/usr/share/perl5/XML/RSS/SimpleGen.pm is in libxml-rss-simplegen-perl 11.11-5.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 | require 5;
package XML::RSS::SimpleGen;
use strict;
use Carp ();
require Exporter;
use vars qw(
@EXPORT %EXPORT_TAGS @ISA $VERSION
%Entities %WinLameEntities %CommonEnts $MIME_Type
$DTD_url $DTD_pubid $Nativize_newlines $DWIM @Hidies $RSS_obj
$Sleepy %IsBlockMarkup $MaybeIndent $MaybeNL %PeriodAsSeconds
$NAMESPACE_SY $CHUNK_MINUTES %BadPorts
@Retry_delays $UserAgentString
);
$VERSION = '11.11';
BEGIN { *DEBUG = sub () {0} unless defined &DEBUG; } # set DEBUG level
@ISA = qw(Exporter);
#$DTD_url ||= 'http://my.netscape.com/publish/formats/rss-0.91.dtd';
#$DTD_pubid ||= '-//Netscape Communications//DTD RSS 0.91//EN';
$NAMESPACE_SY ||= 'http://purl.org/rss/1.0/modules/syndication/';
$CHUNK_MINUTES = 10;
$Nativize_newlines = 1 unless defined $Nativize_newlines;
$DWIM = 1 unless defined $DWIM;
$Sleepy =
$ENV{'MAILTO'} ? 4 # under crontab
: ($ENV{'TERM'} || $ENV{'REQUEST_METHOD'} || $ENV{'COMSPEC'} ) ? 0
# almost definitely not under crontab
: 4 unless defined $Sleepy;
@Retry_delays = (4, 10, 20, 40);
$MaybeIndent = ' ';
$MaybeNL = "\n";
#$MaybeNL = $MaybeIndent = ''; # terser, more grep-worthy
foreach my $p ( # ports we'll refuse to do HTTP on
qw<0 1 7 9 11 13 15 17 19 20 21 22 23 25 37 42 43 53 70 79 95 101 102 103
104 107 109 110 111 113 115 117 119 123 135 137 138 139 143 389 443 512
513 514 515 517 518 526 530 531 532 540 556 6667
>) { $BadPorts{$p} = 1 unless defined $BadPorts{$p}; }
$UserAgentString ||= "XmlRssSimpleGen/$VERSION";
#..........................................................................
sub _hide {push @Hidies, @_ };
_hide qw(init import);
#..........................................................................
=head1 NAME
XML::RSS::SimpleGen - for writing RSS files
=head1 SYNOPSIS
# A complete screen-scraper and RSS generator here:
use strict;
use XML::RSS::SimpleGen;
my $url = q<http://www.exile.ru/>;
rss_new( $url, "eXile", "Moscow-based Alternative Newspaper" );
rss_language( 'en' );
rss_webmaster( 'xxxxx@yourdomain.com' );
rss_twice_daily();
get_url( $url );
while(
m{<h4>\s*<a href='/(.*?)'.*?>(.*?)</a>\s*</h4>\s*<p.*?>(.*?)<a href='/}sg
) {
rss_item("$url$1", $2, $3);
}
die "No items in this content?! {{\n$_\n}}\nAborting"
unless rss_item_count();
rss_save( 'exile.rss', 45 );
exit;
=head1 DESCRIPTION
This module is for writing RSS files, simply. It transparently handles
all the unpleasant details of RSS, like proper XML escaping, and also has
a good number of Do-What-I-Mean features, like not changing the modtime
on a written-out RSS file if the file content hasn't changed, and like
automatically removing any HTML tags from content you might pass in.
This module isn't meant to have the full expressive power of RSS;
instead, it provides functions that are most commonly needed by
RSS-writing programs.
=head1 INTERFACE
This module provides a bunch of functions for starting an RSS feed in
memory, putting items into it, and saving it to disk (or printing it as
a string, as in a CGI). If you prefer an object-oriented interface
(obviously more useful if you're composing several feeds at once), then
you can use this module as a class whose methods are the same as the
function names minus "rss_". Except for this detail of the naming, the
functions and methods are the same, behave the same, and take the same
arguments.
That is, this functional code:
use XML::RSS::SimpleGen;
my $url = q<http://www.exile.ru/>;
rss_new( $url, "eXile" );
rss_language( 'en' );
get_url( $url );
...
does the same work as this OO code:
use XML::RSS::SimpleGen ();
my $url = q<http://www.exile.ru/>;
my $rss = XML::RSS::SimpleGen->new( $url, "eXile");
$rss->language( 'en' );
$rss->get_url( $url );
...
(Note that the function C<get_url> doesn't have a leading "rss_",
so its method name is the same as its function name. It's the
one exception.)
If this talk of objects puzzles you, see
L<HTML::Tree::AboutObjects> in the C<HTML-Tree> dist, and/or see
the chapter "User's View of Object-Oriented Modules"
in my book I<Perl & LWP> (L<http://www.amazon.com/exec/obidos/ASIN/0596001789>).
(The book is also useful as an extended discussion of screen-scraping.)
Note: in the code below, I use the word "accessor" a lot, to refer
to a function or method that you can call two possible ways:
1) like C<foo(I<val>)> to set the "foo" attribute to the value I<val>,
or 2) like C<foo()> to return the value of the "foo" attribute.
=head1 FUNCTIONS
=over
=item C<rss_new( I<url> );>
=item C<rss_new( I<url, title> );>
=item C<rss_new( I<url, title, description> );>
=item I<or:> C<< $rss = XML::RSS::SimpleGen->new(...); >>
This function creates a new RSS feed in memory. This should be the first
C<rss_I<whatever>> function you call in your program. If you call it
again, it erases the current object (if any) and sets up a new one according
to whatever parameters you pass.
The parameters are the full URL, the title, and the description of the
site (or page) that you're providing an RSS feed of. The description is
optional, but you should provide at least a URL and title.
Examples:
rss_new( $url, "eXile", "Moscow-based Alternative Newspaper" );
rss_new( 'http://www.mybazouki.com/news/', "Bazouki News!" );
(As a method, XML::RSS::SimpleGen->new simply returns a new
RSS object.)
=cut
sub new {
my $class = shift;
$class = ref($class) || $class;
my $new = bless { 'items' => [] }, $class;
$new->init();
@_ and $new->url(shift);
@_ and $new->title(shift);
@_ and $new->description(shift);
$new->item_limit( 0 );
$new->retention( 32 * 24 * 60 * 60 ); # 32 days
(-e "rss.css") ? $new->css("./rss.css")
: $new->css("http://www.interglacial.com/rss/rss.css");
(-e "about_rss.html") ? $new->docs("./about_rss.html")
: $new->docs("http://www.interglacial.com/rss/about.html");
return $new;
}
sub init { return; } # override in subclass as necessary
#..........................................................................
__PACKAGE__->_accessorize(
qw(
title description url language css xsl webMaster docs
item_limit ttl
retention
allow_duplicates
image_title image_link image_url image_width image_height image_description
)
);
=item the accessor C<rss_language(I<language_tag>)>
This declares what language this RSS feed is in. It must be
an RFC3066-style language tags like "en", or "en-US", or "zh-TW".
(See I<I18N::LangTags::List> for a list.)
If you don't set the feed's language, it defaults to "en", for generic English.
If you call this function without a parameter, it returns
the current value of the RSS feed's language. For example:
print "I'm making an RSS feed for ", rss_language(), "!\n";
The same is true for all the functions that I label as "accessors".
=item the accessor C<rss_item_limit(I<number>)>
This sets the maximum number of items that this feed will show.
The default value is 0, meaning that there is no maximum.
If you set it to a positive number I<N>, then the feed will show only
the first I<N> items that you declare with C<rss_item>. (Or, if you set
C<rss_history_file>, then the newest I<N> items that you declare
with C<rss_item>.)
If you set it to a negative number I<-N>, then the feed will show only
the last I<N> items that you declare with C<rss_item>. (Or, if you set
C<rss_history_file>, then the oldest I<N> items you declare with C<rss_item>,
which is unlikely to be useful!)
=item the accessor C<rss_webMaster(I<email-address>)>
This declares what email address you, the RSS generator manager, can be
reached at. Example:
rss_webMaster( 'sburke@bazouki-news.int' );
=cut
#..........................................................................
=item C<rss_history_file( I<filename> )>
This declares that you want this RSS feed to keep track of what items are
new, and to list them first when the RSS is emitted. To do this, the RSS
generator has to store information in a file, where it tracks its "history",
i.e., when was the first time it saw given URLs, and the most recent time
it saw given URLs.
Typical usage is:
rss_history_file( 'thisrssfeed.dat' );
You should call C<rss_history_file> I<before> you make any calls to
C<rss_item>.
The history-file feature is meant for cases where your RSS-generator
program calls C<rss_item> on I<every> link it sees, but only wants the
I<new> links to appear in the RSS output. (This can be a good approach
if you're making an RSS feed of a page like
C<http://www.guardian.co.uk/> where there's some new links (to the
recently added stories), but also links to some days-old stories, and
I<also> links to some always-there things like "Archive Search" and
"Contact Us" pages.
Once you call rss_history_file, the specified file is read in. The
in-memory history (stored in the RSS object) is updated as you
call C<rss_item>. But the file isn't updated until you call rss_save.
(A do-what-I-mean side effect of calling C<rss_history_file> is that it
sets rss_item_limit to 25 if it is currently 0.)
(Incidentally, if you're using rss_history_file as part of a CGI that
emits RSS data, instead of a program that just saves to an RSS file,
then things will get complicated. You'll need to call an internal method
to explicitly commit the history file to disk, and you'll need a
semaphore file to avoid race conditions. Email me for full info.)
