variables in the form
`$VARIABLE' or `${VARIABLE}'.  References of the form
`${VARIABLE-DEFAULT}', `${VARIABLE:-DEFAULT}', `${VARIABLE=DEFAULT}',
`${VARIABLE:=DEFAULT}', `${VARIABLE+REPLACEMENT}',
`${VARIABLE:+REPLACEMENT}', `${VARIABLE?IGNORED}',
`${VARIABLE:?IGNORED}', that would be valid inside shell scripts, are
not supported.  The VARIABLE names must consist solely of alphanumeric
or underscore ASCII characters, not start with a digit and be nonempty;
otherwise such a variable reference is ignored.


File: gettext.info,  Node: python-format,  Next: lisp-format,  Prev: sh-format,  Up: Translators for other Languages

13.3.4 Python Format Strings
----------------------------

Python format strings are described in Python Library reference /
2. Built-in Types, Exceptions and Functions / 2.2. Built-in Types /
2.2.6. Sequence Types / 2.2.6.2. String Formatting Operations.
`http://www.python.org/doc/2.2.1/lib/typesseq-strings.html'.


File: gettext.info,  Node: lisp-format,  Next: elisp-format,  Prev: python-format,  Up: Translators for other Languages

13.3.5 Lisp Format Strings
--------------------------

Lisp format strings are described in the Common Lisp HyperSpec, chapter
22.3 Formatted Output,
`http://www.lisp.org/HyperSpec/Body/sec_22-3.html'.


File: gettext.info,  Node: elisp-format,  Next: librep-format,  Prev: lisp-format,  Up: Translators for other Languages

13.3.6 Emacs Lisp Format Strings
--------------------------------

Emacs Lisp format strings are documented in the Emacs Lisp reference,
section Formatting Strings,
`http://www.gnu.org/manual/elisp-manual-21-2.8/html_chapter/elisp_4.html#SEC75'.
Note that as of version 21, XEmacs supports numbered argument
specifications in format strings while FSF Emacs doesn't.


File: gettext.info,  Node: librep-format,  Next: scheme-format,  Prev: elisp-format,  Up: Translators for other Languages

13.3.7 librep Format Strings
----------------------------

librep format strings are documented in the librep manual, section
Formatted Output,
`http://librep.sourceforge.net/librep-manual.html#Formatted%20Output',
`http://www.gwinnup.org/research/docs/librep.html#SEC122'.


File: gettext.info,  Node: scheme-format,  Next: smalltalk-format,  Prev: librep-format,  Up: Translators for other Languages

13.3.8 Scheme Format Strings
----------------------------

Scheme format strings are documented in the SLIB manual, section
Format Specification.


File: gettext.info,  Node: smalltalk-format,  Next: java-format,  Prev: scheme-format,  Up: Translators for other Languages

13.3.9 Smalltalk Format Strings
-------------------------------

Smalltalk format strings are described in the GNU Smalltalk
documentation, class `CharArray', methods `bindWith:' and
`bindWithArguments:'.
`http://www.gnu.org/software/smalltalk/gst-manual/gst_68.html#SEC238'.
In summary, a directive starts with `%' and is followed by `%' or a
nonzero digit (`1' to `9').


File: gettext.info,  Node: java-format,  Next: csharp-format,  Prev: smalltalk-format,  Up: Translators for other Languages

13.3.10 Java Format Strings
---------------------------

Java format strings are described in the JDK documentation for class
`java.text.MessageFormat',
`http://java.sun.com/j2se/1.4/docs/api/java/text/MessageFormat.html'.
See also the ICU documentation
`http://oss.software.ibm.com/icu/apiref/classMessageFormat.html'.


File: gettext.info,  Node: csharp-format,  Next: awk-format,  Prev: java-format,  Up: Translators for other Languages

13.3.11 C# Format Strings
-------------------------

C# format strings are described in the .NET documentation for class
`System.String' and in
`http://msdn.microsoft.com/library/default.asp?url=/library/en-us/cpguide/html/cpConFormattingOverview.asp'.


File: gettext.info,  Node: awk-format,  Next: object-pascal-format,  Prev: csharp-format,  Up: Translators for other Languages

13.3.12 awk Format Strings
--------------------------

awk format strings are described in the gawk documentation, section
Printf, `http://www.gnu.org/manual/gawk/html_node/Printf.html#Printf'.


File: gettext.info,  Node: object-pascal-format,  Next: ycp-format,  Prev: awk-format,  Up: Translators for other Languages

13.3.13 Object Pascal Format Strings
------------------------------------

Where is this documented?


File: gettext.info,  Node: ycp-format,  Next: tcl-format,  Prev: object-pascal-format,  Up: Translators for other Languages

13.3.14 YCP Format Strings
--------------------------

YCP sformat strings are described in the libycp documentation
`file:/usr/share/doc/packages/libycp/YCP-builtins.html'.  In summary, a
directive starts with `%' and is followed by `%' or a nonzero digit
(`1' to `9').


File: gettext.info,  Node: tcl-format,  Next: perl-format,  Prev: ycp-format,  Up: Translators for other Languages

13.3.15 Tcl Format Strings
--------------------------

Tcl format strings are described in the `format.n' manual page,
`http://www.scriptics.com/man/tcl8.3/TclCmd/format.htm'.


File: gettext.info,  Node: perl-format,  Next: php-format,  Prev: tcl-format,  Up: Translators for other Languages

13.3.16 Perl Format Strings
---------------------------

There are two kinds format strings in Perl: those acceptable to the
Perl built-in function `printf', labelled as `perl-format', and those
acceptable to the `libintl-perl' function `__x', labelled as
`perl-brace-format'.

   Perl `printf' format strings are described in the `sprintf' section
of `man perlfunc'.

   Perl brace format strings are described in the
`Locale::TextDomain(3pm)' manual page of the CPAN package libintl-perl.
In brief, Perl format uses placeholders put between braces (`{' and
`}').  The placeholder must have the syntax of simple identifiers.


File: gettext.info,  Node: php-format,  Next: gcc-internal-format,  Prev: perl-format,  Up: Translators for other Languages

13.3.17 PHP Format Strings
--------------------------

PHP format strings are described in the documentation of the PHP
function `sprintf', in `phpdoc/manual/function.sprintf.html' or
`http://www.php.net/manual/en/function.sprintf.php'.


File: gettext.info,  Node: gcc-internal-format,  Next: qt-format,  Prev: php-format,  Up: Translators for other Languages

13.3.18 GCC internal Format Strings
-----------------------------------

These format strings are used inside the GCC sources.  In such a format
string, a directive starts with `%', is optionally followed by a size
specifier `l', an optional flag `+', another optional flag `#', and is
finished by a specifier: `%' denotes a literal percent sign, `c'
denotes a character, `s' denotes a string, `i' and `d' denote an
integer, `o', `u', `x' denote an unsigned integer, `.*s' denotes a
string preceded by a width specification, `H' denotes a `location_t *'
pointer, `D' denotes a general declaration, `F' denotes a function
declaration, `T' denotes a type, `A' denotes a function argument, `C'
denotes a tree code, `E' denotes an expression, `L' denotes a
programming language, `O' denotes a binary operator, `P' denotes a
function parameter, `Q' denotes an assignment operator, `V' denotes a
const/volatile qualifier.


File: gettext.info,  Node: qt-format,  Prev: gcc-internal-format,  Up: Translators for other Languages

13.3.19 Qt Format Strings
-------------------------

Qt format strings are described in the documentation of the QString
class `file:/usr/lib/qt-3.0.5/doc/html/qstring.html'.  In summary, a
directive consists of a `%' followed by a digit. The same directive
cannot occur more than once in a format string.


File: gettext.info,  Node: Maintainers for other Languages,  Next: List of Programming Languages,  Prev: Translators for other Languages,  Up: Programming Languages

13.4 The Maintainer's View
==========================

For the maintainer, the general procedure differs from the C language
case in two ways.

   * For those languages that don't use GNU gettext, the `intl/'
     directory is not needed and can be omitted.  This means that the
     maintainer calls the `gettextize' program without the `--intl'
     option, and that he invokes the `AM_GNU_GETTEXT' autoconf macro via
     `AM_GNU_GETTEXT([external])'.

   * If only a single programming language is used, the
     `XGETTEXT_OPTIONS' variable in `po/Makevars' (*note po/Makevars::)
     should be adjusted to match the `xgettext' options for that
     particular programming language.  If the package uses more than
     one programming language with `gettext' support, it becomes
     necessary to change the POT file construction rule in
     `po/Makefile.in.in'.  It is recommended to make one `xgettext'
     invocation per programming language, each with the options
     appropriate for that language, and to combine the resulting files
     using `msgcat'.


File: gettext.info,  Node: List of Programming Languages,  Next: List of Data Formats,  Prev: Maintainers for other Languages,  Up: Programming Languages

13.5 Individual Programming Languages
=====================================

* Menu:

* C::                           C, C++, Objective C
* sh::                          sh - Shell Script
* bash::                        bash - Bourne-Again Shell Script
* Python::                      Python
* Common Lisp::                 GNU clisp - Common Lisp
* clisp C::                     GNU clisp C sources
* Emacs Lisp::                  Emacs Lisp
* librep::                      librep
* Scheme::                      GNU guile - Scheme
* Smalltalk::                   GNU Smalltalk
* Java::                        Java
* C#::                          C#
* gawk::                        GNU awk
* Pascal::                      Pascal - Free Pascal Compiler
* wxWindows::                   wxWindows library
* YCP::                         YCP - YaST2 scripting language
* Tcl::                         Tcl - Tk's scripting language
* Perl::                        Perl
* PHP::                         PHP Hypertext Preprocessor
* Pike::                        Pike
* GCC-source::                  GNU Compiler Collection sources


File: gettext.info,  Node: C,  Next: sh,  Prev: List of Programming Languages,  Up: List of Programming Languages

13.5.1 C, C++, Objective C
--------------------------

RPMs
     gcc, gpp, gobjc, glibc, gettext

File extension
     For C: `c', `h'.
     For C++: `C', `c++', `cc', `cxx', `cpp', `hpp'.
     For Objective C: `m'.

String syntax
     `"abc"'

gettext shorthand
     `_("abc")'

gettext/ngettext functions
     `gettext', `dgettext', `dcgettext', `ngettext', `dngettext',
     `dcngettext'

textdomain
     `textdomain' function

bindtextdomain
     `bindtextdomain' function

setlocale
     Programmer must call `setlocale (LC_ALL, "")'

Prerequisite
     `#include <libintl.h>'
     `#include <locale.h>'
     `#define _(string) gettext (string)'

Use or emulate GNU gettext
     Use

Extractor
     `xgettext -k_'

Formatting with positions
     `fprintf "%2$d %1$d"'
     In C++: `autosprintf "%2$d %1$d"' (*note Introduction:
     (autosprintf)Top.)

Portability
     autoconf (gettext.m4) and #if ENABLE_NLS

po-mode marking
     yes

   The following examples are available in the `examples' directory:
`hello-c', `hello-c-gnome', `hello-c++', `hello-c++-qt',
`hello-c++-kde', `hello-c++-gnome', `hello-objc', `hello-objc-gnustep',
`hello-objc-gnome'.


