1 /* 2 * Copyright (c) 1998, 2013, 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 public final class ContentModel implements Serializable { 44 /** 45 * Type. Either '*', '?', '+', ',', '|', '&'. 46 */ 47 public int type; 48 49 /** 50 * The content. Either an Element or a ContentModel. 51 */ 52 public Object content; 53 54 /** 55 * The next content model (in a ',', '|' or '&' expression). 56 */ 57 public ContentModel next; 58 59 public ContentModel() { 60 } 61 62 /** 63 * Create a content model for an element. 64 */ 65 public ContentModel(Element content) { 66 this(0, content, null); 67 } 68 69 /** 70 * Create a content model of a particular type. 71 */ 72 public ContentModel(int type, ContentModel content) { 73 this(type, content, null); 74 } 75 76 /** 77 * Create a content model of a particular type. 78 */ 79 public ContentModel(int type, Object content, ContentModel next) { 80 this.type = type; 81 this.content = content; 82 this.next = next; 83 } 84 85 /** 86 * Return true if the content model could 87 * match an empty input stream. 88 */ 89 public boolean empty() { 90 switch (type) { 91 case '*': 92 case '?': 93 return true; 94 95 case '+': 96 case '|': 97 for (ContentModel m = (ContentModel)content ; m != null ; m = m.next) { 98 if (m.empty()) { 99 return true; 100 } 101 } 102 return false; 103 104 case ',': 105 case '&': 106 for (ContentModel m = (ContentModel)content ; m != null ; m = m.next) { 107 if (!m.empty()) { 108 return false; 109 } 110 } 111 return true; 112 113 default: 114 return false; 115 } 116 } 117 118 /** 119 * Update elemVec with the list of elements that are 120 * part of the this contentModel. 121 */ 122 public void getElements(Vector<Element> elemVec) { 123 switch (type) { 124 case '*': 125 case '?': 126 case '+': 127 ((ContentModel)content).getElements(elemVec); 128 break; 129 case ',': 130 case '|': 131 case '&': 132 for (ContentModel m=(ContentModel)content; m != null; m=m.next){ 133 m.getElements(elemVec); 134 } 135 break; 136 default: 137 elemVec.addElement((Element)content); 138 } 139 } 140 141 private boolean valSet[]; 142 private boolean val[]; 143 // A cache used by first(). This cache was found to speed parsing 144 // by about 10% (based on measurements of the 4-12 code base after 145 // buffering was fixed). 146 147 /** 148 * Return true if the token could potentially be the 149 * first token in the input stream. 150 */ 151 public boolean first(Object token) { 152 switch (type) { 153 case '*': 154 case '?': 155 case '+': 156 return ((ContentModel)content).first(token); 157 158 case ',': 159 for (ContentModel m = (ContentModel)content ; m != null ; m = m.next) { 160 if (m.first(token)) { 161 return true; 162 } 163 if (!m.empty()) { 164 return false; 165 } 166 } 167 return false; 168 169 case '|': 170 case '&': { 171 Element e = (Element) token; 172 if (valSet == null) { 173 valSet = new boolean[Element.getMaxIndex() + 1]; 174 val = new boolean[valSet.length]; 175 // All Element instances are created before this ever executes 176 } 177 if (valSet[e.index]) { 178 return val[e.index]; 179 } 180 for (ContentModel m = (ContentModel)content ; m != null ; m = m.next) { 181 if (m.first(token)) { 182 val[e.index] = true; 183 break; 184 } 185 } 186 valSet[e.index] = true; 187 return val[e.index]; 188 } 189 190 default: 191 return (content == token); 192 // PENDING: refer to comment in ContentModelState 193 /* 194 if (content == token) { 195 return true; 196 } 197 Element e = (Element)content; 198 if (e.omitStart() && e.content != null) { 199 return e.content.first(token); 200 } 201 return false; 202 */ 203 } 204 } 205 206 /** 207 * Return the element that must be next. 208 */ 209 public Element first() { 210 switch (type) { 211 case '&': 212 case '|': 213 case '*': 214 case '?': 215 return null; 216 217 case '+': 218 case ',': 219 return ((ContentModel)content).first(); 220 221 default: 222 return (Element)content; 223 } 224 } 225 226 /** 227 * Convert to a string. 228 */ 229 public String toString() { 230 switch (type) { 231 case '*': 232 return content + "*"; 233 case '?': 234 return content + "?"; 235 case '+': 236 return content + "+"; 237 238 case ',': 239 case '|': 240 case '&': 241 char data[] = {' ', (char)type, ' '}; 242 String str = ""; 243 for (ContentModel m = (ContentModel)content ; m != null ; m = m.next) { 244 str = str + m; 245 if (m.next != null) { 246 str += new String(data); 247 } 248 } 249 return "(" + str + ")"; 250 251 default: 252 return content.toString(); 253 } 254 } 255 }