=cut
sub history_file {
my $self = shift;
return $self->{'history_file'} unless @_; # read accession
my $file = $_[0];
unless(defined $file and length $file and $file =~ m/\S/) {
DEBUG and print "Killing $self 's memory-history.\n";
# I don't know if this'd be actually useful for anything tho.
delete $self->{'history_file'};
delete $self->{'_first_seen' };
delete $self->{'_last_seen' };
return undef;
}
DEBUG and print "Considering $file as $self 's history.\n";
$self->{'history_file'} = $file;
$self->_read_history_file;
$self->item_limit( 25 ) if $DWIM and !$self->item_limit();
return $file;
}
#..........................................................................
=item C<rss_item( I<url> );>
=item C<rss_item( I<url, title> );>
=item C<rss_item( I<url, title, description> );>
This adds a new item to the current feed. You will need to specify the
URL to add (and it should be a valid-looking URL, starting with
"I<something:>", and not containing any spaces). You may also specify
the title, but it's optional. And finally, you can optionally specify a
description. (You can remember this because it starts with the essential
item first, and progresses toward the most optional.)
Leading and tailing whitespace is removed from whichever of I<url,
title,> and I<description> are defined values, and HTML is parsed out.
A simple usage:
rss_item(
"http://www.harpers.org/MostRecentWR.html",
"Harper's Magazine's Weekly Review"
);
Although in practice, a typical call won't have string constants, but
will instead be like the example in the L<Synopsis sectios|/"SYNOPSIS">,
namely:
rss_item("$url$1", $2, $3);
Incidentally, as a do-what-I-mean feature, if the first parameter
doesn't look like a URL but one of the others does, then this error is
silently forgiven. This is so you can occasionally slip up and forget
the order of the parameters.
(In the unlikely event where you I<need> to avoid the HTML-removal
features, you can do this by passing scalar-references instead of
normal strings, like so: C<rss_item($url, $title, \$not_to_be_escaped)>.)
=cut
sub item { # Add an item: (url, title, description)
my($self, @params) = @_;
if( grep defined($_) && length($_), @params ) {
push @{$self->{'items'}},
[
$self->_process_item_params(@params) # DWIM things happen here
]
;
DEBUG and print "Adding item ",
join("|", @{ $self->{'items'}[-1] }), "\n";
# Update history...
if( $self->{'_first_seen'} ) {
my $url = $self->{'items'}[-1][0];
my $now =
$self->{'_virgin_item_timestamp'}
? --$self->{'_virgin_item_timestamp'}
: time()
;
$self->{'_first_seen'}{$url} ||= $now;
$self->{'_last_seen' }{$url} = $now;
}
} else {
DEBUG and print "Not adding item -- empty params\n";
}
return $self;
}
#..........................................................................
=item C<rss_item_count()>
This returns the number of items you've declared. I anticipate that its
main usage will be something like:
die "What, no objects found at $url ?!"
unless rss_item_count();
or, maybe...
exit unless rss_item_count();
...depending on how/whether you'd want to react to cases where you don't
see anything to put into an RSS feed.
Note that the parens are optional, since this command takes no options
(just like Perl's C<time()> function).
=cut
sub item_count { scalar @{ $_[0]->{'items'} }; }
sub items_count { shift->item_count } # harmless alias
#..........................................................................
sub _sort_items_newest_first {
my $self = shift;
my $seen = $self->{'_first_seen'};
$seen or Carp::confess(
"Can't sort items by age unless you define a history file!");
my $items = $self->{'items'} || die "NO ITEMS!?";
if( DEBUG ) {
print "\nSorting ", scalar(@$items), " items, newest first. Age dump:\n";
foreach my $i (@$items) {
if( $i->[0] ) {
printf " %s : %s (%s)\n",
$i->[0], $seen->{$i->[0]} || 0, scalar localtime(
$seen->{$i->[0]} || 0)
;
} else {
print " NOURL\n";
}
}
print " (no items)\n" unless @$items;
print "(End history dump.)\n\n";
}
@$items =
sort { ($seen->{$b->[0] ||''} ||0)
<=> ($seen->{$a->[0] ||''} ||0)
or $a->[0] cmp $b->[0] # So it's at least predictable
}
@$items;
return;
}
#..........................................................................
=item C<rss_image( I<url, h, w> );>
This declares that you want to declare a particular image as the logo for
this feed. Most feeds don't have such a thing, and most readers just ignore
it anyway, but if you want to declare it, this function is how. The
three parameters, which are all required, are: the image's URL, its
height in pixels, and its width in pixels.
According to various specs, the width should/must be between 1 and 144,
an the height should/must be between 1 and 400.
A typical usage:
rss_image("http://interglacial.com/rss/weebl.gif", 106, 140);
Be careful not to mix up the height and width.
=cut
sub image {
my($self, $url, $h, $w) = splice(@_,0,4);
Carp::croak "Usage: \$rss->image(\$url, \$h, \$w)"
unless $url and $h and $w
and $h =~ m/^\d{1,3}$/s
and $w =~ m/^\d{1,3}$/s
;
$self->image_url($url);
$self->image_height($h);
$self->image_width( $w);
# width must (should?) be between 1 and 144
# height must (should?) be between 1 and 400
@_ and $self->image_link( shift);
@_ and $self->image_title( shift);
@_ and $self->image_description( shift);
return;
}
#..........................................................................
=item C<rss_save( I<filename> );>
=item C<rss_save( I<filename, max_age_days> );>
This saves the RSS date to the file you specify. If the RSS data hasn't
changed, the file (and its modtime) aren't altered. The optional I<max_age_days>
parameter means that if ever the file exists, and its content hasn't changed
for that many days or longer, then the program should die with a warning
message. For example, in the case of a screen-scraper for a site that we
know should (in theory) change its content at least weekly, we might save
the RSS file with:
rss_save("whatever.rss", 17);
# Scream if the feed is unchanged for 17 days.
The seventeen there is gotten by assuming that just maybe the site
might skip two weeks for a vacation now and then, and might even put
out the pre-vacation issue a few days early -- but that if ever the program
notices that the data hasn't changed for 17 days, then it should emit
error messages. If you want to disable this feature on a one-time basis,
just change the modtime (like via C<touch>) on the F<whatever.rss> file.
If you don't specify a C<max_age_days> value, then this whole
complain-if-it's-old feature is disabled.
=cut
sub save {
my($self, $filename, $maxage) = @_;
Carp::croak("I need a filename to save to")
unless defined $filename and length $filename;
$self->history_file and $self->_sort_items_newest_first;
$self->_write_history_file;
my $new_content = $self->as_string;
local *RSS;
# See if we can skip writing to disk
if(-e $filename and -f _ and -r _ and -s _) {
DEBUG and print "Comparing to $filename...\n";
open RSS, $filename
or Carp::confess "Can't read-open $filename: $!"; # insanity
local $/;
my $content = <RSS>;
close(RSS);
if( $content eq $new_content ) {
DEBUG and print " $filename\'s content is the same.\n";
return $self->_check_age($filename, $maxage);
}
my $new_content_without_builddate = $new_content;
foreach my $c ($new_content_without_builddate, $content) {
$c =~ s{<last[Bb]uild[Dd]ate>.*?</last[Bb]uild[Dd]ate>}{};
$c =~ s{<pub[Dd]ate>.*?</pub[Dd]ate>}{};
$c =~ tr{\n\r}{}s; # And smash newlines while we're at it...
}
if( $content eq $new_content_without_builddate ) {
DEBUG and print " $filename\'s content is the same, basically.\n";
return $self->_check_age($filename, $maxage);
}
DEBUG and print " $filename\'s content is stale. Overwriting.\n";
}
DEBUG and print "Writing to $filename ...\n";
# OK, we have to actually write it. Let's do it fast.
open(RSS, ">$filename")
or Carp::confess "Can't write-open $filename: $!\nAborting";
print RSS $new_content
or Carp::confess "Can't print to $filename: $!\nAborting";
close(RSS)
or Carp::confess "Can't close $filename: $!\nAborting";
eval { chmod 0644, $filename };
DEBUG and print "Done writing to $filename\n";
return 1;
}
#..........................................................................
=item C<rss_as_string();>
This returns the RSS-XML data as a string. This function is called
internally by the rss_save function; but you might want to call it
explicitly, as in a CGI, where your CGI would probably end like this:
print "Content-type: application/xml\n\n", rss_as_string();
exit;
=cut
sub as_string {
my $self = $_[0];
my $namespaces = $self->_namespaces_as_string;
return join '' =>
qq{<?xml version="1.0"?>\n},
($DTD_pubid and $DTD_url)
? qq{<!DOCTYPE rss PUBLIC "$DTD_pubid"\n "$DTD_url">\n} : (),
$self->css ? ( # http://www.w3.org/TR/xml-stylesheet/
qq{<?xml-stylesheet title="CSS_formatting" type="text/css" href="},
$self->xmlesc($self->css),
qq{"?>\n}
) : (),
$self->xsl ? (
qq{<?xml-stylesheet title="XSL_formatting" type="text/xml" href="}, # TODO: better mime type?