File: gettext.info,  Node: sh,  Next: bash,  Prev: C,  Up: List of Programming Languages

13.5.2 sh - Shell Script
------------------------

RPMs
     bash, gettext

File extension
     `sh'

String syntax
     `"abc"', `'abc'', `abc'

gettext shorthand
     `"`gettext \"abc\"`"'

gettext/ngettext functions
     `gettext', `ngettext' programs
     `eval_gettext', `eval_ngettext' shell functions

textdomain
     environment variable `TEXTDOMAIN'

bindtextdomain
     environment variable `TEXTDOMAINDIR'

setlocale
     automatic

Prerequisite
     `. gettext.sh'

Use or emulate GNU gettext
     use

Extractor
     `xgettext'

Formatting with positions
     --

Portability
     fully portable

po-mode marking
     --

   An example is available in the `examples' directory: `hello-sh'.

* Menu:

* Preparing Shell Scripts::     Preparing Shell Scripts for Internationalization
* gettext.sh::                  Contents of `gettext.sh'
* gettext Invocation::          Invoking the `gettext' program
* ngettext Invocation::         Invoking the `ngettext' program
* envsubst Invocation::         Invoking the `envsubst' program
* eval_gettext Invocation::     Invoking the `eval_gettext' function
* eval_ngettext Invocation::    Invoking the `eval_ngettext' function


File: gettext.info,  Node: Preparing Shell Scripts,  Next: gettext.sh,  Prev: sh,  Up: sh

13.5.2.1 Preparing Shell Scripts for Internationalization
.........................................................

Preparing a shell script for internationalization is conceptually
similar to the steps described in *Note Sources::.  The concrete steps
for shell scripts are as follows.

  1. Insert the line

          . gettext.sh

     near the top of the script.  `gettext.sh' is a shell function
     library that provides the functions `eval_gettext' (see *Note
     eval_gettext Invocation::) and `eval_ngettext' (see *Note
     eval_ngettext Invocation::).  You have to ensure that `gettext.sh'
     can be found in the `PATH'.

  2. Set and export the `TEXTDOMAIN' and `TEXTDOMAINDIR' environment
     variables.  Usually `TEXTDOMAIN' is the package or program name,
     and `TEXTDOMAINDIR' is the absolute pathname corresponding to
     `$prefix/share/locale', where `$prefix' is the installation
     location.

          TEXTDOMAIN=@PACKAGE@
          export TEXTDOMAIN
          TEXTDOMAINDIR=@LOCALEDIR@
          export TEXTDOMAINDIR

  3. Prepare the strings for translation, as described in *Note
     Preparing Strings::.

  4. Simplify translatable strings so that they don't contain command
     substitution (`"`...`"' or `"$(...)"'), variable access with
     defaulting (like `${VARIABLE-DEFAULT}'), access to positional
     arguments (like `$0', `$1', ...) or highly volatile shell
     variables (like `$?'). This can always be done through simple
     local code restructuring.  For example,

          echo "Usage: $0 [OPTION] FILE..."

     becomes

          program_name=$0
          echo "Usage: $program_name [OPTION] FILE..."

     Similarly,

          echo "Remaining files: `ls | wc -l`"

     becomes

          filecount="`ls | wc -l`"
          echo "Remaining files: $filecount"

  5. For each translatable string, change the output command `echo' or
     `$echo' to `gettext' (if the string contains no references to
     shell variables) or to `eval_gettext' (if it refers to shell
     variables), followed by a no-argument `echo' command (to account
     for the terminating newline). Similarly, for cases with plural
     handling, replace a conditional `echo' command with an invocation
     of `ngettext' or `eval_ngettext', followed by a no-argument `echo'
     command.

     When doing this, you also need to add an extra backslash before
     the dollar sign in references to shell variables, so that the
     `eval_gettext' function receives the translatable string before
     the variable values are substituted into it. For example,

          echo "Remaining files: $filecount"

     becomes

          eval_gettext "Remaining files: \$filecount"; echo

     If the output command is not `echo', you can make it use `echo'
     nevertheless, through the use of backquotes. However, note that
     inside backquotes, backslashes must be doubled to be effective
     (because the backquoting eats one level of backslashes). For
     example, assuming that `error' is a shell function that signals an
     error,

          error "file not found: $filename"

     is first transformed into

          error "`echo \"file not found: \$filename\"`"

     which then becomes

          error "`eval_gettext \"file not found: \\\$filename\"`"


File: gettext.info,  Node: gettext.sh,  Next: gettext Invocation,  Prev: Preparing Shell Scripts,  Up: sh

13.5.2.2 Contents of `gettext.sh'
.................................

`gettext.sh', contained in the run-time package of GNU gettext, provides
the following:

   * $echo The variable `echo' is set to a command that outputs its
     first argument and a newline, without interpreting backslashes in
     the argument string.

   * eval_gettext See *Note eval_gettext Invocation::.

   * eval_ngettext See *Note eval_ngettext Invocation::.


File: gettext.info,  Node: gettext Invocation,  Next: ngettext Invocation,  Prev: gettext.sh,  Up: sh

13.5.2.3 Invoking the `gettext' program
.......................................

     gettext [OPTION] [[TEXTDOMAIN] MSGID]
     gettext [OPTION] -s [MSGID]...

   The `gettext' program displays the native language translation of a
textual message.

*Arguments*

`-d TEXTDOMAIN'
`--domain=TEXTDOMAIN'
     Retrieve translated messages from TEXTDOMAIN.  Usually a TEXTDOMAIN
     corresponds to a package, a program, or a module of a program.

`-e'
     Enable expansion of some escape sequences.  This option is for
     compatibility with the `echo' program or shell built-in.  The
     escape sequences `\a', `\b', `\c', `\f', `\n', `\r', `\t', `\v',
     `\\', and `\' followed by one to three octal digits, are
     interpreted like the SystemV `echo' program does.

`-E'
     This option is only for compatibility with the `echo' program or
     shell built-in.  It has no effect.

`-h'
`--help'
     Display this help and exit.

`-n'
     Suppress trailing newline.  By default, `gettext' adds a newline to
     the output.

`-V'
`--version'
     Output version information and exit.

`[TEXTDOMAIN] MSGID'
     Retrieve translated message corresponding to MSGID from TEXTDOMAIN.


   If the TEXTDOMAIN parameter is not given, the domain is determined
from the environment variable `TEXTDOMAIN'.  If the message catalog is
not found in the regular directory, another location can be specified
with the environment variable `TEXTDOMAINDIR'.

   When used with the `-s' option the program behaves like the `echo'
command.  But it does not simply copy its arguments to stdout.  Instead
those messages found in the selected catalog are translated.


File: gettext.info,  Node: ngettext Invocation,  Next: envsubst Invocation,  Prev: gettext Invocation,  Up: sh

13.5.2.4 Invoking the `ngettext' program
........................................

     ngettext [OPTION] [TEXTDOMAIN] MSGID MSGID-PLURAL COUNT

   The `ngettext' program displays the native language translation of a
textual message whose grammatical form depends on a number.

*Arguments*

`-d TEXTDOMAIN'
`--domain=TEXTDOMAIN'
     Retrieve translated messages from TEXTDOMAIN.  Usually a TEXTDOMAIN
     corresponds to a package, a program, or a module of a program.

`-e'
     Enable expansion of some escape sequences.  This option is for
     compatibility with the `gettext' program.  The escape sequences
     `\a', `\b', `\c', `\f', `\n', `\r', `\t', `\v', `\\', and `\'
     followed by one to three octal digits, are interpreted like the
     SystemV `echo' program does.

`-E'
     This option is only for compatibility with the `gettext' program.
     It has no effect.

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.

`TEXTDOMAIN'
     Retrieve translated message from TEXTDOMAIN.

`MSGID MSGID-PLURAL'
     Translate MSGID (English singular) / MSGID-PLURAL (English plural).

`COUNT'
     Choose singular/plural form based on this value.


   If the TEXTDOMAIN parameter is not given, the domain is determined
from the environment variable `TEXTDOMAIN'.  If the message catalog is
not found in the regular directory, another location can be specified
with the environment variable `TEXTDOMAINDIR'.


File: gettext.info,  Node: envsubst Invocation,  Next: eval_gettext Invocation,  Prev: ngettext Invocation,  Up: sh

13.5.2.5 Invoking the `envsubst' program
........................................

     envsubst [OPTION] [SHELL-FORMAT]

   The `envsubst' program substitutes the values of environment
variables.

*Operation mode*

`-v'
`--variables'
     Output the variables occurring in SHELL-FORMAT.


*Informative output*

`-h'
`--help'
     Display this help and exit.

`-V'
`--version'
     Output version information and exit.


   In normal operation mode, standard input is copied to standard
output, with references to environment variables of the form
`$VARIABLE' or `${VARIABLE}' being replaced with the corresponding
values.  If a SHELL-FORMAT is given, only those environment variables
that are referenced in SHELL-FORMAT are substituted; otherwise all
environment variables references occurring in standard input are
substituted.

   These substitutions are a subset of the substitutions that a shell
performs on unquoted and double-quoted strings.  Other kinds of
substitutions done by a shell, such as `${VARIABLE-DEFAULT}' or
`$(COMMAND-LIST)' or ``COMMAND-LIST`', are not performed by the
`envsubst' program, due to security reasons.

   When `--variables' is used, standard input is ignored, and the output
consists of the environment variables that are referenced in
SHELL-FORMAT, one per line.


File: gettext.info,  Node: eval_gettext Invocation,  Next: eval_ngettext Invocation,  Prev: envsubst Invocation,  Up: sh

13.5.2.6 Invoking the `eval_gettext' function
.............................................

     eval_gettext MSGID

   This function outputs the native language translation of a textual
message, performing dollar-substitution on the result.  Note that only
shell variables mentioned in MSGID will be dollar-substituted in the
result.


File: gettext.info,  Node: eval_ngettext Invocation,  Prev: eval_gettext Invocation,  Up: sh

13.5.2.7 Invoking the `eval_ngettext' function
..............................................

     eval_ngettext MSGID MSGID-PLURAL COUNT

   This function outputs the native language translation of a textual
message whose grammatical form depends on a number, performing
dollar-substitution on the result.  Note that only shell variables
mentioned in MSGID or MSGID-PLURAL will be dollar-substituted in the
result.


File: gettext.info,  Node: bash,  Next: Python,  Prev: sh,  Up: List of Programming Languages

13.5.3 bash - Bourne-Again Shell Script
---------------------------------------

GNU `bash' 2.0 or newer has a special shorthand for translating a
string and substituting variable values in it: `$"msgid"'.  But the use
of this construct is *discouraged*, due to the security holes it opens
and due to its portability problems.

   The security holes of `$"..."' come from the fact that after looking
up the translation of the string, `bash' processes it like it processes
any double-quoted string: dollar and backquote processing, like `eval'
does.

  1. In a locale whose encoding is one of BIG5, BIG5-HKSCS, GBK,
     GB18030, SHIFT_JIS, JOHAB, some double-byte characters have a
     second byte whose value is `0x60'.  For example, the byte sequence
     `\xe0\x60' is a single character in these locales.  Many versions
     of `bash' (all versions up to bash-2.05, and newer versions on
     platforms without `mbsrtowcs()' function) don't know about
     character boundaries and see a backquote character where there is
     only a particular Chinese character.  Thus it can start executing
     part of the translation as a command list.  This situation can
     occur even without the translator being aware of it: if the
     translator provides translations in the UTF-8 encoding, it is the
     `gettext()' function which will, during its conversion from the
     translator's encoding to the user's locale's encoding, produce the
     dangerous `\x60' bytes.

  2. A translator could - voluntarily or inadvertantly - use backquotes
     `"`...`"' or dollar-parentheses `"$(...)"' in her translations.
     The enclosed strings would be executed as command lists by the
     shell.

   The portability problem is that `bash' must be built with
internationalization support; this is normally not the case on systems
that don't have the `gettext()' function in libc.


