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 | package Torello.HTML; import java.util.*; import java.util.regex.*; import java.util.stream.*; import java.util.function.Predicate; import Torello.HTML.NodeSearch.*; import Torello.Java.*; import Torello.Java.Additional.Ret2; /** * A long list of utilities for searching, finding, extracting and removing HTML from * Vectorized-HTML. * * <BR /><BR /><EMBED CLASS='external-html' DATA-FILE-ID=UTIL> */ @Torello.JavaDoc.StaticFunctional public class Util { private Util() { } // ******************************************************************************************** // ******************************************************************************************** // Trim TextNode Strings // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #trimTextNodes(Vector, int, int, boolean)} */ public static int trimTextNodes(Vector<HTMLNode> page, boolean deleteZeroLengthStrings) { return trimTextNodes(page, 0, -1, deleteZeroLengthStrings); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #trimTextNodes(Vector, int, int, boolean)} */ public static int trimTextNodes (Vector<HTMLNode> page, DotPair dp, boolean deleteZeroLengthStrings) { return trimTextNodes(page, dp.start, dp.end + 1, deleteZeroLengthStrings); } /** * This will iterate through the entire {@code Vector<HTMLNode>}, and invoke * {@code java.lang.String.trim()} on each {@code TextNode} on the page. If this invocation * results in a reduction of {@code String.length()}, then a new {@code TextNode} will be * instantiated whose {@code TextNode.str} field is set to the result of the * {@code String.trim(old_node.str)} operation. * * @param deleteZeroLengthStrings If a {@code TextNode's} length is zero (before or after * {@code trim()} is called) and when this parameter is {@code TRUE}, that {@code TextNode} * must be removed from the {@code Vector}. * * @return Any node that is trimmed or deleted will increment the counter. This counter * final-value is returned */ public static int trimTextNodes (Vector<HTMLNode> page, int sPos, int ePos, boolean deleteZeroLengthStrings) { int counter = 0; IntStream.Builder b = deleteZeroLengthStrings ? IntStream.builder() : null; HTMLNode n = null; LV l = new LV(page, sPos, ePos); for (int i=l.start; i < l.end; i++) if ((n = page.elementAt(i)).isTextNode()) { String trimmed = n.str.trim(); int trimmedLength = trimmed.length(); if ((trimmedLength == 0) && deleteZeroLengthStrings) { b.add(i); counter++; } else if (trimmedLength < n.str.length()) { page.setElementAt(new TextNode(trimmed), i); counter++; } } if (deleteZeroLengthStrings) Util.Remove.nodesOPT(page, b.build().toArray()); return counter; } // ******************************************************************************************** // ******************************************************************************************** // Vectorized-HTML To-String Methods // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #rangeToString(Vector, int, int)} */ public static String pageToString(Vector<? extends HTMLNode> html) { return rangeToString(html, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #rangeToString(Vector, int, int)} */ public static String rangeToString(Vector<? extends HTMLNode> html, DotPair dp) { return rangeToString(html, dp.start, dp.end + 1); } /** * The purpose of this method/function is to convert a portion of the contents of an HTML-Page, * currently being represented as a {@code Vector} of {@code HTMLNode's} into a {@code String.} * Two {@code 'int'} parameters are provided in this method's signature to define a sub-list * of a page to be converted to a {@code java.lang.String} * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The {@code Vector} converted into a {@code String}. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see #pageToString(Vector) * @see #rangeToString(Vector, DotPair) */ public static String rangeToString(Vector<? extends HTMLNode> html, int sPos, int ePos) { StringBuilder ret = new StringBuilder(); LV l = new LV(html, sPos, ePos); for (int i=l.start; i < l.end; i++) ret.append(html.elementAt(i).str); return ret.toString(); } // ******************************************************************************************** // ******************************************************************************************** // Vectorized-HTML TextNode To-String Methods // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #textNodesString(Vector, int, int)} */ public static String textNodesString(Vector<? extends HTMLNode> html) { return textNodesString(html, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #textNodesString(Vector, int, int)} */ public static String textNodesString(Vector<? extends HTMLNode> html, DotPair dp) { return textNodesString(html, dp.start, dp.end + 1); } /** * This will return a {@code String} that is comprised of ONLY the {@code TextNode's} contained * within the input {@code Vector} - <I>and furthermore, only nodes that are situated between * index {@code int 'sPos'} and index {@code int 'ePos'} in that {@code Vector.}</I> * * <BR /><BR />The {@code for-loop} that iterates the input-{@code Vector} parameter will * simply skip an instance of {@code 'TagNode'} and {@code 'CommentNode'} when building the * output return {@code String.}. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return This will return a {@code String} that is comprised of the text-only elements in the * web-page or sub-page. Only text between the requested {@code Vector}-indices is included. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see #textNodesString(Vector, DotPair) * @see #textNodesString(Vector) */ public static String textNodesString(Vector<? extends HTMLNode> html, int sPos, int ePos) { StringBuilder sb = new StringBuilder(); LV l = new LV(html, sPos, ePos); HTMLNode n; for (int i=l.start; i < l.end; i++) if ((n = html.elementAt(i)).isTextNode()) sb.append(n.str); return sb.toString(); } // ******************************************************************************************** // ******************************************************************************************** // TextNode Modification Operations - "Escape Text Nodes" // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #escapeTextNodes(Vector, int, int)} */ public static int escapeTextNodes(Vector<HTMLNode> html) { return escapeTextNodes(html, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #escapeTextNodes(Vector, int, int)} */ public static int escapeTextNodes(Vector<HTMLNode> html, DotPair dp) { return escapeTextNodes(html, dp.start, dp.end + 1); } /** * Will call {@code HTML.Escape.replaceAll} on each {@code TextNode} in the range of * {@code sPos ... ePos} * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The number of {@code TextNode's} that changed as a result of the * {@code Escape.replaceAll(n.str)} loop. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see Escape#replaceAll(String) */ public static int escapeTextNodes(Vector<HTMLNode> html, int sPos, int ePos) { LV l = new LV(html, sPos, ePos); HTMLNode n = null; String s = null; int counter = 0; for (int i=l.start; i < l.end; i++) if ((n = html.elementAt(i)).isTextNode()) if (! (s = Escape.replace(n.str)).equals(n.str)) { html.setElementAt(new TextNode(s), i); counter++; } return counter; } // ******************************************************************************************** // ******************************************************************************************** // Clone HTML Vectors // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #cloneRange(Vector, int, int)} */ public static Vector<HTMLNode> clone(Vector<? extends HTMLNode> html) { return cloneRange(html, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #cloneRange(Vector, int, int)} */ public static Vector<HTMLNode> cloneRange(Vector<? extends HTMLNode> html, DotPair dp) { return cloneRange(html, dp.start, dp.end + 1); } /** * Copies (clones!) a sub-range of the HTML page, stores the results in a {@code Vector}, and * returns it. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The "cloned" (copied) sub-range specified by {@code 'sPos'} and {@code 'ePos'.} * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see #cloneRange(Vector, DotPair) */ public static Vector<HTMLNode> cloneRange(Vector<? extends HTMLNode> html, int sPos, int ePos) { LV l = new LV(html, sPos, ePos); Vector<HTMLNode> ret = new Vector<>(l.size()); // Copy the range specified into the return vector // // HOW THIS WAS DONE BEFORE NOTICING Vector.subList // // for (int i = l.start; i < l.end; i++) ret.addElement(html.elementAt(i)); ret.addAll(html.subList(l.start, l.end)); return ret; } // ******************************************************************************************** // ******************************************************************************************** // String Length of the TextNode's // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #textStrLength(Vector, int, int)} */ public static int textStrLength(Vector<? extends HTMLNode> html, DotPair dp) { return textStrLength(html, dp.start, dp.end + 1); } /** * Convenience Method. * <BR />Invokes: {@link #textStrLength(Vector, int, int)} */ public static int textStrLength(Vector<? extends HTMLNode> html) { return textStrLength(html, 0, -1); } /** * This method will return the length of the strings <I><B>contained by all/only instances of * {@code 'TextNode'}</B></I> among the nodes of the input HTML-{@code Vector}. This is * identical to the behavior of the method with the same name, but includes starting and ending * bounds on the html {@code Vector}: {@code 'sPos'} & {@code 'ePos'}. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The sum of the lengths of the text contained by text-nodes in the {@code Vector} * between {@code 'sPos'} and {@code 'ePos'}. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> */ public static int textStrLength(Vector<? extends HTMLNode> html, int sPos, int ePos) { HTMLNode n; int sum = 0; LV l = new LV(html, sPos, ePos); // Counts the length of each "String" in a "TextNode" between sPos and ePos for (int i=l.start; i < l.end; i++) if ((n = html.elementAt(i)).isTextNode()) sum += n.str.length(); return sum; } // ******************************************************************************************** // ******************************************************************************************** // Compact Adjacent / Adjoining TextNode's // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #compactTextNodes(Vector, int, int)} */ public static int compactTextNodes(Vector<HTMLNode> html) { return compactTextNodes(html, 0, html.size()); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #compactTextNodes(Vector, int, int)} */ public static int compactTextNodes(Vector<HTMLNode> html, DotPair dp) { return compactTextNodes(html, dp.start, dp.end + 1); } /** * Occasionally, when removing instances of {@code TagNode} from a vectorized-html * page, certain instances of {@code TextNode} which were not adjacent / neighbours in * the {@code Vector}, all of a sudden become adjacent. Although there are no major problems * with contiguous instances of {@code TextNode} from the Search Algorithm's perspective, * for programmer's, it can sometimes be befuddling to realize that the output text that * is returned from a call to {@code Util.pageToString(html)} is not being found because * the text that is left is broken amongst multiple instances of adjacent TextNodes. * * <BR /><BR />This method merely combines "Adjacent" instances of {@code class TextNode} * in the {@code Vector} into single instances of {@code class TextNode} * * @param html Any vectorized-html web-page. If this page contain any contiguously placed * {@code TextNode's}, the extra's will be eliminated, and the internal-string's inside the * node's ({@code TextNode.str}) will be combined. This action will reduce the size of the * actual html-{@code Vector}. * * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The number of nodes that were eliminated after being combined, or 0 if there * were no text-nodes that were removed. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see HTMLNode#str * @see TextNode */ public static int compactTextNodes(Vector<HTMLNode> html, int sPos, int ePos) { LV l = new LV(html, sPos, ePos); boolean compacting = false; int firstPos = -1; int delta = 0; for (int i=l.start; i < (l.end - delta); i++) if (html.elementAt(i).isTextNode()) { if (compacting) continue; // Not in "Compacting Mode" compacting = true; // Start "Compacting Mode" - this is a TextNode firstPos = i; } else if (compacting && (firstPos < (i-1))) // Else - Must be a TagNode or CommentNode { // Save compacted TextNode String's into this StringBuilder StringBuilder compacted = new StringBuilder(); // Iterate all TextNodes that were adjacent, put them together into StringBuilder for (int j=firstPos; j < i; j++) compacted.append(html.elementAt(j).str); // Place this new "aggregate TextNode" at location of the first TextNode that // was compacted into this StringBuilder html.setElementAt(new TextNode(compacted.toString()), firstPos); // Remove the rest of the positions in the Vector that had TextNode's. These have // all been put together into the "Aggregate TextNode" at position "firstPos" Util.Remove.range(html, firstPos + 1, i); // The change in the size of the Vector needs to be accounted for. delta += (i - firstPos - 1); // Change the loop-counter variable, too, since the size of the Vector has changed. i = firstPos + 1; // Since we just hit a CommentNode, or TagNode, exit "Compacting Mode." compacting = false; } // NOTE: This, ALSO, MUST BE a TagNode or CommentNode (just like the previous // if-else branch !) // TRICKY: Don't forget this 'else' ! else compacting = false; // Added - Don't forget the case where the Vector ends with a series of TextNodes // TRICKY TOO! (Same as the HTML Parser... The ending or 'trailing' nodes must be parsed int lastNodePos = html.size() - 1; if (html.elementAt(lastNodePos).isTextNode()) if (compacting && (firstPos < lastNodePos)) { StringBuilder compacted = new StringBuilder(); // Compact the TextNodes that were identified at the end of the Vector range. for (int j=firstPos; j <= lastNodePos; j++) compacted.append(html.elementAt(j).str); // Replace the group of TextNode's at the end of the Vector, with the single, aggregate html.setElementAt(new TextNode(compacted.toString()), firstPos); Util.Remove.range(html, firstPos + 1, lastNodePos + 1); } return delta; } // ******************************************************************************************** // ******************************************************************************************** // String-Length Operations // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #strLength(Vector, int, int)} */ public static int strLength(Vector<? extends HTMLNode> html) { return strLength(html, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #strLength(Vector, int, int)} */ public static int strLength(Vector<? extends HTMLNode> html, DotPair dp) { return strLength(html, dp.start, dp.end + 1); } /** * This method simply adds / sums the {@code String}-length of every {@code HTMLNode.str } * field in the passed page-{@code Vector}. It only counts nodes between parameters * {@code sPos} (inclusive) and {@code ePos} (exclusive). * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The total length <B><I>- in characters -</I></B> of the sub-page of HTML between * {@code 'sPos'} and {@code 'ePos'} * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see #strLength(Vector) */ public static int strLength(Vector<? extends HTMLNode> html, int sPos, int ePos) { int ret = 0; LV l = new LV(html, sPos, ePos); for (int i=l.start; i < l.end; i++) ret += html.elementAt(i).str.length(); return ret; } // ******************************************************************************************** // ******************************************************************************************** // Hash-Code Operations // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #hashCode(Vector, int, int)} */ public static int hashCode(Vector<? extends HTMLNode> html) { return hashCode(html, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #hashCode(Vector, int, int)} */ public static int hashCode(Vector<? extends HTMLNode> html, DotPair dp) { return hashCode(html, dp.start, dp.end + 1); } /** * Generates a hash-code for a vectorized html page-{@code Vector}. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return Returns the {@code String.hashCode()} of the <I><B>partial HTML-page</B></i> as if * it were not being stored as a {@code Vector}, but rather as HTML inside of a * Java-{@code String}. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see #hashCode(Vector) */ public static int hashCode(Vector<? extends HTMLNode> html, int sPos, int ePos) { int h = 0; LV lv = new LV(html, sPos, ePos); for (int j=lv.start; j < lv.end; j++) { String s = html.elementAt(j).str; int l = s.length(); // This line has been copied from the jdk8/jdk8 "String.hashCode()" method. // The difference is that it iterates over the entire vector for (int i=0; i < l; i++) h = 31 * h + s.charAt(i); } return h; } // ******************************************************************************************** // ******************************************************************************************** // JSON Script Nodes // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #getJSONScriptBlocks(Vector, int, int)} */ public static Stream<String> getJSONScriptBlocks(Vector<HTMLNode> html) { return getJSONScriptBlocks(html, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair}. * <BR />Invokes: {@link #getJSONScriptBlocks(Vector, int, int)} */ public static Stream<String> getJSONScriptBlocks(Vector<HTMLNode> html, DotPair dp) { return getJSONScriptBlocks(html, dp.start, dp.end + 1); } /** * This method shall search for any and all {@code <SCRIPT TYPE="json">} * <I>JSON TEXT</I> {@code </SCRIPT>} block present in a range of Vectorized HTML. The * search method shall simply look for the toke {@code "JSON"} in the {@code TYPE} attribute * of each and every {@code <SCRIPT> TagNode} that is found on the page. The validity of the * {@code JSON} found within such blocks <I>is not checked for validity, nor is it even * guaranteed to be {@code JSON} data!</I> * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return This will return a {@code java.util.stream.Stream<String>} of each of the * {@code JSON} elements present in the specified range of the Vectorized HTML passed to * parameter {@code 'html'}. * * <EMBED CLASS='external-html' DATA-FILE-ID=STRMCNVT> * * @see StrTokCmpr#containsIgnoreCase(String, Predicate, String) * @see Util#rangeToString(Vector, int, int) */ public static Stream<String> getJSONScriptBlocks(Vector<HTMLNode> html, int sPos, int ePos) { // Whenever building lists, it is usually easiest to use a Stream.Builder Stream.Builder<String> b = Stream.builder(); // This Predicate simply tests that if the substring "json" (CASE INSENSITIVE) is found // in the TYPE attribute of a <SCRIPT TYPE=...> node, that the token-string is, indeed a // word - not a substring of some other word. For instance: TYPE="json" would PASS, but // TYPE="rajsong" would FAIL - because the token string is not surrounded by white-space final Predicate<String> tester = (String s) -> StrTokCmpr.containsIgnoreCase (s, (Character c) -> ! Character.isLetterOrDigit(c), "json"); // Find all <SCRIPT> node-blocks whose "TYPE" attribute abides by the tester // String-Predicate named above. Vector<DotPair> jsonDPList = InnerTagFindInclusive.all (html, sPos, ePos, "script", "type", tester); // Convert each of these DotPair element into a java.lang.String // Add the String to the Stream.Builder<String> for (DotPair jsonDP : jsonDPList) if (jsonDP.size() > 2) b.accept(Util.rangeToString(html, jsonDP.start + 1, jsonDP.end)); // Build the Stream, and return it. return b.build(); } // ******************************************************************************************** // ******************************************************************************************** // MISC // ******************************************************************************************** // ******************************************************************************************** /** * Inserts nodes, and allows a 'varargs' parameter. * * @param html Any HTML Page * * @param pos The position in the original {@code Vector} where the nodes shall be inserted. * * @param nodes A list of nodes to insert. */ public static void insertNodes(Vector<HTMLNode> html, int pos, HTMLNode... nodes) { Vector<HTMLNode> nodesVec = new Vector<>(nodes.length); for (HTMLNode node : nodes) nodesVec.addElement(node); html.addAll(pos, nodesVec); } /** * Convenience Method. * <BR />Invokes: {@link #replaceRange(Vector, int, int, Vector)} */ public static void replaceRange (Vector<HTMLNode> page, DotPair range, Vector<HTMLNode> newNodes) { replaceRange(page, range.start, range.end+1, newNodes); } /** * Replaces any all and all {@code HTMLNode's} located between the {@code Vector} locations * {@code 'sPos'} (inclusive) and {@code 'ePos'} (exclusive). By exclusive, this means that * the {@code HTMLNode} located at positon {@code 'ePos'} <B><I>will not</I></B> be replaced, * but the one at {@code 'sPos'} <I><B>is replaced</B></I>. * * <BR /><BR />The size of the {@code Vector} will change by {@code newNodes.size() - * (ePos + sPos)}. The contents situated between {@code Vector} location {@code sPos} and * {@code sPos + newNodes.size()} will, indeed, be the contents of the {@code 'newNodes'} * parameter. * * @param page Any Java HTML page, constructed of {@code HTMLNode (TagNode & TextNode)} * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * @param newNodes Any Java HTML page-{@code Vector} of {@code HTMLNode}. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see #pollRange(Vector, int, int) * @see Remove#range(Vector, int, int) * @see #replaceRange(Vector, DotPair, Vector) */ public static void replaceRange (Vector<HTMLNode> page, int sPos, int ePos, Vector<HTMLNode> newNodes) { // Torello.Java.LV LV l = new LV(sPos, ePos, page); int oldSize = ePos - sPos; int newSize = newNodes.size(); int insertPos = sPos; int i = 0; while ((i < newSize) && (i < oldSize)) page.setElementAt(newNodes.elementAt(i++), insertPos++); // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** // CASE ONE: // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** if (newSize == oldSize) return; // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** // CASE TWO: // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** // // The new Vector is SMALLER than the old sub-range // The rest of the nodes just need to be trashed // // OLD-WAY: (Before realizing what Vector.subList is actually doing) // Util.removeRange(page, insertPos, ePos); if (newSize < oldSize) page.subList(insertPos, ePos).clear(); // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** // CASE THREE: // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** // // The new Vector is BIGGER than the old sub-range // There are still more nodes to insert. else page.addAll(ePos, newNodes.subList(i, newSize)); } /** * Java's {@code java.util.Vector} class does not allow public access to the * {@code removeRange(start, end)} function. It is listed as {@code 'protected'} in Java's * Documentation about the {@code class Vector.} This method upstages that, and performs the * {@code 'Poll'} operation, where the nodes are first removed, stored, and then return as a * function result. * * <BR /><BR /><B CLASS=JDDescLabel>Poll a Range:</B> * * <BR />The nodes that are removed are placed in a separate return {@code Vector}, and * returned as a result to this method. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return A complete list ({@code Vector<HTMLNode>}) of the nodes that were removed. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see Remove#range(Vector, int, int) * @see Remove#range(Vector, DotPair) * @see #pollRange(Vector, DotPair) */ public static Vector<HTMLNode> pollRange(Vector<? extends HTMLNode> html, int sPos, int ePos) { // The original version of this method is preserved inside comments at the bottom of this // method. Prior to seeing the Sun-Oracle Docs explaining that the return from the SubList // operation "mirrors changes" back to to the original vector, the code in the comments is // how this method was accomplished. LV l = new LV(html, sPos, ePos); Vector<HTMLNode> ret = new Vector<HTMLNode>(l.end - l.start); List<? extends HTMLNode> list = html.subList(l.start, l.end); // Copy the Nodes into the return Vector that the end-user receives ret.addAll(list); // Clear the nodes out of the original Vector. The Sun-Oracle Docs // state that the returned sub-list is "mirrored back into" the original list.clear(); // Return the Vector to the user. Note that the List<HTMLNode> CANNOT be returned, // because of it's mirror-qualities, and because this method expects a vector. return ret; /* // BEFORE READING ABOUT Vector.subList(...), this is how this was accomplished: // NOTE: It isn't so clear how the List<HTMLNode> works - likely it doesn't actually // create any new memory-allocated arrays, it is just an "overlay" // Copy the elements from the input vector into the return vector for (int i=l.start; i < l.end; i++) ret.add(html.elementAt(i)); // Remove the range from the input vector (this is the meaning of 'poll') Util.removeRange(html, sPos, ePos); return ret; */ } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #pollRange(Vector, int, int)}. */ public static Vector<HTMLNode> pollRange(Vector<? extends HTMLNode> html, DotPair dp) { return pollRange(html, dp.start, dp.end + 1); } /** * This removes every element from the {@code Vector} beginning at position 0, all the way to * position {@code 'pos'} (exclusive). The {@code elementAt(pos)} remains in the original page * input-{@code Vector}. This is the definition of 'exclusive'. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * * @param pos Any position within the range of the input {@code Vector}. * * @return The elements in the {@code Vector} from position: {@code 0 ('zero')} all the way to * position: {@code 'pos'} */ public static Vector<HTMLNode> split(Vector<? extends HTMLNode> html, int pos) { return pollRange(html, 0, pos); } // ******************************************************************************************** // ******************************************************************************************** // Static Inner-Class: Count // ******************************************************************************************** // ******************************************************************************************** @Torello.JavaDoc.StaticFunctional public static class Count { private Count() { } // **************************************************************************************** // **************************************************************************************** // Count TextNode's // **************************************************************************************** // **************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #textNodes(Vector, int, int)} */ public static int textNodes(Vector<HTMLNode> page) { return textNodes(page, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #textNodes(Vector, int, int)} */ public static int textNodes(Vector<HTMLNode> page, DotPair dp) { return textNodes(page, dp.start, dp.end + 1); } /** * Counts the number of {@code TextNode's} in a {@code Vector<HTMLNode>} between the * demarcated array / {@code Vector} positions, {@code 'sPos'} and {@code 'ePos'} * * @param page Any HTML page. * * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The number of {@code TextNode's} in the {@code Vector} between the demarcated * indices. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> */ public static int textNodes(Vector<HTMLNode> page, int sPos, int ePos) { int counter = 0; LV l = new LV(page, sPos, ePos); // Iterates the entire page between sPos and ePos, incrementing the count for every // instance of text-node. for (int i=l.start; i < l.end; i++) if (page.elementAt(i).isTextNode()) counter++; return counter; } // **************************************************************************************** // **************************************************************************************** // Count CommentNode's // **************************************************************************************** // **************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #commentNodes(Vector, int, int)} */ public static int commentNodes(Vector<HTMLNode> page) { return commentNodes(page, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #commentNodes(Vector, int, int)} */ public static int commentNodes(Vector<HTMLNode> page, DotPair dp) { return commentNodes(page, dp.start, dp.end + 1); } /** * Counts the number of {@code CommentNode's} in an {@code Vector<HTMLNode>} between the * demarcated array / {@code Vector} positions. * * @param page Any HTML page. * * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The number of {@code CommentNode's} in the {@code Vector} between the demarcated * indices. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> */ public static int commentNodes(Vector<HTMLNode> page, int sPos, int ePos) { int counter = 0; LV l = new LV(page, sPos, ePos); // Iterates the entire page between sPos and ePos, incrementing the count for every // instance of comment-node. for (int i=l.start; i < l.end; i++) if (page.elementAt(i).isCommentNode()) counter++; return counter; } // **************************************************************************************** // **************************************************************************************** // Count TagNode's // **************************************************************************************** // **************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #tagNodes(Vector, int, int)} */ public static int tagNodes(Vector<HTMLNode> page) { return tagNodes(page, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #tagNodes(Vector, int, int)} */ public static int tagNodes(Vector<HTMLNode> page, DotPair dp) { return tagNodes(page, dp.start, dp.end + 1); } /** * Counts the number of {@code TagNode's} in a {@code Vector<HTMLNode>} between the * demarcated array / {@code Vector} positions. * * @param page Any HTML page. * * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The number of {@code TagNode's} in the {@code Vector}. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> */ public static int tagNodes(Vector<HTMLNode> page, int sPos, int ePos) { int counter = 0; LV l = new LV(page, sPos, ePos); // Iterates the entire page between sPos and ePos, incrementing the count for every // instance of TagNode. for (int i=l.start; i < l.end; i++) if (page.elementAt(i).isTagNode()) counter++; return counter; } // **************************************************************************************** // **************************************************************************************** // Count TagNode's, put results in a java table/map // **************************************************************************************** // **************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #tagNodes(Vector, int, int)} */ public static Ret2< Hashtable<String, Integer>, Hashtable<String, Integer> > tagNodesToTable(Vector<HTMLNode> page) { return tagNodesToTable(page, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #tagNodesToTable(Vector, int, int)} */ public static Ret2< Hashtable<String, Integer>, Hashtable<String, Integer> > tagNodesToTable(Vector<HTMLNode> page, DotPair dp) { return tagNodesToTable(page, dp.start, dp.end + 1); } /** * For each tag in HTML-5 (according to class {@link HTMLTags}, this method counts the * number of instances of each {@code TagNode} contained by a {@code Vector<HTMLNode>}. * The count is performed on nodes between the parameter-provided array-indices, and the * results are placed into two {@code Hashtable's}. * * @param page Any HTML page. * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The returned {@link Ret2} instance contains the following data: * * <BR /><BR /><UL CLASS=JDUL> * <LI> <B STYLE='color: red;'>{@code ret2.a}:</B> * * <BR /><BR />A {@code java.util.Hashtable} that contains one entry for each HTML-Tag * present within the page's demarcated array-indicies - {@code 'sPos'} and * {@code 'ePos'}. * * <BR /><BR />The keys in this table are Java {@code String's} that contain a * Lower-Case {@link TagNode#tok Tag-Token} (such as: "div", "p", "span", etc...). * The values in this table contain a count on <B CLASS='color: red;'>the number of * Open-Tags that were identified within the page.</B> * <BR /><BR /></LI> * * <LI> <B STYLE='color: red;'>{@code ret2.b}:</B> * * <BR /><BR />A {@code java.util.Hashtable} with counts for each and every * "Closed Tag" on the page, all in an identical manner to that which was described, * above, for {@code ret2.a} - except the counts in this table are for Closed-Tag's * rather than Open-Tag's - {@code </div>} tags, rather than {@code <DIV ...