$self->xmlesc($self->xsl),
qq{"?>\n}
) : (),
qq{<rss version="2.0"$namespaces><channel>},
$self->_modversion_comment,
$self->_various_comments,
$self->_metadata_as_xml,
$self->_items_as_xml,
"\n</channel></rss>\n",
;
}
sub _namespaces_as_string {
my $self = $_[0];
my $ns = $self->{'_namespaces'};
return '' unless $ns and keys %$ns;
return
join '', "\n",
map qq{ xmlns:$_="$$ns{$_}"\n},
sort keys %$ns
;
}
#..........................................................................
sub _metadata_as_xml {
my $self = $_[0];
my($url, $title, $description) = (
map defined($_) ? $_ : '',
$self->url, $self->title, $self->description,
);
if($DWIM) {
# tolerate switching the description/title and the URL
if($url !~ m{^[a-z]+[a-z0-9]*:\S+$}s) {
DEBUG and print "URL \"$url\" looks fishy...\n";
if( $title =~ m{^[a-z]+[a-z0-9]*:\S+$}s) {
DEBUG and print "Swapping with title \"$title\"\n";
($url, $title) = ($title, $url);
$self->url($url);
$self->title($title);
} elsif( $description =~ m{^[a-z]+[a-z0-9]*:\S+$}s) {
DEBUG and print "Swapping with description \"$description\"\n";
($url, $description) = ($description, $url);
$self->url($url);
$self->description($description);
} else {
Carp::croak( "Invalid URL \"$url\" in metadata "
. ($title||$description||"???") . "\nAborting"
);
}
}
}
my $lang = $self->language;
$lang and $lang =~ tr[_][\-]; # tolerate underscores
$lang = 'en' unless defined $lang
# From I18N::LangTags...
and $lang !~ m/^[iIxI]$/s
and $lang =~
m/^(?: # First subtag
[xiIX] | [a-zA-Z]{2,3}
)
(?: # Subtags thereafter
- # separator
[A-Za-z0-9]{1,8} # subtag
)*
$/xs
;
return join '', sprintf( qq{
<link>%s</link>
<title>%s</title>
<description>%s</description>
<language>%s</language>
<lastBuildDate>%s</lastBuildDate>
},
map( $self->html2text($_),
$url || '!!!!DummyURL!!!!',
$title || $description || $url || '!!!!DummyTitle!!!!',
$description || $title || $url || '!!!!DummyDescription!!!!',
),
$lang,
$self->_date_rfc822(),
),
grep $_,
$self->{"skipHours"},
$self->{"skipDays"},
$self->_sy_update_as_xml,
(($self->{"ttl"} || '') =~ m/^(\d+)$/s) && "<ttl>$1</ttl>\n",
$self->webMaster &&
("<webMaster>" . $self->html2text($self->webMaster) . "</webMaster>\n"),
$self->docs &&
("<docs>" . $self->html2text($self->docs) . "</docs>\n"),
$self->_image_as_xml,
$self->{'more_metadata'}, # a hack for sneaking in more things
;
# ...with sanity-checkers
}
#..........................................................................
sub _process_item_params {
my $self = shift;
my($url, $title, $description) =
map {; (defined($_) && m/\S/) ? $_ : '' } # contentfulness filter
map $self->html2text($_), # here's where we de-htmlify things
@_;
;
for($url, $title, $description) {
if(ref $_ ) { } # Okay
elsif(defined $_) { s/^\s+//s; s/\s+$//s }
else { $_ = '' }
}
# Tolerate switching the description/title and the URL
if($DWIM and $url !~ m{^[a-z]+[a-z0-9]*:\S+$}s) {
DEBUG and print "URL \"$url\" looks fishy...\n";
if( $title =~ m{^[a-z]+[a-z0-9]*:\S+$}s) {
DEBUG and print "Swapping with title \"$title\"\n";
($url, $title) = ($title, $url);
} elsif( $description =~ m{^[a-z]+[a-z0-9]*:\S+$}s) {
DEBUG and print "Swapping with description \"$description\"\n";
($url, $description) = ($title, $description);
} else {
Carp::confess( "Invalid URL \"$url\" in item "
. ($title||$description||"???") . "\nAborting"
);
}
}
return ($url, $title, $description);
}
#..........................................................................
sub _items_as_xml {
my $self = $_[0];
my @items;
my @xml_out = ($MaybeNL);
if( $self->allow_duplicates ) {
@items = @{ $self->{'items'} || die "NO ITEMS!?!?" };
} else {
my %seen;
foreach my $i (@{ $self->{'items'} || die "NO ITEMS!?!?" }) {
if( $seen{ $i->[0] } ++ ) {
DEBUG and print "Removing duplicate item @$i\n";
} else {
push @items, $i;
}
}
}
my $item_limit = int( $self->item_limit || 0 );
if($item_limit) {
if(@items > abs($item_limit)) {
if($item_limit > 0) { # like 4 to mean just the first 4
DEBUG and print " Killing all but the first $item_limit items.\n";
splice @items, $item_limit;
} else { # like -4 to mean just the last 4
DEBUG and print " Killing all but the last ", 0-$item_limit, " items.\n";
splice @items, 0, @items + $item_limit;
# So if item_limit is -3 and @items has 10 elements,
# then that number will be 7, i.e., to chop the first 7
# elements, leaving the last 3.
}
}
}
DEBUG and print scalar(@items), " items at hand:\n";
foreach my $i (@items) {
my($url, $title, $description) = @$i;
DEBUG > 1 and print "I: (u $url) (t $title) (d $description)\n";
next unless $url or $title or $description;
push @xml_out,
"<item>$MaybeNL",
(map "$MaybeIndent$_$MaybeNL",
length($title) ? "<title>$title</title>" : (),
length($url) ? "<link>$url</link>" : (),
length($description) ? "<description>$description</description>" : (),
),
"</item>$MaybeNL\n",
}
DEBUG and print "_items_as_xml returning {\n", join('', @xml_out), "}\n\n";
return join '', @xml_out;
}
#..........................................................................
sub _image_as_xml {
my $self = shift;
return '' unless
$self->image_url and $self->image_height and $self->image_width;
# <!ELEMENT image (title | url | link | width? | height? | description?)*>
return join '',
"<image>\n",
map(" $_\n" =>
$self->xmlelem( 'title' => $self->image_title || $self->html2text($self->title)),
$self->xmlelem( 'url' => $self->image_url), # url of the image
$self->xmlelem( 'link' => $self->image_link || $self->html2text($self->url )),
$self->xmlelem( 'width' => $self->image_width),
$self->xmlelem( 'height' => $self->image_height),
$self->xmlelem( 'description'
=> $self->image_description
|| $self->html2text($self->description)),
),
"</image>\n",
;
}
#==========================================================================
=item C<get_url( I<url> );>
=item C<$content = get_url( I<url> );>
=item I<or:> C<< $content = $rss->get_url(...); >>
=item I<or:> C<< $content->get_url(...); >>
This tries to get the content of the given url, and returns it.
This is quite like L<LWP::Simple>'s C<get> function, but with some
additional features:
=over
=item * If it can't
get the URL's content at first, it will sleep for a few seconds and try
again, up to about five times. (This is to avoid the case of the URL
being temporarily inaccessible simply because the DNS is a bit slow,
or because the server is too busy.)
=item * If it can't get the content, even after several retries,
it will abort the program (like a C<die>). If you want to override this
behavior, then call it as C<eval { get_url($url) };>
=item * If you call the function in void context (i.e., not using its
return value), then the function assigns the URL's content to C<$_>.
That's so you can write nice concise code like this:
get_url $thatsite;
m/Top Stories Tonight/ or die "What, no top stories?";
while( m{<a class="top" href="(.*?)">(.*?)</a>}g ) {
rss_item("$thatsite/$1", $2);
}
=item * This returns the content of the URL not exactly as-is, but after
changing its newlines to native format. That is, if the contents of the
URL use CR-LF pairs to express newlines, then C<get_url> changes these
to C<\n>'s before returning the content. (Similarly for old MacOS
newline format.) Clearly this is wrong in you're dealing with binary
data; in that case, use LWP::Simple's C<get> directly.
=item * Finally, as a resource-conversation measure, this function
will also try to call C<sleep> a few times if it sees several quick
calls to itself coming from a program that seems to be running
under crontab. As most of my RSS-generators are crontabbed, I
find it very useful that I can have however many C<get_url>'s in
my crontabbed programs without worrying that they'll take even a
noticeable part of the server's bandwidth.
=back
=cut
my $last_url_get_time;
sub get_url ($) {
my $self = shift if @_ > 1; # work as a function or method
# Go whip up an object unless one was given:
$self = ($RSS_obj ||= XML::RSS::SimpleGen::->new) unless defined $self;
$self = $self->new unless ref $self;
my $url = $_[0];
Carp::croak "\"$url\" doesn't look like a URL!\nAborting"
unless defined($url) and $url =~ m{^[a-z]+[a-z0-9]*:\S+$}s;
if($Sleepy and $last_url_get_time) {
my $delay = $Sleepy - (time() - $last_url_get_time);
if( $delay > 0 ) {
DEBUG and print "Last URLget was at $last_url_get_time, sleep $delay\n";
sleep $delay;
} else {
DEBUG and print "Last URLget was at $last_url_get_time, so no sleep.\n";
}
}
my $content;
my $count = 0;
foreach my $delay (@Retry_delays, 0) {
delete $self->{'_loops'};
delete $self->{'_http_abort'};
DEBUG and print "Getting $url ...\n";
++$count;
if( defined(
$content = $self->_get($url)
)) {
DEBUG and print "OK, got it (", length($content), " bytes)\n";
last;
}
if( $self->{'_http_abort'} ) {
DEBUG and print "Couldn't get it and won't retry (",
$self->{'_http_abort'}, ")\n";
last;
} else {
DEBUG and print "Odd, couldn't get it.\n";
}
if($delay) { DEBUG and print "Sleeping $delay sec...\n"; sleep $delay; }
}
$last_url_get_time = time();
unless( defined $content ) {
my $headers = $self->{'_http_headers'};
if( $headers and $headers =~ s{^}{ }mg ) {
$headers = "\nResponse headers:\n$headers";
} else {
$headers = '';
}
$count .= ($count == 1) ? " try" : " tries";
Carp::croak("Couldn't get $url in $count$headers\nSo, aborting")
}
if($Nativize_newlines) {
if("\n" eq "\cj") { # CR => LF CR LFLF... => LF LF => LF
$content =~ s/\cm\cj*/\n/g; # most efficient, I dare say
} elsif("\n" eq "\cm") { # CR => CR CR LFLF... => CR LF => CR
$content =~ s/(?:(?:\cm\cj+)|\cj)/\n/g;
} else {
$content =~ s/(?:\n|\r|\n\r)/\n/g;
}
}
$_ = $content unless defined wantarray;
return $content;