File: gettext.info,  Node: Python,  Next: Common Lisp,  Prev: bash,  Up: List of Programming Languages

13.5.4 Python
-------------

RPMs
     python

File extension
     `py'

String syntax
     `'abc'', `u'abc'', `r'abc'', `ur'abc'',
     `"abc"', `u"abc"', `r"abc"', `ur"abc"',
     `'''abc'''', `u'''abc'''', `r'''abc'''', `ur'''abc'''',
     `"""abc"""', `u"""abc"""', `r"""abc"""', `ur"""abc"""'

gettext shorthand
     `_('abc')' etc.

gettext/ngettext functions
     `gettext.gettext', `gettext.dgettext', `gettext.ngettext',
     `gettext.dngettext', also `ugettext', `ungettext'

textdomain
     `gettext.textdomain' function, or `gettext.install(DOMAIN)'
     function

bindtextdomain
     `gettext.bindtextdomain' function, or
     `gettext.install(DOMAIN,LOCALEDIR)' function

setlocale
     not used by the gettext emulation

Prerequisite
     `import gettext'

Use or emulate GNU gettext
     emulate

Extractor
     `xgettext'

Formatting with positions
     `'...%(ident)d...' % { 'ident': value }'

Portability
     fully portable

po-mode marking
     --

   An example is available in the `examples' directory: `hello-python'.


File: gettext.info,  Node: Common Lisp,  Next: clisp C,  Prev: Python,  Up: List of Programming Languages

13.5.5 GNU clisp - Common Lisp
------------------------------

RPMs
     clisp 2.28 or newer

File extension
     `lisp'

String syntax
     `"abc"'

gettext shorthand
     `(_ "abc")', `(ENGLISH "abc")'

gettext/ngettext functions
     `i18n:gettext', `i18n:ngettext'

textdomain
     `i18n:textdomain'

bindtextdomain
     `i18n:textdomaindir'

setlocale
     automatic

Prerequisite
     --

Use or emulate GNU gettext
     use

Extractor
     `xgettext -k_ -kENGLISH'

Formatting with positions
     `format "~1@*~D ~0@*~D"'

Portability
     On platforms without gettext, no translation.

po-mode marking
     --

   An example is available in the `examples' directory: `hello-clisp'.


File: gettext.info,  Node: clisp C,  Next: Emacs Lisp,  Prev: Common Lisp,  Up: List of Programming Languages

13.5.6 GNU clisp C sources
--------------------------

RPMs
     clisp

File extension
     `d'

String syntax
     `"abc"'

gettext shorthand
     `ENGLISH ? "abc" : ""'
     `GETTEXT("abc")'
     `GETTEXTL("abc")'

gettext/ngettext functions
     `clgettext', `clgettextl'

textdomain
     --

bindtextdomain
     --

setlocale
     automatic

Prerequisite
     `#include "lispbibl.c"'

Use or emulate GNU gettext
     use

Extractor
     `clisp-xgettext'

Formatting with positions
     `fprintf "%2$d %1$d"'

Portability
     On platforms without gettext, no translation.

po-mode marking
     --


File: gettext.info,  Node: Emacs Lisp,  Next: librep,  Prev: clisp C,  Up: List of Programming Languages

13.5.7 Emacs Lisp
-----------------

RPMs
     emacs, xemacs

File extension
     `el'

String syntax
     `"abc"'

gettext shorthand
     `(_"abc")'

gettext/ngettext functions
     `gettext', `dgettext' (xemacs only)

textdomain
     `domain' special form (xemacs only)

bindtextdomain
     `bind-text-domain' function (xemacs only)

setlocale
     automatic

Prerequisite
     --

Use or emulate GNU gettext
     use

Extractor
     `xgettext'

Formatting with positions
     `format "%2$d %1$d"'

Portability
     Only XEmacs.  Without `I18N3' defined at build time, no
     translation.

po-mode marking
     --


File: gettext.info,  Node: librep,  Next: Scheme,  Prev: Emacs Lisp,  Up: List of Programming Languages

13.5.8 librep
-------------

RPMs
     librep 0.15.3 or newer

File extension
     `jl'

String syntax
     `"abc"'

gettext shorthand
     `(_"abc")'

gettext/ngettext functions
     `gettext'

textdomain
     `textdomain' function

bindtextdomain
     `bindtextdomain' function

setlocale
     --

Prerequisite
     `(require 'rep.i18n.gettext)'

Use or emulate GNU gettext
     use

Extractor
     `xgettext'

Formatting with positions
     `format "%2$d %1$d"'

Portability
     On platforms without gettext, no translation.

po-mode marking
     --

   An example is available in the `examples' directory: `hello-librep'.


File: gettext.info,  Node: Scheme,  Next: Smalltalk,  Prev: librep,  Up: List of Programming Languages

13.5.9 GNU guile - Scheme
-------------------------

RPMs
     guile

File extension
     `scm'

String syntax
     `"abc"'

gettext shorthand
     `(_ "abc")'

gettext/ngettext functions
     `gettext', `ngettext'

textdomain
     `textdomain'

bindtextdomain
     `bindtextdomain'

setlocale
     `(catch #t (lambda () (setlocale LC_ALL "")) (lambda args #f))'

Prerequisite
     `(use-modules (ice-9 format))'

Use or emulate GNU gettext
     use

Extractor
     `xgettext -k_'

Formatting with positions
     --

Portability
     On platforms without gettext, no translation.

po-mode marking
     --

   An example is available in the `examples' directory: `hello-guile'.


File: gettext.info,  Node: Smalltalk,  Next: Java,  Prev: Scheme,  Up: List of Programming Languages

13.5.10 GNU Smalltalk
---------------------

RPMs
     smalltalk

File extension
     `st'

String syntax
     `'abc''

gettext shorthand
     `NLS ? 'abc''

gettext/ngettext functions
     `LcMessagesDomain>>#at:', `LcMessagesDomain>>#at:plural:with:'

textdomain
     `LcMessages>>#domain:localeDirectory:' (returns a
     `LcMessagesDomain' object).
     Example: `I18N Locale default messages domain: 'gettext'
     localeDirectory: /usr/local/share/locale''

bindtextdomain
     `LcMessages>>#domain:localeDirectory:', see above.

setlocale
     Automatic if you use `I18N Locale default'.

Prerequisite
     `PackageLoader fileInPackage: 'I18N'!'

Use or emulate GNU gettext
     emulate

Extractor
     `xgettext'

Formatting with positions
     `'%1 %2' bindWith: 'Hello' with: 'world''

Portability
     fully portable

po-mode marking
     --

   An example is available in the `examples' directory:
`hello-smalltalk'.


File: gettext.info,  Node: Java,  Next: C#,  Prev: Smalltalk,  Up: List of Programming Languages

13.5.11 Java
------------

RPMs
     java, java2

File extension
     `java'

String syntax
     "abc"

gettext shorthand
     _("abc")

gettext/ngettext functions
     `GettextResource.gettext', `GettextResource.ngettext'

textdomain
     --, use `ResourceBundle.getResource' instead

bindtextdomain
     --, use CLASSPATH instead

setlocale
     automatic

Prerequisite
     --

Use or emulate GNU gettext
     --, uses a Java specific message catalog format

Extractor
     `xgettext -k_'

Formatting with positions
     `MessageFormat.format "{1,number} {0,number}"'

Portability
     fully portable

po-mode marking
     --

   Before marking strings as internationalizable, uses of the string
concatenation operator need to be converted to `MessageFormat'
applications.  For example, `"file "+filename+" not found"' becomes
`MessageFormat.format("file {0} not found", new Object[] { filename })'.
Only after this is done, can the strings be marked and extracted.

   GNU gettext uses the native Java internationalization mechanism,
namely `ResourceBundle's.  There are two formats of `ResourceBundle's:
`.properties' files and `.class' files.  The `.properties' format is a
text file which the translators can directly edit, like PO files, but
which doesn't support plural forms.  Whereas the `.class' format is
compiled from `.java' source code and can support plural forms
(provided it is accessed through an appropriate API, see below).

   To convert a PO file to a `.properties' file, the `msgcat' program
can be used with the option `--properties-output'.  To convert a
`.properties' file back to a PO file, the `msgcat' program can be used
with the option `--properties-input'.  All the tools that manipulate PO
files can work with `.properties' files as well, if given the
`--properties-input' and/or `--properties-output' option.

   To convert a PO file to a ResourceBundle class, the `msgfmt' program
can be used with the option `--java' or `--java2'.  To convert a
ResourceBundle back to a PO file, the `msgunfmt' program can be used
with the option `--java'.

   Two different programmatic APIs can be used to access
ResourceBundles.  Note that both APIs work with all kinds of
ResourceBundles, whether GNU gettext generated classes, or other
`.class' or `.properties' files.

  1. The `java.util.ResourceBundle' API.

     In particular, its `getString' function returns a string
     translation.  Note that a missing translation yields a
     `MissingResourceException'.

     This has the advantage of being the standard API.  And it does not
     require any additional libraries, only the `msgcat' generated
     `.properties' files or the `msgfmt' generated `.class' files.  But
     it cannot do plural handling, even if the resource was generated
     by `msgfmt' from a PO file with plural handling.

  2. The `gnu.gettext.GettextResource' API.

     Reference documentation in Javadoc 1.1 style format is in the
     javadoc1 directory (javadoc1/tree.html) and in Javadoc 2 style
     format in the javadoc2 directory (javadoc2/index.html).

     Its `gettext' function returns a string translation.  Note that
     when a translation is missing, the MSGID argument is returned
     unchanged.

     This has the advantage of having the `ngettext' function for plural
     handling.

     To use this API, one needs the `libintl.jar' file which is part of
     the GNU gettext package and distributed under the LGPL.

   Three examples, using the second API, are available in the `examples'
directory: `hello-java', `hello-java-awt', `hello-java-swing'.

   Now, to make use of the API and define a shorthand for `getString',
there are two idioms that you can choose from:

   * In a unique class of your project, say `Util', define a static
     variable holding the `ResourceBundle' instance:

          public static ResourceBundle myResources =
            ResourceBundle.getBundle("domain-name");

     All classes containing internationalized strings then contain

          private static ResourceBundle res = Util.myResources;
          private static String _(String s) { return res.getString(s); }

     and the shorthand is used like this:

          System.out.println(_("Operation completed."));

   * You add a class with a very short name, say `S', containing just
     the definition of the resource bundle and of the shorthand:

          public class S {
            public static ResourceBundle myResources =
              ResourceBundle.getBundle("domain-name");
            public static String _(String s) {
              return myResources.getString(s);
            }
          }

     and the shorthand is used like this:

          System.out.println(S._("Operation completed."));

   Which of the two idioms you choose, will depend on whether copying
two lines of codes into every class is more acceptable in your project
than a class with a single-letter name.


File: gettext.info,  Node: C#,  Next: gawk,  Prev: Java,  Up: List of Programming Languages

13.5.12 C#
----------

RPMs
     pnet, pnetlib 0.6.2 or newer, or mono 0.29 or newer

File extension
     `cs'

String syntax
     `"abc"', `@"abc"'

gettext shorthand
     _("abc")

gettext/ngettext functions
     `GettextResourceManager.GetString',
     `GettextResourceManager.GetPluralString'

textdomain
     `new GettextResourceManager(domain)'

bindtextdomain
     --, compiled message catalogs are located in subdirectories of the
     directory containing the executable

setlocale
     automatic

Prerequisite
     --

Use or emulate GNU gettext
     --, uses a C# specific message catalog format

Extractor
     `xgettext -k_'

Formatting with positions
     `String.Format "{1} {0}"'

Portability
     fully portable

po-mode marking
     --

   Before marking strings as internationalizable, uses of the string
concatenation operator need to be converted to `String.Format'
invocations.  For example, `"file "+filename+" not found"' becomes
`String.Format("file {0} not found", filename)'.  Only after this is
done, can the strings be marked and extracted.

