1 /*
   2  * Copyright (c) 1998, 2014, Oracle and/or its affiliates. All rights reserved.
   3  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
   4  *
   5  * This code is free software; you can redistribute it and/or modify it
   6  * under the terms of the GNU General Public License version 2 only, as
   7  * published by the Free Software Foundation.  Oracle designates this
   8  * particular file as subject to the "Classpath" exception as provided
   9  * by Oracle in the LICENSE file that accompanied this code.
  10  *
  11  * This code is distributed in the hope that it will be useful, but WITHOUT
  12  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  13  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  14  * version 2 for more details (a copy is included in the LICENSE file that
  15  * accompanied this code).
  16  *
  17  * You should have received a copy of the GNU General Public License version
  18  * 2 along with this work; if not, write to the Free Software Foundation,
  19  * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
  20  *
  21  * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
  22  * or visit www.oracle.com if you need additional information or have any
  23  * questions.
  24  */
  25 
  26 package javax.swing.text.html.parser;
  27 
  28 import java.util.Vector;
  29 import java.util.Enumeration;
  30 import java.io.*;
  31 
  32 
  33 /**
  34  * A representation of a content model. A content model is
  35  * basically a restricted BNF expression. It is restricted in
  36  * the sense that it must be deterministic. This means that you
  37  * don't have to represent it as a finite state automaton.<p>
  38  * See Annex H on page 556 of the SGML handbook for more information.
  39  *
  40  * @author   Arthur van Hoff
  41  *
  42  */
  43 @SuppressWarnings("serial") // Same-version serialization only
  44 public final class ContentModel implements Serializable {
  45     /**
  46      * Type. Either '*', '?', '+', ',', '|', '&amp;'.
  47      */
  48     public int type;
  49 
  50     /**
  51      * The content. Either an Element or a ContentModel.
  52      */
  53     public Object content;
  54 
  55     /**
  56      * The next content model (in a ',', '|' or '&amp;' expression).
  57      */
  58     public ContentModel next;
  59 
  60     /**
  61      * Creates {@code ContentModel}
  62      */
  63     public ContentModel() {
  64     }
  65 
  66     /**
  67      * Create a content model for an element.
  68      *
  69      * @param content  the element
  70      */
  71     public ContentModel(Element content) {
  72         this(0, content, null);
  73     }
  74 
  75     /**
  76      * Create a content model of a particular type.
  77      *
  78      * @param type     the type
  79      * @param content  the content
  80      */
  81     public ContentModel(int type, ContentModel content) {
  82         this(type, content, null);
  83     }
  84 
  85     /**
  86      * Create a content model of a particular type.
  87      *
  88      * @param type     the type
  89      * @param content  the content
  90      * @param next     the next content model
  91      */
  92     public ContentModel(int type, Object content, ContentModel next) {
  93         this.type = type;
  94         this.content = content;
  95         this.next = next;
  96     }
  97 
  98     /**
  99      * Return true if the content model could
 100      * match an empty input stream.
 101      *
 102      * @return {@code true} if the content model could
 103      *         match an empty input stream
 104      */
 105     public boolean empty() {
 106         switch (type) {
 107           case '*':
 108           case '?':
 109             return true;
 110 
 111           case '+':
 112           case '|':
 113             for (ContentModel m = (ContentModel)content ; m != null ; m = m.next) {
 114                 if (m.empty()) {
 115                     return true;
 116                 }
 117             }
 118             return false;
 119 
 120           case ',':
 121           case '&':
 122             for (ContentModel m = (ContentModel)content ; m != null ; m = m.next) {
 123                 if (!m.empty()) {
 124                     return false;
 125                 }
 126             }
 127             return true;
 128 
 129           default:
 130             return false;
 131         }
 132     }
 133 
 134     /**
 135      * Update elemVec with the list of elements that are
 136      * part of the this contentModel.
 137      *
 138      * @param elemVec  the list of elements
 139      */
 140      public void getElements(Vector<Element> elemVec) {
 141          switch (type) {
 142          case '*':
 143          case '?':
 144          case '+':
 145              ((ContentModel)content).getElements(elemVec);
 146              break;
 147          case ',':
 148          case '|':
 149          case '&':
 150              for (ContentModel m=(ContentModel)content; m != null; m=m.next){
 151                  m.getElements(elemVec);
 152              }
 153              break;
 154          default:
 155              elemVec.addElement((Element)content);
 156          }
 157      }
 158 
 159      private boolean valSet[];
 160      private boolean val[];
 161      // A cache used by first().  This cache was found to speed parsing
 162      // by about 10% (based on measurements of the 4-12 code base after
 163      // buffering was fixed).
 164 
 165     /**
 166      * Return true if the token could potentially be the
 167      * first token in the input stream.
 168      *
 169      * @param token  the token
 170      *
 171      * @return {@code true} if the token could potentially be the first token
 172      *         in the input stream
 173      */
 174     public boolean first(Object token) {
 175         switch (type) {
 176           case '*':
 177           case '?':
 178           case '+':
 179             return ((ContentModel)content).first(token);
 180 
 181           case ',':
 182             for (ContentModel m = (ContentModel)content ; m != null ; m = m.next) {
 183                 if (m.first(token)) {
 184                     return true;
 185                 }
 186                 if (!m.empty()) {
 187                     return false;
 188                 }
 189             }
 190             return false;
 191 
 192           case '|':
 193           case '&': {
 194             Element e = (Element) token;
 195             if (valSet == null || valSet.length <= Element.getMaxIndex()) {
 196                 valSet = new boolean[Element.getMaxIndex() + 1];
 197                 val = new boolean[valSet.length];
 198             }
 199             if (valSet[e.index]) {
 200                 return val[e.index];
 201             }
 202             for (ContentModel m = (ContentModel)content ; m != null ; m = m.next) {
 203                 if (m.first(token)) {
 204                     val[e.index] = true;
 205                     break;
 206                 }
 207             }
 208             valSet[e.index] = true;
 209             return val[e.index];
 210           }
 211 
 212           default:
 213             return (content == token);
 214             // PENDING: refer to comment in ContentModelState
 215 /*
 216               if (content == token) {
 217                   return true;
 218               }
 219               Element e = (Element)content;
 220               if (e.omitStart() && e.content != null) {
 221                   return e.content.first(token);
 222               }
 223               return false;
 224 */
 225         }
 226     }
 227 
 228     /**
 229      * Return the element that must be next.
 230      *
 231      * @return the element that must be next
 232      */
 233     public Element first() {
 234         switch (type) {
 235           case '&':
 236           case '|':
 237           case '*':
 238           case '?':
 239             return null;
 240 
 241           case '+':
 242           case ',':
 243             return ((ContentModel)content).first();
 244 
 245           default:
 246             return (Element)content;
 247         }
 248     }
 249 
 250     /**
 251      * Convert to a string.
 252      *
 253      * @return the string representation of this {@code ContentModel}
 254      */
 255     public String toString() {
 256         switch (type) {
 257           case '*':
 258             return content + "*";
 259           case '?':
 260             return content + "?";
 261           case '+':
 262             return content + "+";
 263 
 264           case ',':
 265           case '|':
 266           case '&':
 267             char data[] = {' ', (char)type, ' '};
 268             String str = "";
 269             for (ContentModel m = (ContentModel)content ; m != null ; m = m.next) {
 270                 str = str + m;
 271                 if (m.next != null) {
 272                     str += new String(data);
 273                 }
 274             }
 275             return "(" + str + ")";
 276 
 277           default:
 278             return content.toString();
 279         }
 280     }
 281 }