}
#==========================================================================
# Things below here are less and less interesting to the casual reader.
#==========================================================================
sub _get {
my $self = shift;
if(
!$LWP::Simple::VERSION
and $_[0] =~ m{^http://([^ \n\r\t/:\@]+)(?::(\d+))?(/\S*)?$}
) {
my $host = $1;
my $path = $3;
my $port = 0 + ($2 || 80);
if( $BadPorts{$port} ) {
DEBUG and print "We don't like port $port from $_[0]\n";
return undef;
}
$path = "/" unless defined($path);
$self = $self->new unless ref($self); # need to be an object method
return $self->_trivial_http_get($host, $port, $path);
} else {
return $self->_lwp_get(@_);
}
}
sub _lwp_get {
require LWP::Simple;
DEBUG and print "Calling LWP::Simple on $_[1]\n";
return LWP::Simple::get($_[1]);
}
sub _trivial_http_get {
my($self, $host, $port, $path) = @_;
DEBUG > 1 and print "Getting HOST=$host, PORT=$port, PATH=$path\n";
$self = $self->new unless ref($self); # need to be an object method
my $seen = ( $self->{'_loops'} ||= {} );
require IO::Socket;
local($^W) = 0;
my $sock = IO::Socket::INET->new(PeerAddr => $host,
PeerPort => $port,
Proto => 'tcp',
Timeout => 60) || return undef;
$sock->autoflush;
my $netloc = $host;
$netloc .= ":$port" if $port != 80;
print $sock join("\015\012" =>
"GET $path HTTP/1.0",
"Host: $netloc",
"User-Agent: $UserAgentString",
"", "");
my $buf = "";
my $n;
while( $n = sysread($sock, $buf, 8*1024, length($buf)) ) {
DEBUG > 10 and print " Got $n bytes...\n";
1;
}
return undef unless defined($n);
if( $buf =~ m{^HTTP/\d+\.\d+\s+(\d+)[^\012]*\012} ) {
my $code = $1;
DEBUG and print " Got HTTP status: $code\n";
if( $code =~ m/^30[1237]/s and $buf =~ m/\012Location:\s*(\S+)/ ) {
# Redirection
my $url = $1;
if( $url =~ m/^(file|mailto):/ # protocols we hate
or $seen->{$url}++
or scalar(keys %$seen) > 20
) {
DEBUG and print "I don't like the redirection response $url\n";
$self->{'_http_abort'} = "Bad HTTP-redirection loop.";
return undef;
}
return $self->_get($url); # Recurse!
}
$buf =~ s/(.+?)\015?\012\015?\012//s; # zap the header
( $self->{'_http_headers'} = $1 ) =~ tr/\015\012/\n/sd;
DEBUG > 10 and print "Headers: $$self{'_http_headers'}\n";
$self->{'_http_abort'} = "HTTP status $code"
if $code eq '404' or $code eq '403';
return undef unless $code =~ m/^2/;
DEBUG and print "Returning ", length($buf), " bytes of content.\n";
} else {
DEBUG and print "Got a headerless response. Returning.\n";
}
return $buf;
}
#==========================================================================
sub _read_history_file {
my $self = $_[0];
my $hf = $self->history_file;
unless(defined $hf and length $hf) {
DEBUG and print "No history_file defined for $self.\n";
return;
}
my(%first, %last); # "last" in the sense of "most recently"
$self->{'_first_seen'} = \%first;
$self->{'_last_seen' } = \%last ;
unless( -e $hf and -s _ ) {
$self->{'_virgin_item_timestamp'} = time() if $DWIM;
return 0;
}
my $now = time();
my $forget_before;
my $in;
{
local *IN;
open(IN, $hf) or Carp::confess "Can't read-open $hf: $!"; # insane
$in = *IN{IO};
}
local $_;
my @f;
while(<$in>) {
tr/\n\r//d;
next unless @f = split "\t", $_, 3 and defined($f[0]) and length($f[0]);
$last{$f[0]} = $f[2] if $f[2];
if( $f[1] ) {
$first{$f[0]} = $f[1];
DEBUG > 3 and print " Learning $f[0] first seen at $f[1]\n";
} else {
$first{$f[0]} = $now;
DEBUG > 3 and print " Prelearning $f[0] first seen at $f[1]\n";
# TODO: is this useful?
}
}
close($in);
return 1;
}
# . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
sub _write_history_file {
my $self = $_[0];
my $hf = $self->history_file;
unless(defined $hf and length $hf) {
DEBUG and print "No history_file defined for $self.\n";
return;
}
my $first = $self->{'_first_seen'};
my $last = $self->{'_last_seen' };
my $now = time();
my $out;
DEBUG and print "Saving to history file $hf\n";
DEBUG > 2 and printf "Time now: %s = %s\n", time(), scalar(localtime);
{
local *HF;
open(HF, ">$hf") or Carp::confess "Can't write-open $hf: $!"; # insane
$out = *HF{IO};
}
{
my(@f, @x);
{
my %x;
@x{keys %$first, keys %$last} = ();
@x = sort keys %x;
}
my $forget_before;
{
my $r = $self->retention;
if( $r and $r > 0 ) { $forget_before = time() - $r }
}
foreach my $key (@x) {
next if $key =~ m/[\t\n\r]/;
if( $forget_before and $last->{$key} < $forget_before ) {
DEBUG and printf(
" Forgetting %s as being too old since last-seen (%s = %s)\n",
$key,
$last->{$key},
scalar(localtime($last->{$key})),
);
next;
}
print $out $key, "\t",
$first->{$key}||'', "\t",
$last->{$key}||'', "\n",
;
if(DEBUG > 2) {
printf " Key %s\n First seen: %s = %s\n Last seen: %s = %s\n",
$key,
$first->{$key}||'-',
scalar(localtime( $first->{$key}||0 )),
$last->{$key}||'-',
scalar(localtime( $last->{$key}||0 )),
}
}
close($out);
}
DEBUG and print "Done saving to $hf\n";
return 1;
}
#-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_
=item C<rss_hourly> I<or> C<rss_daily> I<or> C<rss_twice_daily>
I<or> C<rss_thrice_daily> I<or> C<rss_weekly> I<or> C<rss_every_other_hour>
Calling one of these functions declares that this feed is usually
generated at the same time(s) every day (or every week, in the case of
C<rss_weekly>). And, where it's not just once a day/week, these multiple
times a day are evenly spaced. These functions then set the feed's
C<updatePeriod>, C<updateBase>, C<updateFrequency>, C<skipHours>,
C<skipDays>, and C<ttl> elements appropriately, so that RSS readers can know at
at what times there could (or couldn't) be new content in this feed.
In other words: use C<rss_twice_daily> if this feed is updated at about the
same time every day and then again 12 hours later. Use C<rss_thrice_daily>
if this feed is updated at the same time daily, and then 8 hours later, and
then 8 hours later. And use C<rss_every_other_hour> if the feed updates
at about I<n> minutes past every even numbered hour, or every odd-numbered
hour.
Clearly I mean these functions to be used in programs that are crontabbed
to run at particular intervals, as with a crontab line like one of these:
52 * * * * ~/thingy # => rss_hourly
52 23 * * * ~/thingy # => rss_daily
52 4,16 * * * ~/thingy # => rss_twice_daily
52 5,13,21 * * * ~/thingy # => rss_thrice_daily
52 23 * * 3 ~/thingy # => rss_weekly
52 */2 * * * ~/thingy # => rss_every_other_hour
Clearly there aren't C<rss_I<interval>> functions for all the scheduling
possibilities programs -- if you have a program that has to run at
6am, 8am, 1pm, and 4pm, there's no function for that. However, the above
crontab lines (or with minor changes, like C<1,9,17> instead of C<5,13,21>)
are just fine for almost every RSS feed I've run.
An aside: I recommend running the programs at about 52 minutes past the hour,
generally in series, like so:
52 5,13,21 * * * ~/thingy ; ~/dodad ; ~/makething ; ~/gizmo
However, your mileage may vary.