   GNU gettext uses the native C#/.NET internationalization mechanism,
namely the classes `ResourceManager' and `ResourceSet'.  Applications
use the `ResourceManager' methods to retrieve the native language
translation of strings.  An instance of `ResourceSet' is the in-memory
representation of a message catalog file.  The `ResourceManager' loads
and accesses `ResourceSet' instances as needed to look up the
translations.

   There are two formats of `ResourceSet's that can be directly loaded
by the C# runtime: `.resources' files and `.dll' files.

   * The `.resources' format is a binary file usually generated through
     the `resgen' or `monoresgen' utility, but which doesn't support
     plural forms.  `.resources' files can also be embedded in .NET
     `.exe' files.  This only affects whether a file system access is
     performed to load the message catalog; it doesn't affect the
     contents of the message catalog.

   * On the other hand, the `.dll' format is a binary file that is
     compiled from `.cs' source code and can support plural forms
     (provided it is accessed through the GNU gettext API, see below).

   Note that these .NET `.dll' and `.exe' files are not tied to a
particular platform; their file format and GNU gettext for C# can be
used on any platform.

   To convert a PO file to a `.resources' file, the `msgfmt' program
can be used with the option `--csharp-resources'.  To convert a
`.resources' file back to a PO file, the `msgunfmt' program can be used
with the option `--csharp-resources'.  You can also, in some cases, use
the `resgen' program (from the `pnet' package) or the `monoresgen'
program (from the `mono'/`mcs' package).  These programs can also
convert a `.resources' file back to a PO file.  But beware: as of this
writing (January 2004), the `monoresgen' converter is quite buggy and
the `resgen' converter ignores the encoding of the PO files.

   To convert a PO file to a `.dll' file, the `msgfmt' program can be
used with the option `--csharp'.  The result will be a `.dll' file
containing a subclass of `GettextResourceSet', which itself is a
subclass of `ResourceSet'.  To convert a `.dll' file containing a
`GettextResourceSet' subclass back to a PO file, the `msgunfmt' program
can be used with the option `--csharp'.

   The advantages of the `.dll' format over the `.resources' format are:

  1. Freedom to localize: Users can add their own translations to an
     application after it has been built and distributed.  Whereas when
     the programmer uses a `ResourceManager' constructor provided by
     the system, the set of `.resources' files for an application must
     be specified when the application is built and cannot be extended
     afterwards.

  2. Plural handling: A message catalog in `.dll' format supports the
     plural handling function `GetPluralString'.  Whereas `.resources'
     files can only contain data and only support lookups that depend
     on a single string.

  3. The `GettextResourceManager' that loads the message catalogs in
     `.dll' format also provides for inheritance on a per-message basis.
     For example, in Austrian (`de_AT') locale, translations from the
     German (`de') message catalog will be used for messages not found
     in the Austrian message catalog.  This has the consequence that
     the Austrian translators need only translate those few messages
     for which the translation into Austrian differs from the German
     one.  Whereas when working with `.resources' files, each message
     catalog must provide the translations of all messages by itself.

  4. The `GettextResourceManager' that loads the message catalogs in
     `.dll' format also provides for a fallback: The English MSGID is
     returned when no translation can be found.  Whereas when working
     with `.resources' files, a language-neutral `.resources' file must
     explicitly be provided as a fallback.

   On the side of the programmatic APIs, the programmer can use either
the standard `ResourceManager' API and the GNU `GettextResourceManager'
API.  The latter is an extension of the former, because
`GettextResourceManager' is a subclass of `ResourceManager'.

  1. The `System.Resources.ResourceManager' API.

     This API works with resources in `.resources' format.

     The creation of the `ResourceManager' is done through
            new ResourceManager(domainname, Assembly.GetExecutingAssembly())
     The `GetString' function returns a string's translation.  Note
     that this function returns null when a translation is missing
     (i.e. not even found in the fallback resource file).

  2. The `GNU.Gettext.GettextResourceManager' API.

     This API works with resources in `.dll' format.

     Reference documentation is in the csharpdoc directory
     (csharpdoc/index.html).

     The creation of the `ResourceManager' is done through
            new GettextResourceManager(domainname)

     The `GetString' function returns a string's translation.  Note
     that when a translation is missing, the MSGID argument is returned
     unchanged.

     The `GetPluralString' function returns a string translation with
     plural handling, like the `ngettext' function in C.

     To use this API, one needs the `GNU.Gettext.dll' file which is
     part of the GNU gettext package and distributed under the LGPL.

   You can also mix both approaches: use the
`GNU.Gettext.GettextResourceManager' constructor, but otherwise use
only the `ResourceManager' type and only the `GetString' method.  This
is appropriate when you want to profit from the tools for PO files, but
don't want to change an existing source code that uses
`ResourceManager' and don't (yet) need the `GetPluralString' method.

   Two examples, using the second API, are available in the `examples'
directory: `hello-csharp', `hello-csharp-forms'.

   Now, to make use of the API and define a shorthand for `GetString',
there are two idioms that you can choose from:

   * In a unique class of your project, say `Util', define a static
     variable holding the `ResourceManager' instance:

          public static GettextResourceManager MyResourceManager =
            new GettextResourceManager("domain-name");

     All classes containing internationalized strings then contain

          private static GettextResourceManager Res = Util.MyResourceManager;
          private static String _(String s) { return Res.GetString(s); }

     and the shorthand is used like this:

          Console.WriteLine(_("Operation completed."));

   * You add a class with a very short name, say `S', containing just
     the definition of the resource manager and of the shorthand:

          public class S {
            public static GettextResourceManager MyResourceManager =
              new GettextResourceManager("domain-name");
            public static String _(String s) {
               return MyResourceManager.GetString(s);
            }
          }

     and the shorthand is used like this:

          Console.WriteLine(S._("Operation completed."));

   Which of the two idioms you choose, will depend on whether copying
two lines of codes into every class is more acceptable in your project
than a class with a single-letter name.


File: gettext.info,  Node: gawk,  Next: Pascal,  Prev: C#,  Up: List of Programming Languages

13.5.13 GNU awk
---------------

RPMs
     gawk 3.1 or newer

File extension
     `awk'

String syntax
     `"abc"'

gettext shorthand
     `_"abc"'

gettext/ngettext functions
     `dcgettext', missing `dcngettext' in gawk-3.1.0

textdomain
     `TEXTDOMAIN' variable

bindtextdomain
     `bindtextdomain' function

setlocale
     automatic, but missing `setlocale (LC_MESSAGES, "")' in gawk-3.1.0

Prerequisite
     --

Use or emulate GNU gettext
     use

Extractor
     `xgettext'

Formatting with positions
     `printf "%2$d %1$d"' (GNU awk only)

Portability
     On platforms without gettext, no translation.  On non-GNU awks,
     you must define `dcgettext', `dcngettext' and `bindtextdomain'
     yourself.

po-mode marking
     --

   An example is available in the `examples' directory: `hello-gawk'.


File: gettext.info,  Node: Pascal,  Next: wxWindows,  Prev: gawk,  Up: List of Programming Languages

13.5.14 Pascal - Free Pascal Compiler
-------------------------------------

RPMs
     fpk

File extension
     `pp', `pas'

String syntax
     `'abc''

gettext shorthand
     automatic

gettext/ngettext functions
     --, use `ResourceString' data type instead

textdomain
     --, use `TranslateResourceStrings' function instead

bindtextdomain
     --, use `TranslateResourceStrings' function instead

setlocale
     automatic, but uses only LANG, not LC_MESSAGES or LC_ALL

Prerequisite
     `{$mode delphi}' or `{$mode objfpc}'
     `uses gettext;'

Use or emulate GNU gettext
     emulate partially

Extractor
     `ppc386' followed by `xgettext' or `rstconv'

Formatting with positions
     `uses sysutils;'
     `format "%1:d %0:d"'

Portability
     ?

po-mode marking
     --

   The Pascal compiler has special support for the `ResourceString' data
type.  It generates a `.rst' file.  This is then converted to a `.pot'
file by use of `xgettext' or `rstconv'.  At runtime, a `.mo' file
corresponding to translations of this `.pot' file can be loaded using
the `TranslateResourceStrings' function in the `gettext' unit.

   An example is available in the `examples' directory: `hello-pascal'.


File: gettext.info,  Node: wxWindows,  Next: YCP,  Prev: Pascal,  Up: List of Programming Languages

13.5.15 wxWindows library
-------------------------

RPMs
     wxGTK, gettext

File extension
     `cpp'

String syntax
     `"abc"'

gettext shorthand
     `_("abc")'

gettext/ngettext functions
     `wxLocale::GetString', `wxGetTranslation'

textdomain
     `wxLocale::AddCatalog'

bindtextdomain
     `wxLocale::AddCatalogLookupPathPrefix'

setlocale
     `wxLocale::Init', `wxSetLocale'

Prerequisite
     `#include <wx/intl.h>'

Use or emulate GNU gettext
     emulate, see `include/wx/intl.h' and `src/common/intl.cpp'

Extractor
     `xgettext'

Formatting with positions
     --

Portability
     fully portable

po-mode marking
     yes


File: gettext.info,  Node: YCP,  Next: Tcl,  Prev: wxWindows,  Up: List of Programming Languages

13.5.16 YCP - YaST2 scripting language
--------------------------------------

RPMs
     libycp, libycp-devel, yast2-core, yast2-core-devel

File extension
     `ycp'

String syntax
     `"abc"'

gettext shorthand
     `_("abc")'

gettext/ngettext functions
     `_()' with 1 or 3 arguments

textdomain
     `textdomain' statement

bindtextdomain
     --

setlocale
     --

Prerequisite
     --

Use or emulate GNU gettext
     use

Extractor
     `xgettext'

Formatting with positions
     `sformat "%2 %1"'

Portability
     fully portable

po-mode marking
     --

   An example is available in the `examples' directory: `hello-ycp'.


File: gettext.info,  Node: Tcl,  Next: Perl,  Prev: YCP,  Up: List of Programming Languages

13.5.17 Tcl - Tk's scripting language
-------------------------------------

RPMs
     tcl

File extension
     `tcl'

String syntax
     `"abc"'

gettext shorthand
     `[_ "abc"]'

gettext/ngettext functions
     `::msgcat::mc'

textdomain
     --

bindtextdomain
     --, use `::msgcat::mcload' instead

setlocale
     automatic, uses LANG, but ignores LC_MESSAGES and LC_ALL

Prerequisite
     `package require msgcat'
     `proc _ {s} {return [::msgcat::mc $s]}'

Use or emulate GNU gettext
     --, uses a Tcl specific message catalog format

Extractor
     `xgettext -k_'

Formatting with positions
     `format "%2\$d %1\$d"'

Portability
     fully portable

po-mode marking
     --

   Two examples are available in the `examples' directory: `hello-tcl',
`hello-tcl-tk'.

   Before marking strings as internationalizable, substitutions of
variables into the string need to be converted to `format'
applications.  For example, `"file $filename not found"' becomes
`[format "file %s not found" $filename]'.  Only after this is done, can
the strings be marked and extracted.  After marking, this example
becomes `[format [_ "file %s not found"] $filename]' or `[msgcat::mc
"file %s not found" $filename]'.  Note that the `msgcat::mc' function
implicitly calls `format' when more than one argument is given.