>} tags. * </LI> * * </UL> * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> */ public static Ret2< Hashtable<String, Integer>, Hashtable<String, Integer> > tagNodesToTable(Vector<HTMLNode> page, int sPos, int ePos) { LV l = new LV(page, sPos, ePos); TagNode tn = null; Hashtable<String, Integer> openTags = new Hashtable<>(); Hashtable<String, Integer> closedTags = new Hashtable<>(); // Iterates the entire page between sPos and ePos, incrementing the count for every // instance of TagNode. for (int i=l.start; i < l.end; i++) { if ((tn = page.elementAt(i).ifTagNode()) == null) continue; Hashtable<String, Integer> ht = tn.isClosing ? closedTags : openTags; Integer count = ht.get(tn.tok); if (count == null) count = 1; else count = count + 1; ht.put(tn.tok, count); } return new Ret2<>(openTags, closedTags); } // **************************************************************************************** // **************************************************************************************** // Count New Lines // **************************************************************************************** // **************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #newLines(Vector, int, int)} */ public static int newLines(Vector<? extends HTMLNode> html) { return newLines(html, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #newLines(Vector, int, int)} */ public static int newLines(Vector<? extends HTMLNode> html, DotPair dp) { return newLines(html, dp.start, dp.end + 1); } /** * This will count the number of new-line symbols present <B><I>- on the partial HTML * page</I></B>. The count will include a sum of every {@code HTMLNode.str} that * contains the standard new-line symbols: {@code \r\n, \r, \n}, meaning that UNIX, MSFT, * Apple, etc. forms of text-line rendering should all be treated equally. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The number of new-line characters in all of the {@code HTMLNode's} that occur * between vectorized-page positions {@code 'sPos'} and {@code 'ePos.'} * * <BR /><BR /><B>NOTE:</B> The regular-expression used here 'NEWLINEP' is as follows: * * <DIV CLASS="SNIP">{@code * private static final Pattern NEWLINEP = Pattern.compile("\\r\\n|\\r|\\n"); * }</DIV> * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see StringParse#NEWLINEP */ public static int newLines(Vector<? extends HTMLNode> html, int sPos, int ePos) { int newLineCount = 0; LV l = new LV(html, sPos, ePos); for (int i=l.start; i < l.end; i++) // Uses the Torello.Java.StringParse "New Line RegEx" for ( Matcher m = StringParse.NEWLINEP.matcher(html.elementAt(i).str); m.find(); newLineCount++); return newLineCount; } } // ******************************************************************************************** // ******************************************************************************************** // Static Inner-Class: Remove // ******************************************************************************************** // ******************************************************************************************** @Torello.JavaDoc.StaticFunctional public static class Remove { private Remove() { } // **************************************************************************************** // **************************************************************************************** // TextNode Removal Operations // **************************************************************************************** // **************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #allTextNodes(Vector, int, int)} */ public static int allTextNodes(Vector<HTMLNode> page) { return allTextNodes(page, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #allTextNodes(Vector, int, int)} */ public static int allTextNodes(Vector<HTMLNode> page, DotPair dp) { return allTextNodes(page, dp.start, dp.end + 1); } /** * Takes a sub-section of an HTML {@code Vector} and removes all {@code TextNode} present * * @param page Any HTML page * * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The number of HTML {@code TextNode's} that were removed * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see TextNode * @see #nodesOPT(Vector, int[]) */ public static int allTextNodes(Vector<HTMLNode> page, int sPos, int ePos) { IntStream.Builder b = IntStream.builder(); LV l = new LV(page, sPos, ePos); // Use Java-Streams to build the list of nodes that are valid text-nodes. for (int i=l.start; i < l.end; i++) if (page.elementAt(i).isTextNode()) b.add(i); // Build the stream and convert it to an int[] (integer-array) int[] posArr = b.build().toArray(); // The integer array is guaranteed to be sorted, and contain valid vector-indices. nodesOPT(page, posArr); return posArr.length; } // **************************************************************************************** // **************************************************************************************** // TagNode Removal Operations // **************************************************************************************** // **************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #allTagNodes(Vector, int, int)} */ public static int allTagNodes(Vector<HTMLNode> page) { return allTagNodes(page, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #allTagNodes(Vector, int, int)} */ public static int allTagNodes(Vector<HTMLNode> page, DotPair dp) { return allTagNodes(page, dp.start, dp.end + 1); } /** * Takes a sub-section of an HTML {@code Vector} and removes all {@code TagNode} present * * @param page Any HTML page * * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The number of HTML {@code TagNode's} that were removed * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see TagNode * @see #nodesOPT(Vector, int[]) */ public static int allTagNodes(Vector<HTMLNode> page, int sPos, int ePos) { IntStream.Builder b = IntStream.builder(); LV l = new LV(page, sPos, ePos); // Use Java-Streams to build the list of nodes that are valid tag-nodes. for (int i=l.start; i < l.end; i++) if (page.elementAt(i).isTagNode()) b.add(i); // Build the stream and convert it to an int[] (integer-array) int[] posArr = b.build().toArray(); // The integer array is guaranteed to be sorted, and contain valid vector-indices. nodesOPT(page, posArr); return posArr.length; } // **************************************************************************************** // **************************************************************************************** // CommentNode Removal Operations // **************************************************************************************** // **************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #allCommentNodes(Vector, int, int)} */ public static int allCommentNodes(Vector<HTMLNode> page) { return allCommentNodes(page, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #allCommentNodes(Vector, int, int)} */ public static int allCommentNodes(Vector<HTMLNode> page, DotPair dp) { return allCommentNodes(page, dp.start, dp.end + 1); } /** * Takes a sub-section of an HTML {@code Vector} and removes all {@code CommentNode} * present * * @param page Any HTML page * * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The number of HTML {@code CommentNode's} that were removed * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see CommentNode * @see #nodesOPT(Vector, int[]) */ public static int allCommentNodes(Vector<HTMLNode> page, int sPos, int ePos) { IntStream.Builder b = IntStream.builder(); LV l = new LV(page, sPos, ePos); // Use Java-Streams to build the list of nodes that are valid comment-nodes. for (int i=l.start; i < l.end; i++) if (page.elementAt(i).isCommentNode()) b.add(i); // Build the stream and convert it to an int[] (integer-array) int[] posArr = b.build().toArray(); // The integer array is guaranteed to be sorted, and contain valid vector-indices. nodesOPT(page, posArr); return posArr.length; } // **************************************************************************************** // **************************************************************************************** // Remove All Inner Tags // **************************************************************************************** // **************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #allInnerTags(Vector, int, int)} */ public static int allInnerTags(Vector<HTMLNode> html) { return allInnerTags(html, 0, -1); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #allInnerTags(Vector, int, int)} */ public static int allInnerTags(Vector<? super TagNode> html, DotPair dp) { return allInnerTags(html, dp.start, dp.end + 1); } /** * This method removes all inner-tags (all attributes) from every {@link TagNode} inside of * an HTML page. It does this by replacing every {@code TagNode} in the {@code Vector} * with the pre-instantiated, publicly-available {@code TagNode} which can be obtained by a * call to the class {@code HTMLTags.hasTag(token, TC)}. * * <BR /><BR /><B CLASS=JDDescLabel>Replacing {@code TagNode's:}</B> * * <BR />This method determines whether a fresh {@link TagNode} is to be inserted by * measuring the length of the internal {@link TagNode#str} field (a {@code String} field). * If the length {@code TagNode.str} is not equal to the HTML token {@link TagNode#tok} * length <B><I>plus 2</I></B>, then a fresh, pre-instantiated, node is replaced. * * <BR /><BR />The {@code '+2'} figure comes from the additional characters {@code '<'} and * {@code '>'} that start and end every HTML {@code TagNode} * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return The number of {@code TagNode} elements that have were replaced with * zero-attribute HTML Element Tags. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @throws ClassCastException If {@code 'html'} contains references that do not inherit * {@code HTMLNode}. */ @SuppressWarnings("unchecked") public static int allInnerTags(Vector<? super TagNode> html, int sPos, int ePos) { int ret = 0; LV l = new LV(sPos, ePos, html); TagNode tn; for (int i = (l.end-1); i >= l.start; i--) if ((tn = ((HTMLNode) html.elementAt(i)).openTagPWA()) != null) { ret++; // HTMLTags.hasTag(tok, TC) gets an empty and pre-instantiated TagNode, // where TagNode.tok == 'tn.tok' and TagNode.isClosing = false html.setElementAt(HTMLTags.hasTag(tn.tok, TC.OpeningTags), i); } return ret; } // **************************************************************************************** // **************************************************************************************** // Style-Node & Script-Node Block Removal Operations // **************************************************************************************** // **************************************************************************************** /** * Removes all HTML {@code 'style'} Node blocks. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * * @return The number of {@code <STYLE>}-Node Blocks that were removed */ public static int styleNodeBlocks(Vector<? extends HTMLNode> html) { int removeCount = 0; while (TagNodeRemoveInclusive.first(html, "style") > 0) removeCount++; return removeCount; } /** * Removes all {@code 'script'} Node blocks. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * * @return The number of {@code SCRIPT}-Node Blocks that were removed */ public static int scriptNodeBlocks(Vector<? extends HTMLNode> html) { int removeCount = 0; while (TagNodeRemoveInclusive.first(html, "script") > 0) removeCount++; return removeCount; } // **************************************************************************************** // **************************************************************************************** // Remove a Sub-Range of nodes // **************************************************************************************** // **************************************************************************************** /** * Java's {@code java.util.Vector} class does not allow public access to the * {@code removeRange(start, end)} function. It is protected in Java's Documentation about * the {@code Vector} class. This method does exactly that, nothing else. * * @param page Any Java HTML page, constructed of {@code HTMLNode (TagNode & TextNode)} * * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @return the number of nodes removed. * * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> * * @see #pollRange(Vector, int, int) * @see #range(Vector, DotPair) */ public static <T extends HTMLNode> int range(Vector<T> page, int sPos, int ePos) { // Torello.Java.LV LV l = new LV(sPos, ePos, page); // According to the Sun-Oracle Docs, the returned sublist "mirros" the original vector, // which means that when it is changed, so is the original vector. page.subList(l.start, l.end).clear(); return l.size(); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #range(Vector, int, int)} */ public static int range(Vector<? extends HTMLNode> html, DotPair dp) { return range(html, dp.start, dp.end + 1); } // **************************************************************************************** // **************************************************************************************** // Remove Specified Nodes by Vector-Index // **************************************************************************************** // **************************************************************************************** /** * <SPAN STYLE="color: red;"><B>OPT: Optimized</B></SPAN> * * <BR /><BR />This method does the same thing as * {@link Remove#nodes(boolean, Vector, int[])}, but all error checking is skipped, and the * input integer array is presumed to have been sorted. There are no guarantees about the * behavior of this method if the input array {@code 'posArr'} is not sorted, * <I>least-to-greatest,</I> or if there are duplicate or negative values in this array. * * <BR /><BR /><B CLASS=JDDescLabel>Empty Var-Args:</B> * * <BR />If the var-args input integer-array parameter is empty, this method shall exit * gracefully (and immediately). * * @param page Any HTML-Page, usually ones generated by {@code HTMLPage.getPageTokens}, but * these may be obtained or created in any fashion so necessary. * * @param posArr An array of integers which list/identify the nodes in the page to be * removed. Because this implementation has been optimized, no error checking will be * performed on this input. It is presumed to be sorted, least-to-greatest, and that all * values in the array are valid-indices into the vectorized-html parameter {@code 'page'} */ public static <T extends HTMLNode> void nodesOPT(Vector<T> page, int... posArr) { if (posArr.length == 0) return; int endingInsertPos = page.size() - posArr.length; int posArrIndex = 0; int insertPos = posArr[0]; int retrievePos = posArr[0]; // There is very little that can be documented about these two loops. Took 3 hours // to figure out. Read the variables names for "best documentation" while (insertPos < endingInsertPos) { // This inner-loop is necessary for when the posArr has consecutive-elements that // are *ALSO* consecutive-pointers. // // For instance, this invokation: // Util.removeNodes(page, 4, 5, 6); ... // where 4, 5, and 6 are consecutive - the inner while-loop is required. // // For this invokation: // Util.removeNodes(page, 2, 4, 6); // the inner-loop is not entered. while ((posArrIndex < posArr.length) && (retrievePos == posArr[posArrIndex])) { retrievePos++; posArrIndex++; } page.setElementAt(page.elementAt(retrievePos++), insertPos++); } // Remove all remaining elements in the tail of the array. page.setSize(page.size() - posArr.length); } /** * This method remove each HTMLNode from the passed-parameter {@code 'page'} * listed/identified by the input array {@code 'nodeList'}. * * <BR /><BR /><B CLASS=JDDescLabel>Empty Var-Args:</B> * * <BR />If the var-args input integer-array parameter is empty, this method shall exit * gracefully (and immediately). * * @param preserveInputArray This is a convenience input parameter that allows a programmer * to "preserve" the original input-parameter integer-array that is passed to this method. * It could be argued this parameter is "superfluous" - however, keep in mind that the * passed parameter {@code 'nodeList'} <B><I>must be sorted</I></B> before this method is * able function properly. There is a sort that's performed within the body of this method. * Just in case that the original order of the integer-array input-parameter must be * preserved, its possible to request for the sort to operate on "a clone" of the * input-parameter integer-array, instead of the original integer-array {@code 'nodeList'} * itself. * * @param page Any HTML-Page, usually ones generated by * {@code HTMLPage.getPageTokens(...)}, but these may be obtained or created in any fashion * so necessary. * * @param nodeList An array of integers which list/identify the nodes in the page to be * removed. * * @throws IllegalArgumentException If the {@code 'nodeList'} contains duplicate entries. * Obviously, no {@code HTMLNode} may be removed from the {@code Vector<HTMLNode>} more * than once. * * @throws IndexOutOfBoundsException If the nodeList contains index-pointers / items that * are not within the bounds of the passed HTML-Page {@code Vector}. */ public static <T extends HTMLNode> void nodes (boolean preserveInputArray, Vector<T> page, int... nodeList) { if (nodeList.length == 0) return; // @Safe Var Args int[] posArr = preserveInputArray ? nodeList.clone() : nodeList; int len = posArr.length; Arrays.sort(posArr); // Check for duplicates in the nodeList, no HTMLNode may be removed twice! for (int i=0; i < (len - 1); i++) if (posArr[i] == posArr[i+1]) throw new IllegalArgumentException( "The input array contains duplicate items, this is not allowed.\n" + "This is since each array-entry is intended to be a pointer/index for items " + "to be removed.