Incidentally, these functions take no arguments, so the parentheses are
optional. That is, these two lines do the same thing:
rss_hourly;
rss_hourly();
=cut
## Some handy if somewhat arbitrary shortcuts:
#
sub hourly {
my $self = $_[0];
$self->updatePeriod('hourly');
$self->ttl('60');
return;
}
sub daily {
my $self = $_[0];
$self->updateHours();
$self->updatePeriod('daily');
$self->ttl( 24 * 60 );
return;
}
sub twice_daily {
my $self = $_[0];
my $h = (gmtime( $self->_now_rounded_up ))[2];
$self->updateHours( $h, ($h+12) % 24 );
$self->updatePeriod('daily',2);
$self->ttl( 12 * 60 );
return;
}
sub thrice_daily {
my $self = $_[0];
my $h = (gmtime( $self->_now_rounded_up ))[2];
$self->updateHours( $h, ($h+ 8) % 24, ($h+16) % 24 );
$self->updatePeriod('daily',3);
$self->ttl( 8 * 60 );
return;
}
sub weekly {
my $self = $_[0];
$self->updateHours();
$self->updateDays();
$self->updatePeriod('weekly',1);
$self->ttl( 7 * 24 * 60 );
return;
}
{
my(@odds, @evens);
for(0 .. 23) { push @{ ($_ & 1) ? \@odds : \@evens }, $_ }
sub every_other_hour {
my $self = $_[0];
my $h = (gmtime( $self->_now_rounded_up ))[2];
$self->skipHours( ($h & 1) ? @evens : @odds);
$self->updatePeriod('daily',12);
$self->ttl( '120' );
return;
}
}
#..........................................................................
my @day_names = (
"Sunday", "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday",
);
my %is_day_name;
@is_day_name{@day_names} = @day_names;
#..........................................................................
sub _now_rounded_up {
my $self = $_[0];
my $now = $_[0]{'_force_now'} # to be used only for testing purposes
|| time();
if( $CHUNK_MINUTES ) {
my $tweak = ($CHUNK_MINUTES * 60) - ($now % ($CHUNK_MINUTES * 60));
DEBUG and print "Tweaking $now (", scalar(gmtime($now)),
" GMT) by $tweak seconds\n so it'll be an even $CHUNK_MINUTES minutes: ";
$now += $tweak;
DEBUG and print "$now (", scalar(gmtime($now)), " GMT)\n";
} else {
# probably not a good idea
DEBUG and print "Archoring timebase to right this moment.\n";
}
return $now;
}
sub _now { return $_[0]{'_force_now'} || time() }
#..........................................................................
=back
=head2 MINOR FUNCTIONS
These are functions that you probably won't need often, or at all. I include
these for the sake of completeness, and so that advanced users might find them
useful in some cases.
=over
=item C<rss_skipHours( I<gmt_hour_num, gmt_hour_num, ...> );>
This function directly sets the C<skipHours> element's values to the
specified GMT hour numbers.
=cut
sub skipHours {
my($self, @in) = @_;
my @skiphours;
foreach my $hour (@in) {
next unless defined $hour;
Carp::croak "\"$hour\" isn't a valid hour number (must be 0-23)"
unless $hour <= 24 and $hour >= 0;
push @skiphours, ($hour == 24) ? 0 : (0 + $hour);
# tolerate "24" to mean 0h.
}
DEBUG and print "Skipdays: @skiphours\n";
$self->{'skipHours'} = join '',
"<skipHours>", map( "<hour>$_</hour>", @skiphours), "</skipHours>\n"
;
return;
}
#--------------------------------------------------------------------------
=item C<rss_updateHours();>
=item C<rss_updateHours( I<gmt_hour_num, gmt_hour_num, ...> );>
This function is a wrapper around C<rss_skipHours> -- you call
C<rss_updateHours> with a list of GMT hour numbers, and
C<rss_updateHours> will call C<rss_skipHours(0 .. 23)> except I<without>
whatever hour numbers you specified.
If you call with an empty list (i.e., C<rss_updateHours();>), then
we uses C<gmtime> to find out the current hour (and rounds it up
if it's after 50 minutes past), basically just as if you'd called:
rss_updateHours( (gmtime(600+time()))[2] );
=cut
sub updateHours { # Just the complement of skipHours.
# Feeding it () means updates only at this hour of day
# (This is fine since you'd never mean to actually declare
# a feed whose updateHours is never, i.e. whose skipHours
# is all of 0-23)
my $self = shift;
my %hours;
@hours{ @_ ? (map $_+0, @_) :
( gmtime( $self->_now_rounded_up ) )[2] } = ();
# might as well count 10:57 as 11h, etc
DEBUG and print "HOURS UPDATEY :", join(' ', sort keys %hours), "\n";
$self->skipHours( grep !exists($hours{$_}), 0 .. 23 );
return;
}
#..........................................................................
=item C<rss_skipDays();>
=item C<rss_skipDays( I<gmt_day_num, gmt_day_num, ...> );>
=item C<rss_skipDays( I<gmt_day_name, gmt_day_name, ...> );>
This function directly sets the C<skipDays> element's values to the
specified weekdays. Note that this accepts either integers (like
6 for Saturday, Sunday being either 0 or 7), or their exact
English names.
If you use the C<skipDays> field, consider that it refers to days
figured by GMT, not local time. For example, if I say to skip Saturdays,
that means Saturdays GMT, which in my timezone (Alaska) starts
in the middle of Friday afternoon.
=cut
sub skipDays {
my($self,@in) = @_;
my @skipdays;
foreach my $day (@in) {
next unless defined $day;
if($day =~ m/^[0-7]$/s) { # tolerate numeric day specs
$day = 0 if $day == 7;
$day = $day_names[$day]
|| Carp::croak "Day number \"$day\" is out of range (0-6)";
} else {
Carp::croak "\"$day\" isn't a valid day name (use 0-6 or one of: @day_names)"
unless $is_day_name{$day};
}
push @skipdays, $day;
};
DEBUG and print "Skipdays: @skipdays\n";
$self->{'skipDays'} = join '',
"<skipDays>", map( "<day>$_</day>", @skipdays), "</skipDays>\n"
;
return;
}
#..........................................................................
=item C<rss_updateDays();>
=item C<rss_updateDays( I<gmt_day_num, gmt_day_num, ...> );>
=item C<rss_updateDays( I<gmt_day_name, gmt_day_name, ...> );>
This function is a wrapper around C<rss_skipDays> -- you call
C<rss_updateDays> with a list of GMT day names/numbers, and
C<rss_updateDays> will call C<rss_skipDays(0 .. 6)> except I<without>
whatever days you specified.
If you call with an empty list (i.e., C<rss_updateDays();>), then
we uses C<gmtime> to find out the current day (GMT!), basically
just as if you'd called:
rss_updateDays( (gmtime(600+time()))[6] );
=cut
sub updateDays { # just the complement of skipDays
# Feeding it () means updates only at this day of the week
# (This is fine since you'd never mean to actually declare
# a feed whose updateDays is never, i.e., whose updateDays
# is all of Monday thru Sunday)
my $self = shift;
my %days;
@days{
map {;
m/^[0-7]$/ ? $day_names[ ($_ == 7) ? 0 : $_ ]
: $is_day_name{$_} ? $_
: Carp::croak "\"$_\" isn't a valid day name (use 0-6 or one of: @day_names)"
}
@_ ? @_ : ( gmtime( $self->_now_rounded_up ) )[6]
} = ();
DEBUG and print "DAYS UPDATEY :", join(' ', sort keys %days), "\n";
$self->skipDays( grep !exists($days{$_}), @day_names );
return;
}
#--------------------------------------------------------------------------
=item C<rss_updatePeriod( I<periodstring> );>
This function directly sets the C<sy:updatePeriod> element's value to the
period specified. You must specify one of the strings:
"yearly", "monthly", "weekly", "daily", "hourly".
I advise using "weekly" only if you know what you're doing, and
"yearly", "monthly" only if you I<really> know what you're doing.
=item C<rss_updatePeriod( I<periodstring>, I<int>, I<base> );>
This is a shortcut for
C<<
rss_updatePeriod(I<periodstring>); rss_updateFrequency(I<int>)
>>
=item C<rss_updatePeriod( I<periodstring>, I<int>, I<base> );>
This is a shortcut for
C<<
rss_updatePeriod(I<periodstring>); rss_updateFrequency(I<int>);
rss_updateBase(I<base>)
>>
=cut
sub updatePeriod {
return $_[0]->{'updatePeriod'} if @_ == 1;
# Else we're a write accessor:
my($self, $period) = @_;
$period or Carp::confess(
"What period? yearly/monthly/weekly/daily/hourly?");
if($period =~ m/^(yearly|monthly|weekly|daily|hourly)$/s) {
$self->{'updatePeriod'} = $period;
$self->updateFrequency($_[2]) if @_ > 2;
$self->updateBase($_[3]) if @_ > 3;
$self->{'_namespaces'}{'sy'} = $NAMESPACE_SY;
return $period;
} else {
Carp::confess(
"What kind of period is \"$period\"? Use one of: yearly|monthly|weekly|daily|hourly");
}
}
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
=item C<rss_updateBase( I<iso_date_string> );>
=item C<rss_updateBase( I<epoch_time> );>
This function directly sets the C<sy:updateBase> element's value to the
moment specified. If you pass in an epoch time, it is converted to
an ISO date string.
=cut
sub updateBase {
return $_[0]->{'updateBase'} if @_ == 1;
# Else we're a write accessor:
my($self, $then) = @_;
if( $then =~ m/^-?\d+$/s ) {
$self->{'updateBase'} = $self->_epoch2isodate($then);
} elsif ( $then =~ # basically ISO8601
m<^
\d\d\d\d # year
(?:
-\d\d # month
(?:
-\d\d # day
(?:
T\d\d:\d\d # hh:mm
(?:
:\d\d # seconds
(?:
\.\d+ # fractions of a second
)?
)?
(?: # TZ offset
Z # Zulu
|
(?: # or by offset:
[-+]
\d\d:\d\d # hh:mm, with leading '+' or '-'
)
)?
)?
)?
)?