File: gettext.info,  Node: Perl,  Next: PHP,  Prev: Tcl,  Up: List of Programming Languages

13.5.18 Perl
------------

RPMs
     perl

File extension
     `pl', `PL', `pm', `cgi'

String syntax
        * `"abc"'

        * `'abc''

        * `qq (abc)'

        * `q (abc)'

        * `qr /abc/'

        * `qx (/bin/date)'

        * `/pattern match/'

        * `?pattern match?'

        * `s/substitution/operators/'

        * `$tied_hash{"message"}'

        * `$tied_hash_reference->{"message"}'

        * etc., issue the command `man perlsyn' for details


gettext shorthand
     `__' (double underscore)

gettext/ngettext functions
     `gettext', `dgettext', `dcgettext', `ngettext', `dngettext',
     `dcngettext'

textdomain
     `textdomain' function

bindtextdomain
     `bindtextdomain' function

bind_textdomain_codeset
     `bind_textdomain_codeset' function

setlocale
     Use `setlocale (LC_ALL, "");'

Prerequisite
     `use POSIX;'
     `use Locale::TextDomain;' (included in the package libintl-perl
     which is available on the Comprehensive Perl Archive Network CPAN,
     http://www.cpan.org/).

Use or emulate GNU gettext
     platform dependent: gettext_pp emulates, gettext_xs uses GNU
     gettext

Extractor
     `xgettext -k__ -k\$__ -k%__ -k__x -k__n:1,2 -k__nx:1,2 -k__xn:1,2
     -kN__ -k'

Formatting with positions
     Both kinds of format strings support formatting with positions.
     `printf "%2\$d %1\$d", ...' (requires Perl 5.8.0 or newer)
     `__expand("[new] replaces [old]", old => $oldvalue, new =>
     $newvalue)'

Portability
     The `libintl-perl' package is platform independent but is not part
     of the Perl core.  The programmer is responsible for providing a
     dummy implementation of the required functions if the package is
     not installed on the target system.

po-mode marking
     --

Documentation
     Included in `libintl-perl', available on CPAN
     (http://www.cpan.org/).


   An example is available in the `examples' directory: `hello-perl'.

   The `xgettext' parser backend for Perl differs significantly from
the parser backends for other programming languages, just as Perl
itself differs significantly from other programming languages.  The
Perl parser backend offers many more string marking facilities than the
other backends but it also has some Perl specific limitations, the
worst probably being its imperfectness.

* Menu:

* General Problems::            General Problems Parsing Perl Code
* Default Keywords::            Which Keywords Will xgettext Look For?
* Special Keywords::            How to Extract Hash Keys
* Quote-like Expressions::      What are Strings And Quote-like Expressions?
* Interpolation I::             Invalid String Interpolation
* Interpolation II::            Valid String Interpolation
* Parentheses::                 When To Use Parentheses
* Long Lines::                  How To Grok with Long Lines
* Perl Pitfalls::               Bugs, Pitfalls, and Things That Do Not Work


File: gettext.info,  Node: General Problems,  Next: Default Keywords,  Up: Perl

13.5.18.1 General Problems Parsing Perl Code
............................................

It is often heard that only Perl can parse Perl.  This is not true.
Perl cannot be _parsed_ at all, it can only be _executed_.  Perl has
various built-in ambiguities that can only be resolved at runtime.

   The following example may illustrate one common problem:

     print gettext "Hello World!";

   Although this example looks like a bullet-proof case of a function
invocation, it is not:

     open gettext, ">testfile" or die;
     print gettext "Hello world!"

   In this context, the string `gettext' looks more like a file handle.
But not necessarily:

     use Locale::Messages qw (:libintl_h);
     open gettext ">testfile" or die;
     print gettext "Hello world!";

   Now, the file is probably syntactically incorrect, provided that the
module `Locale::Messages' found first in the Perl include path exports a
function `gettext'.  But what if the module `Locale::Messages' really
looks like this?

     use vars qw (*gettext);

     1;

   In this case, the string `gettext' will be interpreted as a file
handle again, and the above example will create a file `testfile' and
write the string "Hello world!" into it.  Even advanced control flow
analysis will not really help:

     if (0.5 < rand) {
        eval "use Sane";
     } else {
        eval "use InSane";
     }
     print gettext "Hello world!";

   If the module `Sane' exports a function `gettext' that does what we
expect, and the module `InSane' opens a file for writing and associates
the _handle_ `gettext' with this output stream, we are clueless again
about what will happen at runtime.  It is completely unpredictable.
The truth is that Perl has so many ways to fill its symbol table at
runtime that it is impossible to interpret a particular piece of code
without executing it.

   Of course, `xgettext' will not execute your Perl sources while
scanning for translatable strings, but rather use heuristics in order
to guess what you meant.

   Another problem is the ambiguity of the slash and the question mark.
Their interpretation depends on the context:

     # A pattern match.
     print "OK\n" if /foobar/;

     # A division.
     print 1 / 2;

     # Another pattern match.
     print "OK\n" if ?foobar?;

     # Conditional.
     print $x ? "foo" : "bar";

   The slash may either act as the division operator or introduce a
pattern match, whereas the question mark may act as the ternary
conditional operator or as a pattern match, too.  Other programming
languages like `awk' present similar problems, but the consequences of a
misinterpretation are particularly nasty with Perl sources.  In `awk'
for instance, a statement can never exceed one line and the parser can
recover from a parsing error at the next newline and interpret the rest
of the input stream correctly.  Perl is different, as a pattern match
is terminated by the next appearance of the delimiter (the slash or the
question mark) in the input stream, regardless of the semantic context.
If a slash is really a division sign but mis-interpreted as a pattern
match, the rest of the input file is most probably parsed incorrectly.

   If you find that `xgettext' fails to extract strings from portions
of your sources, you should therefore look out for slashes and/or
question marks preceding these sections.  You may have come across a
bug in `xgettext''s Perl parser (and of course you should report that
bug).  In the meantime you should consider to reformulate your code in
a manner less challenging to `xgettext'.


File: gettext.info,  Node: Default Keywords,  Next: Special Keywords,  Prev: General Problems,  Up: Perl

13.5.18.2 Which keywords will xgettext look for?
................................................

Unless you instruct `xgettext' otherwise by invoking it with one of the
options `--keyword' or `-k', it will recognize the following keywords
in your Perl sources:

   * `gettext'

   * `dgettext'

   * `dcgettext'

   * `ngettext:1,2'

     The first (singular) and the second (plural) argument will be
     extracted.

   * `dngettext:1,2'

     The first (singular) and the second (plural) argument will be
     extracted.

   * `dcngettext:1,2'

     The first (singular) and the second (plural) argument will be
     extracted.

   * `gettext_noop'

   * `%gettext'

     The keys of lookups into the hash `%gettext' will be extracted.

   * `$gettext'

     The keys of lookups into the hash reference `$gettext' will be
     extracted.



File: gettext.info,  Node: Special Keywords,  Next: Quote-like Expressions,  Prev: Default Keywords,  Up: Perl

13.5.18.3 How to Extract Hash Keys
..................................

Translating messages at runtime is normally performed by looking up the
original string in the translation database and returning the
translated version.  The "natural" Perl implementation is a hash
lookup, and, of course, `xgettext' supports such practice.

     print __"Hello world!";
     print $__{"Hello world!"};
     print $__->{"Hello world!"};
     print $$__{"Hello world!"};

   The above four lines all do the same thing.  The Perl module
`Locale::TextDomain' exports by default a hash `%__' that is tied to
the function `__()'.  It also exports a reference `$__' to `%__'.

   If an argument to the `xgettext' option `--keyword', resp. `-k'
starts with a percent sign, the rest of the keyword is interpreted as
the name of a hash.  If it starts with a dollar sign, the rest of the
keyword is interpreted as a reference to a hash.

   Note that you can omit the quotation marks (single or double) around
the hash key (almost) whenever Perl itself allows it:

     print $gettext{Error};

   The exact rule is: You can omit the surrounding quotes, when the hash
key is a valid C (!) identifier, i. e. when it starts with an
underscore or an ASCII letter and is followed by an arbitrary number of
underscores, ASCII letters or digits.  Other Unicode characters are
_not_ allowed, regardless of the `use utf8' pragma.


File: gettext.info,  Node: Quote-like Expressions,  Next: Interpolation I,  Prev: Special Keywords,  Up: Perl

13.5.18.4 What are Strings And Quote-like Expressions?
......................................................

Perl offers a plethora of different string constructs.  Those that can
be used either as arguments to functions or inside braces for hash
lookups are generally supported by `xgettext'.

   * *double-quoted strings*
          print gettext "Hello World!";

   * *single-quoted strings*
          print gettext 'Hello World!';

   * *the operator qq*
          print gettext qq |Hello World!|;
          print gettext qq <E-mail: <guido\@imperia.net>>;

     The operator `qq' is fully supported.  You can use arbitrary
     delimiters, including the four bracketing delimiters (round, angle,
     square, curly) that nest.

   * *the operator q*
          print gettext q |Hello World!|;
          print gettext q <E-mail: <guido@imperia.net>>;

     The operator `q' is fully supported.  You can use arbitrary
     delimiters, including the four bracketing delimiters (round, angle,
     square, curly) that nest.

   * *the operator qx*
          print gettext qx ;LANGUAGE=C /bin/date;
          print gettext qx [/usr/bin/ls | grep '^[A-Z]*'];

     The operator `qx' is fully supported.  You can use arbitrary
     delimiters, including the four bracketing delimiters (round, angle,
     square, curly) that nest.

     The example is actually a useless use of `gettext'.  It will
     invoke the `gettext' function on the output of the command
     specified with the `qx' operator.  The feature was included in
     order to make the interface consistent (the parser will extract
     all strings and quote-like expressions).

   * *here documents*
          print gettext <<'EOF';
          program not found in $PATH
          EOF

          print ngettext <<EOF, <<"EOF";
          one file deleted
          EOF
          several files deleted
          EOF

     Here-documents are recognized.  If the delimiter is enclosed in
     single quotes, the string is not interpolated.  If it is enclosed
     in double quotes or has no quotes at all, the string is
     interpolated.

     Delimiters that start with a digit are not supported!



File: gettext.info,  Node: Interpolation I,  Next: Interpolation II,  Prev: Quote-like Expressions,  Up: Perl

13.5.18.5 Invalid Uses Of String Interpolation
..............................................

Perl is capable of interpolating variables into strings.  This offers
some nice features in localized programs but can also lead to problems.

   A common error is a construct like the following:

     print gettext "This is the program $0!\n";

   Perl will interpolate at runtime the value of the variable `$0' into
the argument of the `gettext()' function.  Hence, this argument is not
a string constant but a variable argument (`$0' is a global variable
that holds the name of the Perl script being executed).  The
interpolation is performed by Perl before the string argument is passed
to `gettext()' and will therefore depend on the name of the script
which can only be determined at runtime.  Consequently, it is almost
impossible that a translation can be looked up at runtime (except if,
by accident, the interpolated string is found in the message catalog).

   The `xgettext' program will therefore terminate parsing with a fatal
error if it encounters a variable inside of an extracted string.  In
general, this will happen for all kinds of string interpolations that
cannot be safely performed at compile time.  If you absolutely know
what you are doing, you can always circumvent this behavior:

     my $know_what_i_am_doing = "This is program $0!\n";
     print gettext $know_what_i_am_doing;

   Since the parser only recognizes strings and quote-like expressions,
but not variables or other terms, the above construct will be accepted.
You will have to find another way, however, to let your original
string make it into your message catalog.

