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 | package Torello.HTML; import Torello.HTML.NodeSearch.*; import static Torello.Java.C.*; import Torello.Java.FileRW; import Torello.Java.C; import Torello.HTML.HelperPackages.parse.HTMLTagCounter; import java.util.*; import java.util.function.Predicate; import java.net.URL; import java.io.IOException; /** * Class for finding ancestor & parent nodes of any selected {@link HTMLNode}. * * <BR /><BR /><EMBED CLASS='external-html' DATA-FILE-ID=SURROUNDING> */ @Torello.JavaDoc.StaticFunctional public class Surrounding { private Surrounding() { } /** * This will return the first <B><SPAN STYLE="color: red;">ancestor</SPAN></B> node - along * with it's closing element - as a {@code DotPair} - that matches. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * * @param index This is the index of the node for whose "ancestors" we are searching (to use a * Java-Script DOM Tree term). * * @param htmlTags If this list is empty, we shall look for any ancestor node. Since this * method returns the first, if this list is left empty, and the index-node is surrounded by * even a bold "{@code <B>...</B>}" then that will be the {@code DotPair} result that is * returned. If this list is left non-empty, then the only ancestor nodes whose HTML Element * Tag (usually referred to as "the Element") matches a tag from this list shall be returned. * * <BR /><BR /><B>FOR INSTANCE:</B> If {@code "div", "p"}, and {@code "a"} were provided as * values to this parameter - <I>the search loop would skip over all ancestors that were not * HTML divider, paragraph or anchor elements</I> before selecting a result. * * @return This shall return the first sub-list, as a {@code 'DotPair'} (start & end index * pair). If no matches are found, null will return. This sublist is nearly identical to the * Java-Script <B STYLE="color: red">DOM Tree</B> concept of ancestor-node, though no trees are * constructed by this method. * * @throws ArrayIndexOutOfBoundsException If index is not within the bounds of the passed * vectorized-html parameter {@code 'html'} * * @throws HTMLTokException If any of the tags passed are null, or not found in the table of * {@code class HTMLTags} - specifically if they are not valid HTML Elements. * * @see #FIRST(Vector, int, HTMLTagCounter) * @see ARGCHECK#index(Vector, int) */ public static DotPair first(Vector<? extends HTMLNode> html, int index, String... htmlTags) { return FIRST( html, ARGCHECK.index(html, index), new HTMLTagCounter(htmlTags, HTMLTagCounter.NORMAL, HTMLTagCounter.FIRST) ); } /** * This will return the first <B><SPAN STYLE="color: red;">ancestor</SPAN></B> node - along * with it's closing element - as a {@code DotPair} - that matches the input-parameter * {@code 'htmlTags'} In this case, the term {@code 'except'} shall mean that any matches whose * HTML Token is among the list in parameter {@code String... htmlTags} will be <B>skipped</B>, * and a "higher-level" ancestor will be returned instead. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * * @param index This is the index of the node for whose "ancestors" we are searching (to use a * Java-Script {@code DOM Tree} term). * * @param htmlTags When this list is non-empty (contains <I>at least one token</I>), the search * loop will skip over ancestor nodes that are among the members of this var-args parameter * list. If this method is invoked <I>and this parameter is an empty list</I>, then the search * loop will return the first anestor node identified. * * <BR /><BR /><B>FOR INSTANCE:</B> If {@code "B"} and {@code "P"} were passed as parameters to * this method, then the search-loop will continue looking for higher-level ancestors - * <I>until one was found that was not an HTML {@code 'bold'} or {@code 'paragraph'} element * {@code DotPair}.</I> * * @return This shall return the first sub-list, as a {@code 'DotPair'} (start & end index * pair). If no matches are found, null will return. This sublist is nearly identical to the * Java-Script <B STYLE="color: red">DOM Tree</B> concept of ancestor-node, though no trees are * constructed by this method. * * @throws ArrayIndexOutOfBoundsException If index is not within the bounds of the passed * vectorized-html parameter {@code 'html'} * * @throws HTMLTokException If any of the tags passed are null, or not found in the table of * {@code class HTMLTags} - specifically if they are not valid HTML Elements. * * @see #FIRST(Vector, int, HTMLTagCounter) * @see ARGCHECK#index(Vector, int) */ public static DotPair firstExcept(Vector<? extends HTMLNode> html, int index, String... htmlTags) { return FIRST( html, ARGCHECK.index(html, index), new HTMLTagCounter(htmlTags, HTMLTagCounter.EXCEPT, HTMLTagCounter.FIRST) ); } /** * This will find all <B><SPAN STYLE="color: red;">ancestors</SPAN></B> of a given index. If * parameter {@code String... htmlTags} is null, all HTML elements will be considered. If this * parameter contains any elements, then only those elements shall be considered as match in * the ancestor hierarchy tree. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * * @param index This is the index of the node for whose "ancestors" we are searching (to use a * Java-Script {@code DOM Tree} term). * * @param htmlTags If this list is empty, we shall look for <I><B>all ancestor nodes.</I></B> * Since this method returns the first ancestor node-pair found, f this list is left non-empty, * then the only ancestor nodes whose HTML Element Tag (usually referred to as "the token") are * members of this varargs {@code String} parameter list shall be considered eligible as a * return result for this method. * * <BR /><BR /><B>FOR INSTANCE:</B> If {@code "DIV", "P"}, and {@code "A"} were listed - <I>the * search loop would skip over all ancestors that were not HTML divider, paragraph or anchor * elements</I> before selecting a result. * * @return This shall return <I><B>every</I></B> sub-list, as a {@code 'DotPair'} * (start & end index pair). If no matches are found, an empty {@code Vector} of * zero-elements shall return. These sublists are nearly identical to the Java-Script * <B STYLE="color: red">DOM Tree</B> concept of ancestor-nodes, though no trees are * constructed by this method. * * @throws ArrayIndexOutOfBoundsException If index is not within the bounds of the passed * vectorized-html parameter {@code 'html'} * * @throws HTMLTokException If any of the tags passed are null, or not found in the table of * {@code class HTMLTags} - specifically if they are not valid HTML Elements. * * @see #ALL(Vector, int, HTMLTagCounter) * @see ARGCHECK#index(Vector, int) */ public static Vector<DotPair> all(Vector<? extends HTMLNode> html, int index, String... htmlTags) { return ALL( html, ARGCHECK.index(html, index), new HTMLTagCounter(htmlTags, HTMLTagCounter.NORMAL, HTMLTagCounter.ALL) ); } /** * This will find all <B><SPAN STYLE="color: red;">ancestors</SPAN></B> of a given index. If * parameter {@code String... htmlTags} is null, all HTML elements will be considered. If this * parameter contains any elements, then those elements <B><I>shall not be considered</B></I> * as a match in the ancestor hierarchy tree. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * * @param index This is the index of the node for whose "ancestors" we are searching (to use a * Java-Script {@code DOM Tree} term). * * @param htmlTags When this list is non-empty (contains <I>at least one token</I>), the search * loop will skip over ancestor nodes that are among the members of this var-args parameter * list. If this method is invoked <I>and this parameter is an empty list</I>, then the search * loop will return all ancestor nodes of the index node. * * <BR /><BR /><B>FOR INSTANCE:</B> If {@code "B"} and {@code "P"} were passed as parameters to * this method, then the search-loop which is saving all ancestor matches to it's result-set, * would skip over any HTML {@code 'bold'} or {@code 'paragraph'} {@code DotPair's}. * * @return This shall return <I><B>every</I></B> sub-list, as a {@code 'DotPair'} * (start & end index pair). If no matches are found, an empty {@code Vector} of * zero-elements shall return. These sublists are nearly identical to the Java-Script * <B STYLE="color: red">DOM Tree</B> concept of ancestor-nodes, though no trees are * constructed by this method. * * @throws ArrayIndexOutOfBoundsException If index is not within the bounds of the passed * vectorized-html parameter {@code 'html'} * * @throws HTMLTokException If any of the tags passed are null, or not found in the table of * {@code class HTMLTags} - specifically if they are not valid HTML Elements. * * @see #ALL(Vector, int, HTMLTagCounter) * @see ARGCHECK#index(Vector, int) */ public static Vector<DotPair> allExcept (Vector<? extends HTMLNode> html, int index, String... htmlTags) { return ALL( html, ARGCHECK.index(html, index), new HTMLTagCounter(htmlTags, HTMLTagCounter.EXCEPT, HTMLTagCounter.ALL) ); } // ******************************************************************************************** // ******************************************************************************************** // FIND INTERNAL METHODS // ******************************************************************************************** // ******************************************************************************************** /** * Finds the first <B><SPAN STYLE="color: red;">ancestor</SPAN></B> ("surrounding") node pair. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param index This is any index within the bounds of the {@code 'html'} parameter. * @param tagCounter Any internally used counter, to optimize the search routine. * * @return The matching <B STYLE="color: red;">ancestor</B> node's start-and-end index as a * {@code 'DotPair'}. * * @see TagNode * @see HTMLNode * @see DotPair * @see DotPair#isInside(int) * @see Util.Inclusive#dotPairOPT(Vector, int, int) */ protected static DotPair FIRST (Vector<? extends HTMLNode> html, int index, HTMLTagCounter tagCounter) { int size = html.size(); TagNode tn; DotPair ret; for ( int i=(index-1); (i >= 0) && (! tagCounter.allBanned()); i-- ) if ( ((tn = html.elementAt(i).openTag()) != null) && tagCounter.check(tn) && ((ret = Util.Inclusive.dotPairOPT(html, i, size)) != null) && ret.isInside(index) // isInside(...) Should never fail, but ) // This guarantees to prevent erroneous answers // If there is a match, return that match, and exit immediately. return ret; return null; } /** * Finds all <B><SPAN STYLE="color: red;">ancestor</SPAN></B> ("surrounding"} node pairs. * * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTMLVEC> * @param index This is any index within the bounds of the {@code 'html'} parameter. * @param tagCounter Any internally used counter, to optimize the search routine. * * @return All matching <B STYLE="color: red;">ancestor</B> nodes' start-and-end index pairs * inside a {@code Vector<DotPair>} * * @see TagNode * @see HTMLNode * @see DotPair * @see DotPair#isInside(int) * @see Util.Inclusive#dotPairOPT(Vector, int, int) */ protected static Vector<DotPair> ALL (Vector<? extends HTMLNode> html, int index, HTMLTagCounter tagCounter) { HTMLNode n; TagNode tn; DotPair dp; int size = html.size(); Vector<DotPair> ret = new Vector<>(); for (int i=(index-1); (i >= 0) && (! tagCounter.allBanned()); i--) if ( (n = html.elementAt(i)).isTagNode() && tagCounter.check(tn = (TagNode) n) ) { if ( ((dp = Util.Inclusive.dotPairOPT(html, i, size)) != null) && dp.isInside(index) ) // isInside(...) Should never fail, but // This guarantees to prevent erroneous answers ret.addElement(dp); else // If finding a token match fails, just ignore that token from now on... tagCounter.reportFailed(tn.tok); } return ret; } // ******************************************************************************************** // ******************************************************************************************** // Tester, leave it here! It's not doing you no harm. // ******************************************************************************************** // ******************************************************************************************** static void test(String urlStr, String fileName) throws IOException { // String url = "http://developer.torello.directory/JavaHTML/Version%201/1.4/javadoc/" + // "Torello/HTML/NodeSearch/CommentNodeCount.html"; StringBuilder sb = new StringBuilder(); URL url = new URL(urlStr); Vector<HTMLNode> page = HTMLPage.getPageTokens(url, false); int pos = TextNodeFind.first(page, TextComparitor.CN_CI, "a count of how many"); DotPair dp = Surrounding.firstExcept(page, pos, "li", "body", "div"); sb.append("Text Node Found: [" + page.elementAt(pos) + "]\n"); sb.append("Index Found: " + pos + ", DotPair Found: " + dp.toString() + "\n"); sb.append(Debug.print(page, dp, Debug::J) + "\n"); Vector<DotPair> allDP = Surrounding.allExcept(page, pos, "body", "html", "div"); for (DotPair l : allDP) sb.append( BCYAN + "************************************************************\n" + "************************************************************\n" + RESET + "Index Found: " + pos + ", DotPair Found: " + l.toString() + "\n" + "Starting Node: " + BRED + page.elementAt(l.start).str + RESET + "\n" + "Ending Node:" + BRED + page.elementAt(l.end).str + RESET + "\n" ); String s = sb.toString(); System.out.println(s); if (fileName != null) FileRW.writeFile(C.toHTML(s.replace("<", "<").replace(">", ">")), fileName); } } |