# The month was optional, but that
# makes "1994" ambiguous -- a year or an epoch time?
# I doubt anyone wants to write <updateBase>2000</updateBase>,
# esp as the default is basically == <updateBase>1970</updateBase>.
$
>sx
) {
$self->{'updateBase'} = $then;
} else {
Carp::confess("What kind of updateBase is \"$then\"?");
}
return $self->{'updateBase'};
}
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
sub _epoch2isodate {
my($self, $time) = @_;
my(@timelist) = gmtime($time);
++$timelist[4];
$timelist[5] += 1900;
return sprintf("%04d-%02d-%02dT%02d:%02d+00:00",
@timelist[ 5, 4, 3 , 2 ,1 ]);
}
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
%PeriodAsSeconds = (
'hourly' => 60 * 60,
'daily' => 60 * 60 * 24,
'weekly' => 60 * 60 * 24 * 7,
);
sub _updateBase_init {
# What to do? Peg it on now plus Interval, rounded up to next M-minute interval?
my $self = $_[0];
my $now = $self->_now_rounded_up;
my $period_type = $self->updatePeriod;
if( $period_type eq 'monthly' or $period_type eq 'yearly') {
$now = $self->_epoch2isodate( $now );
if($period_type eq 'yearly') {
$now =~ s/^....-/2000-/s || die "SPORK93931!"; # sanity
} elsif($period_type eq 'monthly') {
$now =~ s/^....-..-/2000-01-/s || die "SPORK35286!"; # sanity
} else {
die "SPORK!!!!!94829045"; #sanity
}
DEBUG > 1and print "Using $now as updateBase.\n";
} else {
# It's a plain ol' interval.
DEBUG > 1 and print "Slapping $now (", gmtime($now). " into 1970.\n";
my $freq = $self->updateFrequency();
my $interval_as_seconds = int(
($PeriodAsSeconds{$period_type} ||die "SPORK84258 on '$period_type'!")
/ $freq)
;
DEBUG > 1 and print
"So, $freq times $period_type is $interval_as_seconds seconds...\n";
$now %= $interval_as_seconds;
DEBUG > 1 and print "Using $now (", gmtime($now). " as updateBase.\n";
}
$self->updateBase($now);
return;
}
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
=item the accessor C<rss_updateFrequency( I<integer> );>
This function directly sets the C<sy:updateFrequency> element's value to the
value specified. The value has to be a nonzero positive integer.
For example, this means that this feed updates at/by the start of every hour
and 30 minutes past:
rss_updateBase('2000-01-01T00:00-00:00');
rss_updateFrequency(2);
rss_updatePeriod('hourly'); # 2*hourly means "twice an hour"
Recall that this can also be done with the
the C<rss_updatePeriod( I<per>, I<freq>, I<base> )> shortcut, like so:
rss_updateBase('hourly', 2, '2000-01-01T00:00-00:00');
=cut
sub updateFrequency { # simple accessor, plus the int() thing
if(@_ > 1) {
$_[0]->{'updateFrequency'} = int($_[1]) || 1;
} else {
$_[0]->{'updateFrequency'}
}
}
sub _updateFrequency_init { $_[0]->{'updateFrequency'} ||= 1 }
#--------------------------------------------------------------------------
sub _sy_update_as_xml {
my $self = $_[0];
return '' unless $self->{'updatePeriod'};
$self->_updateFrequency_init();
$self->_updateBase_init();
return sprintf(
q{<sy:updateFrequency>%s</sy:updateFrequency>
<sy:updatePeriod>%s</sy:updatePeriod>
<sy:updateBase>%s</sy:updateBase>
},
$self->updateFrequency,
$self->updatePeriod,
$self->updateBase,
);
}
#--------------------------------------------------------------------------
# Aliases:
sub skip_hours {shift->skipHours( @_)}
sub skip_days {shift->skipDays( @_)}
sub update_days {shift->updateDays( @_)}
sub update_hours {shift->updateHours( @_)}
sub update_period {shift->updatePeriod( @_)}
sub update_base {shift->updateBase( @_)}
sub update_frequency {shift->updateFrequency( @_)}
sub webmaster {shift->webMaster( @_)}
#--------------------------------------------------------------------------
=item the accessor C<rss_retention(I<number>)>
If you are using an C<rss_history_file(I<file>)>, the history file will
accrete a list of all URLs it has seen. But to keep this file from potentially
getting immense, items that haven't been seen for a while are thrown out.
The period of time a feed's items go unseen before each is forgotten is
called that feed's B<retention>, and is expressed in seconds.
The default retention value is 32 days (i.e., 32*24*60*60, the number
of seconds in 32 days). If you wanted to change it to just a week,
you would do this with C<rss_retention(7*24*60*60)>.
As a special case, a zero or negative value for the retention means
to never clear anything from the history file, no matter how long
it has gone unseen.
=cut
#..........................................................................
=item C<rss_add_comment( I<strings> );>
Call this function if you want to add extra XML comments to this RSS file.
For example, if you call this:
rss_add_comment(
"Our terms of use: http://wherever.int/rsstou.html",
"Any questions? Ask jimmy@wherever.int",
);
...then this RSS feed will contain this XML fairly early on in the file:
<!-- Our terms of use: http://wherever.int/rsstou.html -->
<!-- Any questions? Ask jimmy@wherever.int -->
=cut
sub add_comment {
my $self = shift;
foreach my $c (@_) {
push @{ $self->{'_comments'} }, $c
if defined $c and length $c and $c =~ m/\S/;
# no point in having contentless comments
}
return;
}
#--------------------------------------------------------------------------
=item the accessor C<rss_css( I<url> )>
This defines the given URL as being the XML-CSS stylesheet for this RSS
feed. The default value is "./rss.css" if C<-e "rss.css"> is true, otherwise
is the value http://www.interglacial.com/rss/rss.css
=item the accessor C<rss_xsl( I<url> )>
This defines the given URL as being the XML-XSL stylesheet for this RSS
feed. The default value is none.
=item The accessors
C<<
rss_url( I<string> ), rss_title( I<string> ), rss_description( I<string> )
>>
These define this feed's URL, title, and description. These functions
are just for completeness, since it's simpler to just specify any/all of
these parameters in the call to C<rss_new>.
=item the accessor C<rss_ttl( I<number> )>
This sets the parameter of this RSS feed's C<ttl> element, which
suggests how long (in minutes, not seconds!) an RSS reader should wait after it polls
a feed until it polls it again. For example, C<rss_ttl(90)> would suggest
that a reader should not poll this feed more often than every 90 minutes.
(This element is somewhat obsolescent next to the newer and more
informative C<sy:update*> elements, but is included for backward
compatibility.)
=item the accessor C<rss_allow_duplicates( I<boolean> )>
This controls whether or not duplicate items are filtered out out the
feed. By default this is I<on>. Note that duplicates are detected only
by their URL, so if you call this:
rss_item('http://foo.int/donate', "Give!");
rss_item('http://foo.int/donate', "We need money!");
rss_save('begging.rss');
...then only the first will appear in the feed, since the second item
has a URL that is already being saved in this feed. (However,
C<rss_item_count> is still 2, because filtering out duplicates is
something that only happens as the feed is saved.)
=item the accessor C<rss_docs( I<url> )>
This sets the value of the not-generally-useful C<doc> RSS element.
The default value is "./about_rss.html" if C<-e "about_rss.html"> is
true, otherwise "http://www.interglacial.com/rss/about.html".
=item the accessors
C<<
rss_image_url(I<url>), rss_image_width(I<number>),
rss_image_height(I<number>),
rss_image_title(I<text>), rss_image_link(I<url>),
rss_image_description(I<text>)
>>
These are for manually setting the values of this feed's image element's
subelements:
<image>
<url> (rss_image_url) </url>
<width> (rss_image_width) </width>
<height> (rss_image_height) </height>
<title> (rss_image_title) </title>
<link> (rss_image_link) </link>
<description> (rss_image_description) </description>
</image>
You rarely need to call any of these C<rss_image_I<whatever>> functions --
usually just calling C<rss_image( I<url, h, w> );> is enough.
=cut
#..........................................................................
my @DoW = qw(Sun Mon Tue Wed Thu Fri Sat);
my @Month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
sub _date_rfc822 {
my $self = shift;
my @timelist = (@_ == 0) ? gmtime : (@_ == 1) ? gmtime($_[0]) : @_;
$timelist[5] += 1900;
return sprintf(
"%s, %02d %s %04d %02d:%02d:%02d GMT",
$DoW[$timelist[6]],
$timelist[3],
$Month[$timelist[4]],
@timelist[5, 2,1,0],
);
}
sub _check_age {
my($self, $filename, $maxage) = @_;
my $age;
if($filename and $maxage and $maxage < ($age = -M $filename)) {
Carp::carp(
sprintf "%s warning - %s is getting old -- it hasn't changed in %0.1f days!",
ref($self) || $self,
$filename,
$age,
);
}
return 0;
}
#..........................................................................
sub _various_comments {
my $self = $_[0];
my $x;
return
join '',
map {; $x = $_; $x =~ s/--/__/g; "<!-- $x -->\n"; }
@{ $self->{'_comments'} || [] }
;
}
#..........................................................................
sub _modversion_comment {
my $self = $_[0];
my $selfclass = ref($self);
my $v = eval { $selfclass->VERSION } || $VERSION;
return "\n<!-- Generated with Perl's $selfclass v$v -->\n";
}
#..........................................................................
sub _accessorize { # A simple-minded method-maker
no strict 'refs';
foreach my $attrname (@_) {
next if $attrname =~ m/::/; # a hack
*{caller() . '::' . $attrname} = sub {
use strict;
unless((@_ == 1 or @_ == 2) and ref $_[0] ) {
$Carp::CarpLevel = 1;
Carp::croak(
"Accessor usage: \$obj->$attrname() or \$obj->$attrname(\$new_value)"
);
}
(@_ == 1) ? $_[0]->{$attrname}
: ($_[0]->{$attrname} = $_[1]);
};
}
# Ya know, they say accessories make the ensemble!
return;
}
#..........................................................................
sub xmlesc {
my $self = shift;
my $out = join '', @_;
$out =~ s<([^\x20\x21\x23\x24\x25\x27-\x3b\x3d\x3f-\x7e])>
<$CommonEnts{$1} || ('&#'.(ord($1)).';') >seg;
return $out;
}
sub xmlelem {
my $self = shift;
my $gi = shift;
return "<$gi>" . $self->xmlesc(@_) . "</$gi>";
}
#..........................................................................
sub html2text {
# A rudimentary HTML tokenizer, adapted and simplified
# from Gisle Aas's HTML::Parser v2.25...
local $_;
my($self, @out);
($self, $_) = @_;
return undef unless defined $_;
return $$_ if ref($_) eq 'SCALAR'; # Pass a scalar ref to bypass!
return '' unless length $_;
if( m/^[\x00-\x7e]+$/s and ! m/[<>&]/s) {
# Most common case: a simple string needing no HTML parsing.
# So just compact and trim whitespace, and move on.
tr/\n\r\f\t / /s;
s/ $//s;
s/^ //s;
return $_;
}
while( length($_) ) {
if ( s@^([^&<]+)@@s) { # Any plaintext
DEBUG > 5 and print ":: Plaintext {$1}\n";
push @out, $1;
} elsif ( s@^
(
&\#
(?:
(?: # dec
([0-9]{1,7})
)|(?: # or hex
[xX]([0-9a-fA-F]{1,7})
)
)
)
\b
;?