   If invoked with the option `--extract-all', resp. `-a', variable
interpolation will be accepted.  Rationale: You will generally use this
option in order to prepare your sources for internationalization.

   Please see the manual page `man perlop' for details of strings and
quote-like expressions that are subject to interpolation and those that
are not.  Safe interpolations (that will not lead to a fatal error) are:

   * the escape sequences `\t' (tab, HT, TAB), `\n' (newline, NL), `\r'
     (return, CR), `\f' (form feed, FF), `\b' (backspace, BS), `\a'
     (alarm, bell, BEL), and `\e' (escape, ESC).

   * octal chars, like `\033'
     Note that octal escapes in the range of 400-777 are translated
     into a UTF-8 representation, regardless of the presence of the
     `use utf8' pragma.

   * hex chars, like `\x1b'

   * wide hex chars, like `\x{263a}'
     Note that this escape is translated into a UTF-8 representation,
     regardless of the presence of the `use utf8' pragma.

   * control chars, like `\c[' (CTRL-[)

   * named Unicode chars, like `\N{LATIN CAPITAL LETTER C WITH CEDILLA}'
     Note that this escape is translated into a UTF-8 representation,
     regardless of the presence of the `use utf8' pragma.

   The following escapes are considered partially safe:

   * `\l' lowercase next char

   * `\u' uppercase next char

   * `\L' lowercase till \E

   * `\U' uppercase till \E

   * `\E' end case modification

   * `\Q' quote non-word characters till \E


   These escapes are only considered safe if the string consists of
ASCII characters only.  Translation of characters outside the range
defined by ASCII is locale-dependent and can actually only be performed
at runtime; `xgettext' doesn't do these locale-dependent translations
at extraction time.

   Except for the modifier `\Q', these translations, albeit valid, are
generally useless and only obfuscate your sources.  If a translation
can be safely performed at compile time you can just as well write what
you mean.


File: gettext.info,  Node: Interpolation II,  Next: Parentheses,  Prev: Interpolation I,  Up: Perl

13.5.18.6 Valid Uses Of String Interpolation
............................................

Perl is often used to generate sources for other programming languages
or arbitrary file formats.  Web applications that output HTML code make
a prominent example for such usage.

   You will often come across situations where you want to intersperse
code written in the target (programming) language with translatable
messages, like in the following HTML example:

     print gettext <<EOF;
     <h1>My Homepage</h1>
     <script language="JavaScript"><!--
     for (i = 0; i < 100; ++i) {
         alert ("Thank you so much for visiting my homepage!");
     }
     //--></script>
     EOF

   The parser will extract the entire here document, and it will appear
entirely in the resulting PO file, including the JavaScript snippet
embedded in the HTML code.  If you exaggerate with constructs like the
above, you will run the risk that the translators of your package will
look out for a less challenging project.  You should consider an
alternative expression here:

     print <<EOF;
     <h1>$gettext{"My Homepage"}</h1>
     <script language="JavaScript"><!--
     for (i = 0; i < 100; ++i) {
         alert ("$gettext{'Thank you so much for visiting my homepage!'}");
     }
     //--></script>
     EOF

   Only the translatable portions of the code will be extracted here,
and the resulting PO file will begrudgingly improve in terms of
readability.

   You can interpolate hash lookups in all strings or quote-like
expressions that are subject to interpolation (see the manual page `man
perlop' for details).  Double interpolation is invalid, however:

     # TRANSLATORS: Replace "the earth" with the name of your planet.
     print gettext qq{Welcome to $gettext->{"the earth"}};

   The `qq'-quoted string is recognized as an argument to `xgettext' in
the first place, and checked for invalid variable interpolation.  The
dollar sign of hash-dereferencing will therefore terminate the parser
with an "invalid interpolation" error.

   It is valid to interpolate hash lookups in regular expressions:

     if ($var =~ /$gettext{"the earth"}/) {
        print gettext "Match!\n";
     }
     s/$gettext{"U. S. A."}/$gettext{"U. S. A."} $gettext{"(dial +0)"}/g;


File: gettext.info,  Node: Parentheses,  Next: Long Lines,  Prev: Interpolation II,  Up: Perl

13.5.18.7 When To Use Parentheses
.................................

In Perl, parentheses around function arguments are mostly optional.
`xgettext' will always assume that all recognized keywords (except for
hashs and hash references) are names of properly prototyped functions,
and will (hopefully) only require parentheses where Perl itself
requires them.  All constructs in the following example are therefore
ok to use:

     print gettext ("Hello World!\n");
     print gettext "Hello World!\n";
     print dgettext ($package => "Hello World!\n");
     print dgettext $package, "Hello World!\n";

     # The "fat comma" => turns the left-hand side argument into a
     # single-quoted string!
     print dgettext smellovision => "Hello World!\n";

     # The following assignment only works with prototyped functions.
     # Otherwise, the functions will act as "greedy" list operators and
     # eat up all following arguments.
     my $anonymous_hash = {
        planet => gettext "earth",
        cakes => ngettext "one cake", "several cakes", $n,
        still => $works,
     };
     # The same without fat comma:
     my $other_hash = {
        'planet', gettext "earth",
        'cakes', ngettext "one cake", "several cakes", $n,
        'still', $works,
     };

     # Parentheses are only significant for the first argument.
     print dngettext 'package', ("one cake", "several cakes", $n), $discarded;


File: gettext.info,  Node: Long Lines,  Next: Perl Pitfalls,  Prev: Parentheses,  Up: Perl

13.5.18.8 How To Grok with Long Lines
.....................................

The necessity of long messages can often lead to a cumbersome or
unreadable coding style.  Perl has several options that may prevent you
from writing unreadable code, and `xgettext' does its best to do
likewise.  This is where the dot operator (the string concatenation
operator) may come in handy:

     print gettext ("This is a very long"
                    . " message that is still"
                    . " readable, because"
                    . " it is split into"
                    . " multiple lines.\n");

   Perl is smart enough to concatenate these constant string fragments
into one long string at compile time, and so is `xgettext'.  You will
only find one long message in the resulting POT file.

   Note that the future Perl 6 will probably use the underscore (`_')
as the string concatenation operator, and the dot (`.') for
dereferencing.  This new syntax is not yet supported by `xgettext'.

   If embedded newline characters are not an issue, or even desired, you
may also insert newline characters inside quoted strings wherever you
feel like it:

     print gettext ("<em>In HTML output
     embedded newlines are generally no
     problem, since adjacent whitespace
     is always rendered into a single
     space character.</em>");

   You may also consider to use here documents:

     print gettext <<EOF;
     <em>In HTML output
     embedded newlines are generally no
     problem, since adjacent whitespace
     is always rendered into a single
     space character.</em>
     EOF

   Please do not forget, that the line breaks are real, i. e. they
translate into newline characters that will consequently show up in the
resulting POT file.


File: gettext.info,  Node: Perl Pitfalls,  Prev: Long Lines,  Up: Perl

13.5.18.9 Bugs, Pitfalls, And Things That Do Not Work
.....................................................

The foregoing sections should have proven that `xgettext' is quite
smart in extracting translatable strings from Perl sources.  Yet, some
more or less exotic constructs that could be expected to work, actually
do not work.

   One of the more relevant limitations can be found in the
implementation of variable interpolation inside quoted strings.  Only
simple hash lookups can be used there:

     print <<EOF;
     $gettext{"The dot operator"
               . " does not work"
               . "here!"}
     Likewise, you cannot @{[ gettext ("interpolate function calls") ]}
     inside quoted strings or quote-like expressions.
     EOF

   This is valid Perl code and will actually trigger invocations of the
`gettext' function at runtime.  Yet, the Perl parser in `xgettext' will
fail to recognize the strings.  A less obvious example can be found in
the interpolation of regular expressions:

     s/<!--START_OF_WEEK-->/gettext ("Sunday")/e;

   The modifier `e' will cause the substitution to be interpreted as an
evaluable statement.  Consequently, at runtime the function `gettext()'
is called, but again, the parser fails to extract the string "Sunday".
Use a temporary variable as a simple workaround if you really happen to
need this feature:

     my $sunday = gettext "Sunday";
     s/<!--START_OF_WEEK-->/$sunday/;

   Hash slices would also be handy but are not recognized:

     my @weekdays = @gettext{'Sunday', 'Monday', 'Tuesday', 'Wednesday',
                             'Thursday', 'Friday', 'Saturday'};
     # Or even:
     @weekdays = @gettext{qw (Sunday Monday Tuesday Wednesday Thursday
                              Friday Saturday) };

   This is perfectly valid usage of the tied hash `%gettext' but the
strings are not recognized and therefore will not be extracted.

   Another caveat of the current version is its rudimentary support for
non-ASCII characters in identifiers.  You may encounter serious
problems if you use identifiers with characters outside the range of
'A'-'Z', 'a'-'z', '0'-'9' and the underscore '_'.

   Maybe some of these missing features will be implemented in future
versions, but since you can always make do without them at minimal
effort, these todos have very low priority.

   A nasty problem are brace format strings that already contain braces
as part of the normal text, for example the usage strings typically
encountered in programs:

     die "usage: $0 {OPTIONS} FILENAME...\n";

   If you want to internationalize this code with Perl brace format
strings, you will run into a problem:

     die __x ("usage: {program} {OPTIONS} FILENAME...\n", program => $0);

   Whereas `{program}' is a placeholder, `{OPTIONS}' is not and should
probably be translated. Yet, there is no way to teach the Perl parser
in `xgettext' to recognize the first one, and leave the other one alone.

   There are two possible work-arounds for this problem.  If you are
sure that your program will run under Perl 5.8.0 or newer (these Perl
versions handle positional parameters in `printf()') or if you are sure
that the translator will not have to reorder the arguments in her
translation - for example if you have only one brace placeholder in
your string, or if it describes a syntax, like in this one -, you can
mark the string as `no-perl-brace-format' and use `printf()':

     # xgettext: no-perl-brace-format
     die sprintf ("usage: %s {OPTIONS} FILENAME...\n", $0);

   If you want to use the more portable Perl brace format, you will
have to do put placeholders in place of the literal braces:

     die __x ("usage: {program} {[}OPTIONS{]} FILENAME...\n",
              program => $0, '[' => '{', ']' => '}');

   Perl brace format strings know no escaping mechanism.  No matter how
this escaping mechanism looked like, it would either give the
programmer a hard time, make translating Perl brace format strings
heavy-going, or result in a performance penalty at runtime, when the
format directives get executed.  Most of the time you will happily get
along with `printf()' for this special case.


File: gettext.info,  Node: PHP,  Next: Pike,  Prev: Perl,  Up: List of Programming Languages

13.5.19 PHP Hypertext Preprocessor
----------------------------------

RPMs
     mod_php4, mod_php4-core, phpdoc

File extension
     `php', `php3', `php4'

String syntax
     `"abc"', `'abc''

gettext shorthand
     `_("abc")'

gettext/ngettext functions
     `gettext', `dgettext', `dcgettext'; starting with PHP 4.2.0 also
     `ngettext', `dngettext', `dcngettext'

textdomain
     `textdomain' function

bindtextdomain
     `bindtextdomain' function

setlocale
     Programmer must call `setlocale (LC_ALL, "")'

Prerequisite
     --

Use or emulate GNU gettext
     use

Extractor
     `xgettext'

Formatting with positions
     `printf "%2\$d %1\$d"'

Portability
     On platforms without gettext, the functions are not available.

po-mode marking
     --

   An example is available in the `examples' directory: `hello-php'.