\nNo item can possibly be removed twice.!" ); // Make sure all nodes are within the bounds of the original Vector. (no negative // indexes, no indexes greater than the size of the Vector) if ((posArr[0] < 0) || (posArr[len - 1] >= page.size())) throw new IndexOutOfBoundsException ( "The input array contains entries which are not within the bounds of the " + "original-passed Vector.\nHTMLPage Vector has: " + page.size() + " elements.\n" + "Maximum element in the nodeList is [" + posArr[len - 1] + "], and the " + "minimum element is: [" + posArr[0] + "]" ); int endingInsertPos = page.size() - posArr.length; int posArrIndex = 0; int insertPos = posArr[0]; int retrievePos = posArr[0]; // There is very little that can be documented about these two loops. Took 3 hours // to figure out. Read the variables names for "best documentation" while (insertPos < endingInsertPos) { // This inner-loop is necessary for when the posArr has consecutive-elements that // are *ALSO* consecutive-pointers. // // For instance, this invocation: // Util.removeNodes(page, 4, 5, 6); // where 4, 5, and 6 are consecutive - the inner while-loop is required. // // For this invocation: // Util.removeNodes(page, 2, 4, 6); // the inner-loop is not entered. while ((posArrIndex < posArr.length) && (retrievePos == posArr[posArrIndex])) { retrievePos++; posArrIndex++; } page.setElementAt(page.elementAt(retrievePos++), insertPos++); } // Remove all remaining elements in the tail of the array. page.setSize(page.size() - posArr.length); } // **************************************************************************************** // **************************************************************************************** // Inclusive-Empty Removal Operations // **************************************************************************************** // **************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #inclusiveEmpty(Vector, int, int, String[])} */ public static int inclusiveEmpty(Vector<HTMLNode> page, String... htmlTags) { return inclusiveEmpty(page, 0, -1, htmlTags); } /** * Convenience Method. * <BR />Receives: {@code DotPair} * <BR />Invokes: {@link #inclusiveEmpty(Vector, int, int, String[])} */ public static int inclusiveEmpty(Vector<HTMLNode> page, DotPair dp, String... htmlTags) { return inclusiveEmpty(page, dp.start, dp.end + 1, htmlTags); } /** * This will do an "Inclusive Search" using the standard class * {@link TagNodeInclusiveIterator} in the {@code package NodeSearch}. Then it will * inspect the contents of the subsections. Any subsections that do not contain any * instances of {@code HTMLNode} in between them, or any subsections that only contain * "blank-text" (white-space) between them shall be removed. * * <BR /><BR /><B CLASS=JDDescLabel>Recursive Method:</B> * * <BR />The search logic shall perform multiple <I><B>recursive iterations</B></I> of * itself, such that if, for instance, the user requested that all empty HTML divider * ({@code <DIV>}) elements be removed, if after removing a set a dividers resulted in more * empty ones (nested {@code <DIV>} elements), then an additional removal shall be called. * <I>This recursion shall continue until there are no empty HTML elements of the types * listed by</I> {@code 'htmlTags'} * * @param page Any vectorized-html page or sub-page. * @param sPos <EMBED CLASS='external-html' DATA-FILE-ID=SPOSVEC> * @param ePos <EMBED CLASS='external-html' DATA-FILE-ID=EPOSVEC> * * @param htmlTags The list of <I>inclusive</I> (non-singleton) html elements to search for * possibly being empty container tags. * * @return The number of {@code HTMLNode's} that were removed. * @throws IndexOutOfBoundsException <EMBED CLASS='external-html' DATA-FILE-ID=VIOOBEX> */ public static int inclusiveEmpty (Vector<HTMLNode> page, int sPos, int ePos, String... htmlTags) { DotPair subList; int removed = 0; HNLIInclusive iter = TagNodeInclusiveIterator.iter(page, htmlTags); LV l = new LV(page, sPos, ePos); iter.restrictCursor(l); TOP: while (iter.hasNext()) // If there is only the opening & closing pair, with nothing in between, // then the pair must be removed because it is "Empty" (Inclusive Empty) if ((subList = iter.nextDotPair()).size() == 2) { iter.remove(); ePos -= subList.size(); removed += subList.size(); } else { // If there is any TagNode in between the start-end pair, then this is NOT // EMPTY. In this case, skip to the next start-end opening-closing pair. for (int i=(subList.start + 1); i < subList.end; i++) if (! page.elementAt(i).isTextNode()) continue TOP; // If there were only TextNode's between an opening-closing TagNode Pair.... // **AND** those TextNode's are only white-space, then this also considered // Inclusively Empty. (Get all TextNode's, and if .trim() reduces the length() // to zero, then it was only white-space. if (Util.textNodesString(page, subList).trim().length() == 0) { iter.remove(); ePos -= subList.size(); removed += subList.size(); } } // This process must be continued recursively, because if any inner, for instance, // <DIV> ... </DIV> was removed, then the outer list must be re-checked... if (removed > 0) return removed + Remove.inclusiveEmpty(page, sPos, ePos, htmlTags); else return 0; } // **************************************************************************************** // **************************************************************************************** // Miscellaneous Removal Operations // **************************************************************************************** // **************************************************************************************** /** * Removes the first and last element of a vectorized-HTML web-page, or sub-page. * Generally, this could be used to remove the surrounding tag's {@code '<DIV>'} ... * {@code '</DIV>'}, or something similar. * * <BR /><BR />This method <B STYLE="color: red;">WILL NOT CHECK</B> whether there are * matching HTML open-and-close tags at the end beginning and end of this sub-section. * Generally, though, that is how this method is intended to be used. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * * @throws IllegalArgumentException If the {@code Vector} has fewer than two elements. */ public static void firstLast(Vector<? extends HTMLNode> html) { int size = html.size(); if (size < 2) throw new IllegalArgumentException( "You have requested that the first and last elements the input 'page' parameter " + "(a vector) be removed. However, the vector size is only [" + size + "], so " + "this cannot be performed." ); // NOTE: *** This removes elementAt(0) and elementAt(size-1) // *** NOT ALL ELEMENTS BETWEEN 0 and (size-1) Util.Remove.nodesOPT(html, 0, size-1); } } // ******************************************************************************************** // ******************************************************************************************** // Static Inner-Class: Inclusive // ******************************************************************************************** // ******************************************************************************************** /** * Tools for finding the matching-closing tag of any open {@link TagNode}. * * <BR /><BR /><EMBED CLASS='external-html' DATA-FILE-ID=UTILINCL> */ @Torello.JavaDoc.StaticFunctional public static class Inclusive { private Inclusive() { } // **************************************************************************************** // **************************************************************************************** // Inclusive Find/Get // **************************************************************************************** // **************************************************************************************** /** * This finds the closing HTML {@code 'TagNode'} match for a given opening * {@code 'TagNode'} in a given-input html page or sub-section. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * * @param nodeIndex An index into that {@code Vector}. This index must point to an * {@code HTMLNode} element that is: * * <BR /><BR /><OL CLASS=JDOL> * <LI>An instance of {@code TagNode}</LI> * <LI>A {@code TagNode} whose {@code 'isClosing'} field is {@code FALSE}</LI> * <LI>Is not a {@code 'singleton'} HTML element-token * (i.e. {@code <IMG>, <BR>, <H1>, etc...}) * </LI> * </OL> * * @return An "inclusive search" finds {@code OpeningTag} and {@code ClosingTag} pairs - * <I>and returns all the elements between them in the contents of a * return-{@code Vector}, or {@code Vector DotPair}-end-point value</I>. This method * will take a particular node of a {@code Vector}, and (as long it has a match) * find it's <I><B>closing {@code HTMLNode} match.</B></I> The integer returned will * be the index into this page of the closing, matching {@code TagNode.