@@sx
) {
DEBUG > 5 and print ":: Numeric ent {$1}",
defined($2) ? " (dec $2)"
: defined($3) ? " (hex $3)"
: " (weird!)",
"\n";
if( defined $3 and exists $WinLameEntities{hex($3)} ) {
# it's a winlame ent, in hex
DEBUG > 6 and print " Correcting that to &#$WinLameEntities{hex($3)};\n";
push @out, \"&#$WinLameEntities{hex($3)};" ;
} elsif( defined $2 and exists $WinLameEntities{0 + $2} ) {
# it's a winlame ent, in decimal
DEBUG > 6 and print " Correcting that to &#$WinLameEntities{0 + $2};\n";
push @out, \"&#$WinLameEntities{0 + $2};" ;
} else {
# it's a normal entity
DEBUG > 6 and print " Passing it thru as \"$1;\"\n";
push @out, \"$1;";
}
} elsif ( s@^&([A-Za-z][A-Za-z0-9]{0,10})\b(;?)@@s) {
DEBUG > 5 and print ":: Named entity {$1}\n";
if(exists $Entities{$1}) {
push @out, \ $Entities{$1};
} elsif(exists $Entities{ ucfirst(lc($1)) }) {
DEBUG > 6 and print "::: Treating as if it were &",
ucfirst(lc($1)), ";\n";
push @out, \ $Entities{ ucfirst(lc($1)) };
} else {
DEBUG > 6 and print "::: Unresolvable! Treating as plaintext\n";
push @out, "&$1" . ($2 || '');
}
# Things we just ignore:
} elsif( s@^(<!\s*--.*?--\s*>)@@s ) { # "Netscape" comments
DEBUG > 5 and print ":: Simple comment {$1}\n";
} elsif( s@^(<[!?][^>]*>)@@s ) { # doctype, PI, or a weird comment
DEBUG > 5 and print ":: Directive/PI {$1}\n";
} elsif( s@^</?([a-zA-Z][a-zA-Z0-9\.\:\_\-]{0,72})\s*/?>@@ ) {
# End-tag, or a simple start-tag
push @out, ' ' if $IsBlockMarkup{lc $1};
DEBUG > 5 and print ":: Simple tag {$1}",
$IsBlockMarkup{lc $1} ? " +breaky": (), "\n";
} elsif ( # complex start-tag
s@
^
(
<
([a-zA-Z][a-zA-Z0-9\.\:\_\-]{0,72}) # the G.I.
(?:
\s+
[a-zA-Z][a-zA-Z0-9\.\:\_\-]{0,72}
(?: # Attributes can be valueless!
\s*
=
\s*
(?: # Attribute value...
(?:
"[^"]*" # "foo bar"
)|(?:
'[^']*' # 'foo bar'
)|(?:
[^<>\n\r\t ]{0,90} # foobarbaz
# 90 is my sane length-limit on unquoted attrvalues
)
)
)?
)* # any nubmer of attribs
\s* # optional ending whitespace
/? # optional emptiness flag
>
)
@@x
) {
push @out, ' ' if $IsBlockMarkup{lc $2};
DEBUG > 5 and print ":: Complex start-tag {$2}",
$IsBlockMarkup{lc $2} ? " +breaky": (), "\n";
# Gets called only on aberrant input, I think:
} elsif( s@^(.)@@s ) {
DEBUG > 5 and print ":: Last-resort single character {$1}\n";
push @out, $1;
} else {
die "IMPOSSIBLE {$_}\n !!! "; # sanity-check
}
}
foreach my $x (@out) {
if( ref $x ) {
$x = $$x;
} else { # do necessary escaping
$x =~ tr/\n\r\f\t / /s; # smash whitespace
$x = $self->xmlesc($x) unless $x =~ m/^[a-zA-Z0-9_'",\. ]*$/s
# Dodge calling on the most common case, i.e., text
# that really doesn't need any excuse at all.
}
}
return join '', @out;
}
#..........................................................................
$MIME_Type = 'application/rss+xml';
%WinLameEntities = (
do {;
my $c = 0x80;
map {; $c++ => (hex($_) || 0x007e) }
qw(
20ac 0000 201a 0192 201e 2026 2020 2021 02c6 2030 0160 2039 0152 00 017d 0000
0000 2018 2019 201c 201d 2022 2013 2014 02dc 2122 0161 203a 0153 00 017e 0178
)# | # |
});
_init_common_ents();
sub _init_common_ents {
%CommonEnts = (
'&' => '&',
'<' => '<',
'>' => '>',
'"' => '"',
( map {; chr($_) => " " } 0 .. 31 ),
( map {; chr($_) => "&#$WinLameEntities{$_};" } keys %WinLameEntities ),
);
return;
}
%Entities = (
# HTML entities gotten from the HTML DTDs
'Aacute' => 'Á', 'aacute' => 'á', 'Acirc' => 'Â',
'acirc' => 'â', 'acute' => '´', 'AElig' => 'Æ',
'aelig' => 'æ', 'Agrave' => 'À', 'agrave' => 'à',
'alefsym' => 'ℵ', 'Alpha' => 'Α', 'alpha' => 'α',
'amp' => '&', 'and' => '∧', 'ang' => '∠',
'apos' => ''', 'Aring' => 'Å', 'aring' => 'å',
'asymp' => '≈', 'Atilde' => 'Ã', 'atilde' => 'ã',
'Auml' => 'Ä', 'auml' => 'ä', 'bdquo' => '„',
'Beta' => 'Β', 'beta' => 'β', 'brvbar' => '¦',
'bull' => '•', 'cap' => '∩', 'Ccedil' => 'Ç',
'ccedil' => 'ç', 'cedil' => '¸', 'cent' => '¢',
'Chi' => 'Χ', 'chi' => 'χ', 'circ' => 'ˆ',
'clubs' => '♣', 'cong' => '≅', 'copy' => '©',
'crarr' => '↵', 'cup' => '∪', 'curren' => '¤',
'dagger' => '†', 'Dagger' => '‡', 'darr' => '↓',
'dArr' => '⇓', 'deg' => '°', 'Delta' => 'Δ',
'delta' => 'δ', 'diams' => '♦', 'divide' => '÷',
'Eacute' => 'É', 'eacute' => 'é', 'Ecirc' => 'Ê',
'ecirc' => 'ê', 'Egrave' => 'È', 'egrave' => 'è',
'empty' => '∅', 'emsp' => ' ', 'ensp' => ' ',
'Epsilon' => 'Ε', 'epsilon' => 'ε', 'equiv' => '≡',
'Eta' => 'Η', 'eta' => 'η', 'ETH' => 'Ð',
'eth' => 'ð', 'Euml' => 'Ë', 'euml' => 'ë',
'euro' => '€', 'exist' => '∃', 'fnof' => 'ƒ',
'forall' => '∀', 'frac12' => '½', 'frac14' => '¼',
'frac34' => '¾', 'frasl' => '⁄', 'Gamma' => 'Γ',
'gamma' => 'γ', 'ge' => '≥', 'gt' => '>',
'harr' => '↔', 'hArr' => '⇔', 'hearts' => '♥',
'hellip' => '…', 'Iacute' => 'Í', 'iacute' => 'í',
'Icirc' => 'Î', 'icirc' => 'î', 'iexcl' => '¡',
'Igrave' => 'Ì', 'igrave' => 'ì', 'image' => 'ℑ',
'infin' => '∞', 'int' => '∫', 'Iota' => 'Ι',
'iota' => 'ι', 'iquest' => '¿', 'isin' => '∈',
'Iuml' => 'Ï', 'iuml' => 'ï', 'Kappa' => 'Κ',
'kappa' => 'κ', 'Lambda' => 'Λ', 'lambda' => 'λ',
'lang' => '〈', 'laquo' => '«', 'larr' => '←',
'lArr' => '⇐', 'lceil' => '⌈', 'ldquo' => '“',
'le' => '≤', 'lfloor' => '⌊', 'lowast' => '∗',
'loz' => '◊', 'lrm' => '‎', 'lsaquo' => '‹',
'lsquo' => '‘', 'lt' => '<', 'macr' => '¯',
'mdash' => '—', 'micro' => 'µ', 'middot' => '·',
'minus' => '−', 'Mu' => 'Μ', 'mu' => 'μ',
'nabla' => '∇', 'nbsp' => ' ', 'ndash' => '–',
'ne' => '≠', 'ni' => '∋', 'not' => '¬',
'notin' => '∉', 'nsub' => '⊄', 'Ntilde' => 'Ñ',
'ntilde' => 'ñ', 'Nu' => 'Ν', 'nu' => 'ν',
'Oacute' => 'Ó', 'oacute' => 'ó', 'Ocirc' => 'Ô',
'ocirc' => 'ô', 'OElig' => 'Œ', 'oelig' => 'œ',
'Ograve' => 'Ò', 'ograve' => 'ò', 'oline' => '‾',
'Omega' => 'Ω', 'omega' => 'ω', 'Omicron' => 'Ο',
'omicron' => 'ο', 'oplus' => '⊕', 'or' => '∨',
'ordf' => 'ª', 'ordm' => 'º', 'Oslash' => 'Ø',
'oslash' => 'ø', 'Otilde' => 'Õ', 'otilde' => 'õ',
'otimes' => '⊗', 'Ouml' => 'Ö', 'ouml' => 'ö',
'para' => '¶', 'part' => '∂', 'permil' => '‰',
'perp' => '⊥', 'Phi' => 'Φ', 'phi' => 'φ',
'Pi' => 'Π', 'pi' => 'π', 'piv' => 'ϖ',
'plusmn' => '±', 'pound' => '£', 'prime' => '′',
'Prime' => '″', 'prod' => '∏', 'prop' => '∝',
'Psi' => 'Ψ', 'psi' => 'ψ', 'quot' => '"',
'radic' => '√', 'rang' => '〉', 'raquo' => '»',
'rarr' => '→', 'rArr' => '⇒', 'rceil' => '⌉',
'rdquo' => '”', 'real' => 'ℜ', 'reg' => '®',
'rfloor' => '⌋', 'Rho' => 'Ρ', 'rho' => 'ρ',
'rlm' => '‏', 'rsaquo' => '›', 'rsquo' => '’',
'sbquo' => '‚', 'Scaron' => 'Š', 'scaron' => 'š',
'sdot' => '⋅', 'sect' => '§', 'shy' => '­',
'Sigma' => 'Σ', 'sigma' => 'σ', 'sigmaf' => 'ς',
'sim' => '∼', 'spades' => '♠', 'sub' => '⊂',
'sube' => '⊆', 'sum' => '∑', 'sup' => '⊃',
'sup1' => '¹', 'sup2' => '²', 'sup3' => '³',