File: gettext.info,  Node: Pike,  Next: GCC-source,  Prev: PHP,  Up: List of Programming Languages

13.5.20 Pike
------------

RPMs
     roxen

File extension
     `pike'

String syntax
     `"abc"'

gettext shorthand
     --

gettext/ngettext functions
     `gettext', `dgettext', `dcgettext'

textdomain
     `textdomain' function

bindtextdomain
     `bindtextdomain' function

setlocale
     `setlocale' function

Prerequisite
     `import Locale.Gettext;'

Use or emulate GNU gettext
     use

Extractor
     --

Formatting with positions
     --

Portability
     On platforms without gettext, the functions are not available.

po-mode marking
     --


File: gettext.info,  Node: GCC-source,  Prev: Pike,  Up: List of Programming Languages

13.5.21 GNU Compiler Collection sources
---------------------------------------

RPMs
     gcc

File extension
     `c', `h'.

String syntax
     `"abc"'

gettext shorthand
     `_("abc")'

gettext/ngettext functions
     `gettext', `dgettext', `dcgettext', `ngettext', `dngettext',
     `dcngettext'

textdomain
     `textdomain' function

bindtextdomain
     `bindtextdomain' function

setlocale
     Programmer must call `setlocale (LC_ALL, "")'

Prerequisite
     `#include "intl.h"'

Use or emulate GNU gettext
     Use

Extractor
     `xgettext -k_'

Formatting with positions
     --

Portability
     Uses autoconf macros

po-mode marking
     yes


File: gettext.info,  Node: List of Data Formats,  Prev: List of Programming Languages,  Up: Programming Languages

13.6 Internationalizable Data
=============================

Here is a list of other data formats which can be internationalized
using GNU gettext.

* Menu:

* POT::                         POT - Portable Object Template
* RST::                         Resource String Table
* Glade::                       Glade - GNOME user interface description


File: gettext.info,  Node: POT,  Next: RST,  Prev: List of Data Formats,  Up: List of Data Formats

13.6.1 POT - Portable Object Template
-------------------------------------

RPMs
     gettext

File extension
     `pot', `po'

Extractor
     `xgettext'


File: gettext.info,  Node: RST,  Next: Glade,  Prev: POT,  Up: List of Data Formats

13.6.2 Resource String Table
----------------------------

RPMs
     fpk

File extension
     `rst'

Extractor
     `xgettext', `rstconv'


File: gettext.info,  Node: Glade,  Prev: RST,  Up: List of Data Formats

13.6.3 Glade - GNOME user interface description
-----------------------------------------------

RPMs
     glade, libglade, glade2, libglade2, intltool

File extension
     `glade', `glade2'

Extractor
     `xgettext', `libglade-xgettext', `xml-i18n-extract',
     `intltool-extract'


File: gettext.info,  Node: Conclusion,  Next: Language Codes,  Prev: Programming Languages,  Up: Top

14 Concluding Remarks
*********************

We would like to conclude this GNU `gettext' manual by presenting an
history of the Translation Project so far.  We finally give a few
pointers for those who want to do further research or readings about
Native Language Support matters.

* Menu:

* History::                     History of GNU `gettext'
* References::                  Related Readings


File: gettext.info,  Node: History,  Next: References,  Prev: Conclusion,  Up: Conclusion

14.1 History of GNU `gettext'
=============================

Internationalization concerns and algorithms have been informally and
casually discussed for years in GNU, sometimes around GNU `libc', maybe
around the incoming `Hurd', or otherwise (nobody clearly remembers).
And even then, when the work started for real, this was somewhat
independently of these previous discussions.

   This all began in July 1994, when Patrick D'Cruze had the idea and
initiative of internationalizing version 3.9.2 of GNU `fileutils'.  He
then asked Jim Meyering, the maintainer, how to get those changes
folded into an official release.  That first draft was full of
`#ifdef's and somewhat disconcerting, and Jim wanted to find nicer
ways.  Patrick and Jim shared some tries and experimentations in this
area.  Then, feeling that this might eventually have a deeper impact on
GNU, Jim wanted to know what standards were, and contacted Richard
Stallman, who very quickly and verbally described an overall design for
what was meant to become `glocale', at that time.

   Jim implemented `glocale' and got a lot of exhausting feedback from
Patrick and Richard, of course, but also from Mitchum DSouza (who wrote
a `catgets'-like package), Roland McGrath, maybe David MacKenzie,
Franc,ois Pinard, and Paul Eggert, all pushing and pulling in various
directions, not always compatible, to the extent that after a couple of
test releases, `glocale' was torn apart.  In particular, Paul Eggert -
always keeping an eye on developments in Solaris - advocated the use of
the `gettext' API over `glocale''s `catgets'-based API.

   While Jim took some distance and time and became dad for a second
time, Roland wanted to get GNU `libc' internationalized, and got Ulrich
Drepper involved in that project.  Instead of starting from `glocale',
Ulrich rewrote something from scratch, but more conformant to the set
of guidelines who emerged out of the `glocale' effort.  Then, Ulrich
got people from the previous forum to involve themselves into this new
project, and the switch from `glocale' to what was first named
`msgutils', renamed `nlsutils', and later `gettext', became officially
accepted by Richard in May 1995 or so.

   Let's summarize by saying that Ulrich Drepper wrote GNU `gettext' in
April 1995.  The first official release of the package, including PO
mode, occurred in July 1995, and was numbered 0.7.  Other people
contributed to the effort by providing a discussion forum around
Ulrich, writing little pieces of code, or testing.  These are quoted in
the `THANKS' file which comes with the GNU `gettext' distribution.

   While this was being done, Franc,ois adapted half a dozen of GNU
packages to `glocale' first, then later to `gettext', putting them in
pretest, so providing along the way an effective user environment for
fine tuning the evolving tools.  He also took the responsibility of
organizing and coordinating the Translation Project.  After nearly a
year of informal exchanges between people from many countries,
translator teams started to exist in May 1995, through the creation and
support by Patrick D'Cruze of twenty unmoderated mailing lists for that
many native languages, and two moderated lists: one for reaching all
teams at once, the other for reaching all willing maintainers of
internationalized free software packages.

   Franc,ois also wrote PO mode in June 1995 with the collaboration of
Greg McGary, as a kind of contribution to Ulrich's package.  He also
gave a hand with the GNU `gettext' Texinfo manual.

   In 1997, Ulrich Drepper released the GNU libc 2.0, which included the
`gettext', `textdomain' and `bindtextdomain' functions.

   In 2000, Ulrich Drepper added plural form handling (the `ngettext'
function) to GNU libc.  Later, in 2001, he released GNU libc 2.2.x,
which is the first free C library with full internationalization
support.

   Ulrich being quite busy in his role of General Maintainer of GNU
libc, he handed over the GNU `gettext' maintenance to Bruno Haible in
2000.  Bruno added the plural form handling to the tools as well, added
support for UTF-8 and CJK locales, and wrote a few new tools for
manipulating PO files.


File: gettext.info,  Node: References,  Prev: History,  Up: Conclusion

14.2 Related Readings
=====================

Eugene H. Dorr (`dorre@well.com') maintains an interesting bibliography
on internationalization matters, called `Internationalization Reference
List', which is available as:
     ftp://ftp.ora.com/pub/examples/nutshell/ujip/doc/i18n-books.txt

   Michael Gschwind (`mike@vlsivie.tuwien.ac.at') maintains a
Frequently Asked Questions (FAQ) list, entitled `Programming for
Internationalisation'.  This FAQ discusses writing programs which can
handle different language conventions, character sets, etc.; and is
applicable to all character set encodings, with particular emphasis on
ISO 8859-1.  It is regularly published in Usenet groups
`comp.unix.questions', `comp.std.internat',
`comp.software.international', `comp.lang.c', `comp.windows.x',
`comp.std.c', `comp.answers' and `news.answers'.  The home location of
this document is:
     ftp://ftp.vlsivie.tuwien.ac.at/pub/8bit/ISO-programming

   Patrick D'Cruze (`pdcruze@li.org') wrote a tutorial about NLS
matters, and Jochen Hein (`Hein@student.tu-clausthal.de') took over the
responsibility of maintaining it.  It may be found as:
     ftp://sunsite.unc.edu/pub/Linux/utils/nls/catalogs/Incoming/...
          ...locale-tutorial-0.8.txt.gz
   This site is mirrored in:
     ftp://ftp.ibp.fr/pub/linux/sunsite/

   A French version of the same tutorial should be findable at:
     ftp://ftp.ibp.fr/pub/linux/french/docs/
   together with French translations of many Linux-related documents.


File: gettext.info,  Node: Language Codes,  Next: Country Codes,  Prev: Conclusion,  Up: Top

Appendix A Language Codes
*************************

The ISO 639 standard defines two character codes for many languages.
All abbreviations for languages used in the Translation Project should
come from this standard.

`aa'
     Afar.

`ab'
     Abkhazian.

`ae'
     Avestan.

`af'
     Afrikaans.

`ak'
     Akan.

`am'
     Amharic.

`an'
     Aragonese.

`ar'
     Arabic.

`as'
     Assamese.

`av'
     Avaric.

`ay'
     Aymara.

`az'
     Azerbaijani.

`ba'
     Bashkir.

`be'
     Byelorussian; Belarusian.

`bg'
     Bulgarian.

`bh'
     Bihari.

`bi'
     Bislama.

`bm'
     Bambara.

`bn'
     Bengali; Bangla.

`bo'
     Tibetan.

`br'
     Breton.

`bs'
     Bosnian.

`ca'
     Catalan.

`ce'
     Chechen.

`ch'
     Chamorro.

`co'
     Corsican.

`cr'
     Cree.

`cs'
     Czech.

`cu'
     Church Slavic.

`cv'
     Chuvash.

`cy'
     Welsh.

`da'
     Danish.

`de'
     German.

`dv'
     Divehi.

`dz'
     Dzongkha; Bhutani.

`ee'
     E'we'.

`el'
     Greek.

`en'
     English.

`eo'
     Esperanto.

`es'
     Spanish.

`et'
     Estonian.

`eu'
     Basque.

`fa'
     Persian.

`ff'
     Fulah.

`fi'
     Finnish.

`fj'
     Fijian; Fiji.

`fo'
     Faroese.

`fr'
     French.

`fy'
     Frisian.

`ga'
     Irish.

`gd'
     Scots; Gaelic.

`gl'
     Gallegan; Galician.

`gn'
     Guarani.

`gu'
     Gujarati.

`gv'
     Manx.

`ha'
     Hausa (?).

`he'
     Hebrew (formerly iw).

`hi'
     Hindi.

`ho'
     Hiri Motu.

`hr'
     Croatian.

`ht'
     Haitian; Haitian Creole.

`hu'
     Hungarian.

`hy'
     Armenian.

`hz'
     Herero.

`ia'
     Interlingua.

`id'
     Indonesian (formerly in).

`ie'
     Interlingue.

`ig'
     Igbo.

`ii'
     Sichuan Yi.

`ik'
     Inupiak.

`io'
     Ido.

`is'
     Icelandic.

`it'
     Italian.

`iu'
     Inuktitut.

`ja'
     Japanese.

`jv'
     Javanese.

`ka'
     Georgian.

`kg'
     Kongo.

`ki'
     Kikuyu.

`kj'
     Kuanyama.

`kk'
     Kazakh.

`kl'
     Kalaallisut; Greenlandic.

`km'
     Khmer; Cambodian.

`kn'
     Kannada.

`ko'
     Korean.

`kr'
     Kanuri.

`ks'
     Kashmiri.