} * * @throws TagNodeExpectedException If the node in the {@code Vector}-parameter * {@code 'html'} contained at index {@code 'nodeIndex'} is not an instance of * {@code TagNode}, then this exception is thrown. * * @throws OpeningTagNodeExpectedException If the node in the {@code Vector}-parameter * {@code 'html'} at index {@code 'nodeIndex'} is a closing version of the HTML element, * then this exception shall throw. * * @throws InclusiveException If the node in {@code Vector}-parameter {@code 'html'}, * pointed-to by index {@code 'nodeIndex'} is an HTML {@code 'Singleton'} / Self-Closing * Tag, then this exception will be thrown. * * @see TagNode * @see TagNode#tok * @see TagNode#isClosing * @see HTMLNode */ public static int find(Vector<? extends HTMLNode> html, int nodeIndex) { TagNode tn = null; HTMLNode n = null; String tok = null; if (! html.elementAt(nodeIndex).isTagNode()) throw new TagNodeExpectedException ( "You have attempted to find a closing tag to match an opening one, " + "but the 'nodeIndex' (" + nodeIndex + ") you have passed doesn't contain " + "an instance of TagNode." ); else tn = (TagNode) html.elementAt(nodeIndex); if (tn.isClosing) throw new OpeningTagNodeExpectedException( "The TagNode indicated by 'nodeIndex' = " + nodeIndex + " has its 'isClosing' " + "boolean as TRUE - this is not an opening TagNode, but it must be to continue." ); // Checks to ensure this token is not a 'self-closing' or 'singleton' tag. // If it is an exception shall throw. InclusiveException.check(tok = tn.tok); int end = html.size(); int openCount = 1; for (int pos = (nodeIndex+1); pos < end; pos++) if ((n = html.elementAt(pos)).isTagNode()) if ((tn = ((TagNode) n)).tok.equals(tok)) { // This keeps a "Depth Count" - where "depth" is just the number of // opened tags, for which a matching, closing tag hasn't been found yet. openCount += (tn.isClosing ? -1 : 1); // When all open-tags of the specified HTML Element 'tok' have been // found, search has finished. if (openCount == 0) return pos; } // The closing-matching tag was not found return -1; } /** * Convenience Method. * <BR />Invokes: {@link #find(Vector, int)} * <BR />Converts: output to <B><CODE>'GET'</CODE></B> format ({@code Vector}-sublist) * <BR />Using: {@link Util#cloneRange(Vector, int, int)} */ public static Vector<HTMLNode> get(Vector<? extends HTMLNode> html, int nodeIndex) { int endPos = find(html, nodeIndex); return (endPos == -1) ? null : cloneRange(html, nodeIndex, endPos + 1); } /** * Convenience Method. * <BR />Invokes: {@link #find(Vector, int)} * <BR />Converts: output to <B><CODE>'PEEK'</CODE></B> format ({@code SubSection}) * <BR />Using: {@link Util#cloneRange(Vector, int, int)} */ public static SubSection peek(Vector<? extends HTMLNode> html, int nodeIndex) { int endPos = find(html, nodeIndex); return (endPos == -1) ? null : new SubSection( new DotPair(nodeIndex, endPos), cloneRange(html, nodeIndex, endPos + 1) ); } /** * Convenience Method. * <BR />Invokes: {@link #find(Vector, int)} * <BR />Converts: output to <B><CODE>'POLL'</CODE></B> format ({@code Vector}-sublist), * <BR />Using: {@link Util#pollRange(Vector, int, int)} * <BR />Removes: The requested Sub-List */ public static Vector<HTMLNode> poll(Vector<? extends HTMLNode> html, int nodeIndex) { int endPos = find(html, nodeIndex); return (endPos == -1) ? null : pollRange(html, nodeIndex, endPos + 1); } /** * Convenience Method. * <BR />Invokes: {@link #find(Vector, int)} * <BR />Converts: output to <B><CODE>'REMOVE'</CODE></B> format ({@code int} - number * of nodes removed) * <BR />Using: {@link Remove#range(Vector, int, int)} * <BR />Removes: The requested Sub-List */ public static int remove(Vector<? extends HTMLNode> html, int nodeIndex) { int endPos = find(html, nodeIndex); return (endPos == -1) ? 0 : Util.Remove.range(html, nodeIndex, endPos + 1); } // **************************************************************************************** // **************************************************************************************** // Optimized Methods, Inclusive Find/Get/Subsection // **************************************************************************************** // **************************************************************************************** /** * Convenience Method. * <BR />Invokes: {@link #dotPairOPT(Vector, int)} * <BR />Converts: output to {@code Vector<HTMLNode>} */ public static Vector<HTMLNode> vectorOPT(Vector<? extends HTMLNode> html, int tagPos) { DotPair dp = dotPairOPT(html, tagPos); if (dp == null) return null; else return Util.cloneRange(html, dp.start, dp.end + 1); } /** * Convenience Method. * <BR />Invokes: {@link #dotPairOPT(Vector, int)} * <BR />Converts: output to {@code SubSection} */ public static SubSection subSectionOPT(Vector<? extends HTMLNode> html, int tagPos) { DotPair dp = dotPairOPT(html, tagPos); if (dp == null) return null; else return new SubSection(dp, Util.cloneRange(html, dp.start, dp.end + 1)); } /** * * <EMBED CLASS='external-html' DATA-FILE-ID=UTILIOPT> * <!-- Inclusive Opt Description --> * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param tagPos <EMBED CLASS='external-html' DATA-FILE-ID=UTILOPTTP> * @return A <B>'DotPair'</B> version of an inclusive, end-to-end HTML tag-element. * * <EMBED CLASS='external-html' DATA-FILE-ID=UTILOPTJSN> * <!-- Note on JS-DOM Tree innerHTML --> * * @see TagNode * @see TagNode#isClosing * @see TagNode#tok * @see DotPair */ public static DotPair dotPairOPT(Vector<? extends HTMLNode> html, int tagPos) { // Temp Variables HTMLNode n; TagNode tn; int openCount = 1; int len = html.size(); // This is the name (token) of the "Opening HTML Element", we are searching for // the matching, closing element String tok = ((TagNode) html.elementAt(tagPos)).tok; for (int i = (tagPos+1); i < len; i++) if ((n = html.elementAt(i)).isTagNode()) if ((tn = (TagNode) n).tok.equals(tok)) { // This keeps a "Depth Count" - where "depth" is just the number of // opened tags, for which a matching, closing tag hasn't been found yet. openCount += (tn.isClosing ? -1 : 1); // When all open-tags of the specified HTML Element 'tok' have been // found, search has finished. if (openCount == 0) return new DotPair(tagPos, i); } // Was not found return null; } /** * Convenience Method. * <BR />Invokes: {@link #dotPairOPT(Vector, int, int)} * <BR />Converts: output to {@code Vector<HTMLNode>} */ public static Vector<HTMLNode> vectorOPT (Vector<? extends HTMLNode> html, int tagPos, int end) { DotPair dp = dotPairOPT(html, tagPos, end); if (dp == null) return null; else return Util.cloneRange(html, dp.start, dp.end + 1); } /** * Convenience Method. * <BR />Invokes: {@link #dotPairOPT(Vector, int, int)} * <BR />Converts: output to {@code SubSection} */ public static SubSection subSectionOPT (Vector<? extends HTMLNode> html, int tagPos, int end) { DotPair dp = dotPairOPT(html, tagPos, end); if (dp == null) return null; else return new SubSection(dp, Util.cloneRange(html, dp.start, dp.end + 1)); } /** * * <EMBED CLASS='external-html' DATA-FILE-ID=UTILIOPT> * <!-- Inclusive Opt Description --> * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param tagPos <EMBED CLASS='external-html' DATA-FILE-ID=UTILOPTTP> * @param end <EMBED CLASS='external-html' DATA-FILE-ID=UTILOPTEND> * * @return A <B>'DotPair'</B> version of an inclusive, end-to-end HTML tag-element. * * <EMBED CLASS='external-html' DATA-FILE-ID=UTILOPTJSN> * <!-- Note on JS-DOM Tree innerHTML --> * * @see TagNode * @see TagNode#isClosing * @see TagNode#tok * @see DotPair */ public static DotPair dotPairOPT(Vector<? extends HTMLNode> html, int tagPos, int end) { // Temp Variables HTMLNode n; TagNode tn; int openCount = 1; int endPos; // This is the name (token) of the "Opening HTML Element", we are searching for // the matching, closing element String tok = ((TagNode) html.elementAt(tagPos)).tok; for (endPos = (tagPos+1); endPos < end; endPos++) if ((n = html.elementAt(endPos)).isTagNode()) if ((tn = (TagNode) n).tok.equals(tok)) { // This keeps a "Depth Count" - where "depth" is just the number of // opened tags, for which a matching, closing tag hasn't been found yet. openCount += (tn.isClosing ? -1 : 1); // When all open-tags of the specified HTML Element 'tok' have been // found, search has finished. if (openCount == 0) return new DotPair(tagPos, endPos); } // The end of the vectorized-html page (or subsection) was reached, but the // matching-closing element was not found. return null; // assert(endPos == html.size()); } } } |