'supe' => '⊇', 'szlig' => 'ß', 'Tau' => 'Τ',
'tau' => 'τ', 'there4' => '∴', 'Theta' => 'Θ',
'theta' => 'θ', 'thetasym' => 'ϑ','thinsp' => ' ',
'THORN' => 'Þ', 'thorn' => 'þ', 'tilde' => '˜',
'times' => '×', 'trade' => '™', 'Uacute' => 'Ú',
'uacute' => 'ú', 'uarr' => '↑', 'uArr' => '⇑',
'Ucirc' => 'Û', 'ucirc' => 'û', 'Ugrave' => 'Ù',
'ugrave' => 'ù', 'uml' => '¨', 'upsih' => 'ϒ',
'Upsilon' => 'Υ', 'upsilon' => 'υ', 'Uuml' => 'Ü',
'uuml' => 'ü', 'weierp' => '℘', 'Xi' => 'Ξ',
'xi' => 'ξ', 'Yacute' => 'Ý', 'yacute' => 'ý',
'yen' => '¥', 'yuml' => 'ÿ', 'Yuml' => 'Ÿ',
'Zeta' => 'Ζ', 'zeta' => 'ζ', 'zwj' => '‍',
'zwnj' => '‌',
);
foreach my $tagname ( qw{
br
address applet area base bgsound blockquote body button caption center col
colgroup dd del dir div dl dt fieldset form frame frameset h1 h2 h3 h4 h5
h6 head hr html iframe ilayer input ins isindex label layer legend li link
listing map menu meta multicol noframes nolayer noscript object ol
optgroup option p param plaintext pre script select style table tbody td
textarea tfoot th thead title tr ul xmp
}) { $IsBlockMarkup{$tagname} = 1 unless exists $IsBlockMarkup{$tagname} }
#..........................................................................
# Now the function generators:
@EXPORT = ( 'get_url' );
$EXPORT_TAGS{'functions'} = \@EXPORT; # just for my own backward compat
foreach my $method (
do {
no strict 'refs';
my %to_hide;
@to_hide{@Hidies} = ();
sort
grep !exists $to_hide{$_} && !m/^rss_/s
&& m/^[a-z][_A-Za-z0-9]+$/s && defined &{"XML::RSS::SimpleGen::$_"},
keys %XML::RSS::SimpleGen::
}
) {
my $function = "rss_$method";
DEBUG > 20 and print "$method => $function\n";
push @EXPORT, $function;
no strict 'refs';
unless( defined &{$function} ) {
DEBUG > 20 and print " Defining $function => $function\n";
*{$function} = sub {
use strict 'refs';
unshift @_, ($RSS_obj ||= XML::RSS::SimpleGen::->new);
goto &{
$_[0]->can($method)
|| die "Where's $method for $_[0]?!"
# insane error, should never happen, unless somebody
# goes undefining existing methods!
};
};
}
}
sub rss_new { $RSS_obj = XML::RSS::SimpleGen->new(@_) }
DEBUG > 20 and print "Done compiling ", __PACKAGE__, ".\n";
#--------------------------------------------------------------------------
1;
__END__
=back
=head1 RSS VERSION
RSS feeds emitted by this module are basically according to v0.92 RSS,
with a very few extensions from v2.0 RSS. They are not RDF files.
=head1 SEE ALSO
L<XML::RSS>
L<http://my.netscape.com/publish/formats/rss-0.91.dtd>
L<http://blogs.law.harvard.edu/tech/rss>
L<http://directory.google.com/Top/Reference/Libraries/Library_and_Information_Science/Technical_Services/Cataloguing/Metadata/RDF/Applications/RSS/Specifications/>
L<http://feedvalidator.org/>
You might also like my book I<Perl and LWP>, which discusses the many
screen-scraping techniques that you would use for extracting data from
HTML to make into RSS feeds:
=over
=item L<http://www.oreilly.com/catalog/perllwp/>
=item L<http://www.amazon.com/exec/obidos/ASIN/0596001789/>
=item L<http://www.amazon.co.uk/exec/obidos/ASIN/0596001789/t>
=item L<http://interglacial.com/d/scrapers> -- examples of Perl
programs that produce RSS's (which are visible at
L<http://interglacial.com/rss/> )
=back
=head1 COPYRIGHT AND DISCLAIMERS
Copyright (c) 2003,4 Sean M. Burke. All rights reserved.
This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself.
This program is distributed in the hope that it will be useful, but
without any warranty; without even the implied warranty of
merchantability or fitness for a particular purpose.
Portions of the data tables in this module are derived from the
entity declarations in the W3C XHTML specification.
Currently (January 2004), that's these three:
http://www.w3.org/TR/xhtml1/DTD/xhtml-lat1.ent
http://www.w3.org/TR/xhtml1/DTD/xhtml-special.ent
http://www.w3.org/TR/xhtml1/DTD/xhtml-symbol.ent
Portions of the code in this module were adapted from parts of
Gisle Aas's L<LWP::Simple> and the old (v2.x) version of his
L<HTML::Parser>.
=head1 AUTHOR
Sean M. Burke C<sburke@cpan.org>
=cut
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
On Babbage's Disease:
Charles Babbage, as (necessarily) the first person to work with machines
that can attack problems at arbitrary levels of abstraction, fell into a
trap familiar to toolsmiths since, as described here by the English
ethicist, Lord Moulton:
"One of the sad memories of my life is a visit to the celebrated
mathematician and inventor, Mr Babbage. He was far advanced in age, but
his mind was still as vigorous as ever. He took me through his
work-rooms. In the first room I saw parts of the original Calculating
Machine, which had been shown in an incomplete state many years before
and had even been put to some use. I asked him about its present form.
'I have not finished it because in working at it I came on the idea of
my Analytical Machine, which would do all that it was capable of doing
and much more. Indeed, the idea was so much simpler that it would have
taken more work to complete the Calculating Machine than to design and
construct the other in its entirety, so I turned my attention to the
Analytical Machine.'"
"After a few minutes' talk, we went into the next work-room, where he
showed and explained to me the working of the elements of the Analytical
Machine. I asked if I could see it. 'I have never completed it,' he
said, 'because I hit upon an idea of doing the same thing by a different
and far more effective method, and this rendered it useless to proceed
on the old lines.' Then we went into the third room. There lay scattered
bits of mechanism, but I saw no trace of any working machine. Very
cautiously I approached the subject, and received the dreaded answer,
'It is not constructed yet, but I am working on it, and it will take
less time to construct it altogether than it would have token to
complete the Analytical Machine from the stage in which I left it.' I
took leave of the old man with a heavy heart."
"When he died a few years later, not only had he constructed no machine,
but the verdict of a jury of kind and sympathetic scientific men who
were deputed to pronounce upon what he had left behind him, either in
papers or in mechanism, was that everything was too incomplete of be
capable of being put to any useful purpose."
[Lord Moulton, "The invention of algorithms, its genesis, and growth",
in G. C. Knott, ed., "Napier tercentenary memorial volume" (London,
1915), p. 1-24; quoted in Charles Babbage "Passage from the Life of a
Philosopher", Martin Campbell-Kelly, ed. (Rutgers U. Press and IEEE
Press, 1994), p. 34].
-*-
|