`ku'
     Kurdish.

`kv'
     Komi.

`kw'
     Cornish.

`ky'
     Kirghiz.

`la'
     Latin.

`lb'
     Letzeburgesch.

`lg'
     Ganda.

`li'
     Limburgish; Limburger; Limburgan.

`ln'
     Lingala.

`lo'
     Lao; Laotian.

`lt'
     Lithuanian.

`lu'
     Luba-Katanga.

`lv'
     Latvian; Lettish.

`mg'
     Malagasy.

`mh'
     Marshall.

`mi'
     Maori.

`mk'
     Macedonian.

`ml'
     Malayalam.

`mn'
     Mongolian.

`mo'
     Moldavian.

`mr'
     Marathi.

`ms'
     Malay.

`mt'
     Maltese.

`my'
     Burmese.

`na'
     Nauru.

`nb'
     Norwegian Bokmaal.

`nd'
     Ndebele, North.

`ne'
     Nepali.

`ng'
     Ndonga.

`nl'
     Dutch.

`nn'
     Norwegian Nynorsk.

`no'
     Norwegian.

`nr'
     Ndebele, South.

`nv'
     Navajo.

`ny'
     Chichewa; Nyanja.

`oc'
     Occitan; Provenc,al.

`oj'
     Ojibwa.

`om'
     (Afan) Oromo.

`or'
     Oriya.

`os'
     Ossetian; Ossetic.

`pa'
     Panjabi; Punjabi.

`pi'
     Pali.

`pl'
     Polish.

`ps'
     Pashto, Pushto.

`pt'
     Portuguese.

`qu'
     Quechua.

`rm'
     Rhaeto-Romance.

`rn'
     Rundi; Kirundi.

`ro'
     Romanian.

`ru'
     Russian.

`rw'
     Kinyarwanda.

`sa'
     Sanskrit.

`sc'
     Sardinian.

`sd'
     Sindhi.

`se'
     Northern Sami.

`sg'
     Sango; Sangro.

`si'
     Sinhalese.

`sk'
     Slovak.

`sl'
     Slovenian.

`sm'
     Samoan.

`sn'
     Shona.

`so'
     Somali.

`sq'
     Albanian.

`sr'
     Serbian.

`ss'
     Swati; Siswati.

`st'
     Sesotho; Sotho, Southern.

`su'
     Sundanese.

`sv'
     Swedish.

`sw'
     Swahili.

`ta'
     Tamil.

`te'
     Telugu.

`tg'
     Tajik.

`th'
     Thai.

`ti'
     Tigrinya.

`tk'
     Turkmen.

`tl'
     Tagalog.

`tn'
     Tswana; Setswana.

`to'
     Tonga (?).

`tr'
     Turkish.

`ts'
     Tsonga.

`tt'
     Tatar.

`tw'
     Twi.

`ty'
     Tahitian.

`ug'
     Uighur.

`uk'
     Ukrainian.

`ur'
     Urdu.

`uz'
     Uzbek.

`ve'
     Venda.

`vi'
     Vietnamese.

`vo'
     Volapu"k; Volapuk.

`wa'
     Walloon.

`wo'
     Wolof.

`xh'
     Xhosa.

`yi'
     Yiddish (formerly ji).

`yo'
     Yoruba.

`za'
     Zhuang.

`zh'
     Chinese.

`zu'
     Zulu.


File: gettext.info,  Node: Country Codes,  Next: Program Index,  Prev: Language Codes,  Up: Top

Appendix B Country Codes
************************

The ISO 3166 standard defines two character codes for many countries
and territories.  All abbreviations for countries used in the
Translation Project should come from this standard.

`AD'
     Andorra.

`AE'
     United Arab Emirates.

`AF'
     Afghanistan.

`AG'
     Antigua and Barbuda.

`AI'
     Anguilla.

`AL'
     Albania.

`AM'
     Armenia.

`AN'
     Netherlands Antilles.

`AO'
     Angola.

`AQ'
     Antarctica.

`AR'
     Argentina.

`AS'
     Samoa (American).

`AT'
     Austria.

`AU'
     Australia.

`AW'
     Aruba.

`AZ'
     Azerbaijan.

`BA'
     Bosnia and Herzegovina.

`BB'
     Barbados.

`BD'
     Bangladesh.

`BE'
     Belgium.

`BF'
     Burkina Faso.

`BG'
     Bulgaria.

`BH'
     Bahrain.

`BI'
     Burundi.

`BJ'
     Benin.

`BM'
     Bermuda.

`BN'
     Brunei.

`BO'
     Bolivia.

`BR'
     Brazil.

`BS'
     Bahamas.

`BT'
     Bhutan.

`BV'
     Bouvet Island.

`BW'
     Botswana.

`BY'
     Belarus.

`BZ'
     Belize.

`CA'
     Canada.

`CC'
     Cocos (Keeling) Islands.

`CD'
     Congo (Dem. Rep.).

`CF'
     Central African Rep..

`CG'
     Congo (Rep.).

`CH'
     Switzerland.

`CI'
     Co^te d'Ivoire.

`CK'
     Cook Islands.

`CL'
     Chile.

`CM'
     Cameroon.

`CN'
     China.

`CO'
     Colombia.

`CR'
     Costa Rica.

`CS'
     Serbia and Montenegro.

`CU'
     Cuba.

`CV'
     Cape Verde.

`CX'
     Christmas Island.

`CY'
     Cyprus.

`CZ'
     Czech Republic.

`DE'
     Germany.

`DJ'
     Djibouti.

`DK'
     Denmark.

`DM'
     Dominica.

`DO'
     Dominican Republic.

`DZ'
     Algeria.

`EC'
     Ecuador.

`EE'
     Estonia.

`EG'
     Egypt.

`EH'
     Western Sahara.

`ER'
     Eritrea.

`ES'
     Spain.

`ET'
     Ethiopia.

`FI'
     Finland.

`FJ'
     Fiji.

`FK'
     Falkland Islands.

`FM'
     Micronesia.

`FO'
     Faeroe Islands.

`FR'
     France.

`GA'
     Gabon.

`GB'
     Britain (UK).

`GD'
     Grenada.

`GE'
     Georgia.

`GF'
     French Guiana.

`GH'
     Ghana.

`GI'
     Gibraltar.

`GL'
     Greenland.

`GM'
     Gambia.

`GN'
     Guinea.

`GP'
     Guadeloupe.

`GQ'
     Equatorial Guinea.

`GR'
     Greece.

`GS'
     South Georgia and the South Sandwich Islands.

`GT'
     Guatemala.

`GU'
     Guam.

`GW'
     Guinea-Bissau.

`GY'
     Guyana.

`HK'
     Hong Kong.

`HM'
     Heard Island and McDonald Islands.

`HN'
     Honduras.

`HR'
     Croatia.

`HT'
     Haiti.

`HU'
     Hungary.

`ID'
     Indonesia.

`IE'
     Ireland.

`IL'
     Israel.

`IN'
     India.

`IO'
     British Indian Ocean Territory.

`IQ'
     Iraq.

`IR'
     Iran.

`IS'
     Iceland.

`IT'
     Italy.

`JM'
     Jamaica.

`JO'
     Jordan.

`JP'
     Japan.

`KE'
     Kenya.

`KG'
     Kyrgyzstan.

`KH'
     Cambodia.

`KI'
     Kiribati.

`KM'
     Comoros.

`KN'
     St Kitts and Nevis.

`KP'
     Korea (North).

`KR'
     Korea (South).

`KW'
     Kuwait.

`KY'
     Cayman Islands.

`KZ'
     Kazakhstan.

`LA'
     Laos.

`LB'
     Lebanon.

`LC'
     St Lucia.

`LI'
     Liechtenstein.

`LK'
     Sri Lanka.

`LR'
     Liberia.

`LS'
     Lesotho.

`LT'
     Lithuania.

`LU'
     Luxembourg.

`LV'
     Latvia.

`LY'
     Libya.

`MA'
     Morocco.

`MC'
     Monaco.

`MD'
     Moldova.

`MG'
     Madagascar.

`MH'
     Marshall Islands.

`MK'
     Macedonia.

`ML'
     Mali.

`MM'
     Myanmar (Burma).

`MN'
     Mongolia.

`MO'
     Macao.

`MP'
     Northern Mariana Islands.

`MQ'
     Martinique.

`MR'
     Mauritania.

`MS'
     Montserrat.

`MT'
     Malta.

`MU'
     Mauritius.

`MV'
     Maldives.

`MW'
     Malawi.

`MX'
     Mexico.

`MY'
     Malaysia.

`MZ'
     Mozambique.

`NA'
     Namibia.

`NC'
     New Caledonia.

`NE'
     Niger.

`NF'
     Norfolk Island.

`NG'
     Nigeria.

`NI'
     Nicaragua.

`NL'
     Netherlands.

`NO'
     Norway.

`NP'
     Nepal.

`NR'
     Nauru.

`NU'
     Niue.

`NZ'
     New Zealand.

`OM'
     Oman.

`PA'
     Panama.

`PE'
     Peru.

`PF'
     French Polynesia.

`PG'
     Papua New Guinea.

`PH'
     Philippines.

`PK'
     Pakistan.

`PL'
     Poland.

`PM'
     St Pierre and Miquelon.

`PN'
     Pitcairn.

`PR'
     Puerto Rico.

`PS'
     Palestine.

`PT'
     Portugal.

`PW'
     Palau.

`PY'
     Paraguay.

`QA'
     Qatar.

`RE'
     Reunion.

`RO'
     Romania.

`RU'
     Russia.

`RW'
     Rwanda.

`SA'
     Saudi Arabia.

`SB'
     Solomon Islands.

`SC'
     Seychelles.

`SD'
     Sudan.

`SE'
     Sweden.

`SG'
     Singapore.

`SH'
     St Helena.

`SI'
     Slovenia.

`SJ'
     Svalbard and Jan Mayen.

`SK'
     Slovakia.

`SL'
     Sierra Leone.

`SM'
     San Marino.

`SN'
     Senegal.

`SO'
     Somalia.

`SR'
     Suriname.

`ST'
     Sao Tome and Principe.

`SV'
     El Salvador.

`SY'
     Syria.

`SZ'
     Swaziland.

`TC'
     Turks and Caicos Islands.

`TD'
     Chad.

`TF'
     French Southern and Antarctic Lands.

`TG'
     Togo.

`TH'
     Thailand.

`TJ'
     Tajikistan.

`TK'
     Tokelau.

`TL'
     Timor-Leste.

`TM'
     Turkmenistan.

`TN'
     Tunisia.

`TO'
     Tonga.

`TR'
     Turkey.

`TT'
     Trinidad and Tobago.

`TV'
     Tuvalu.

`TW'
     Taiwan.

`TZ'
     Tanzania.

`UA'
     Ukraine.

`UG'
     Uganda.

`UM'
     US minor outlying islands.

`US'
     United States.

`UY'
     Uruguay.

`UZ'
     Uzbekistan.

`VA'
     Vatican City.

`VC'
     St Vincent.

`VE'
     Venezuela.

`VG'
     Virgin Islands (UK).

`VI'
     Virgin Islands (US).

`VN'
     Vietnam.

`VU'
     Vanuatu.

`WF'
     Wallis and Futuna.

`WS'
     Samoa (Western).

`YE'
     Yemen.

`YT'
     Mayotte.

`ZA'
     South Africa.

`ZM'
     Zambia.

`ZW'
     Zimbabwe.


File: gettext.info,  Node: Program Index,  Next: Option Index,  Prev: Country Codes,  Up: Top

Program Index
*************