1 /*
   2  * Copyright (c) 2000, 2006, 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.xml.parsers;
  27 
  28 import javax.xml.validation.Schema;
  29 
  30 /**
  31  * Defines a factory API that enables applications to obtain a
  32  * parser that produces DOM object trees from XML documents.
  33  *
  34  * @author <a href="mailto:Jeff.Suttor@Sun.com">Jeff Suttor</a>
  35  * @author <a href="mailto:Neeraj.Bajaj@sun.com">Neeraj Bajaj</a>
  36  *
  37  * @version $Revision: 1.9 $, $Date: 2010/05/25 16:19:44 $
  38 
  39  */
  40 
  41 public abstract class DocumentBuilderFactory {
  42 
  43     private boolean validating = false;
  44     private boolean namespaceAware = false;
  45     private boolean whitespace = false;
  46     private boolean expandEntityRef = true;
  47     private boolean ignoreComments = false;
  48     private boolean coalescing = false;
  49 
  50     /**
  51      * <p>Protected constructor to prevent instantiation.
  52      * Use {@link #newInstance()}.</p>
  53      */
  54     protected DocumentBuilderFactory () {
  55     }
  56 
  57     /**
  58      * Obtain a new instance of a
  59      * <code>DocumentBuilderFactory</code>. This static method creates
  60      * a new factory instance.
  61      * This method uses the following ordered lookup procedure to determine
  62      * the <code>DocumentBuilderFactory</code> implementation class to
  63      * load:
  64      * <p></p>
  65      * <ul>
  66      * <li>
  67      * Use the <code>javax.xml.parsers.DocumentBuilderFactory</code> system
  68      * property.
  69      * </li>
  70      * <li>
  71      * Use the properties file "lib/jaxp.properties" in the JRE directory.
  72      * This configuration file is in standard <code>java.util.Properties
  73      * </code> format and contains the fully qualified name of the
  74      * implementation class with the key being the system property defined
  75      * above.
  76      *
  77      * The jaxp.properties file is read only once by the JAXP implementation
  78      * and it's values are then cached for future use.  If the file does not exist
  79      * when the first attempt is made to read from it, no further attempts are
  80      * made to check for its existence.  It is not possible to change the value
  81      * of any property in jaxp.properties after it has been read for the first time.
  82      * </li>
  83      * <li>
  84      * Uses the service-provider loading facilities, defined by the 
  85      * {@link java.util.ServiceLoader} class, to attempt to locate and load an
  86      * implementation of the service. If there are providers other than the
  87      * implementation specific default located, then the first provider that is
  88      * not the default is instantiated and returned.
  89      * </li>
  90      * <li>
  91      * Otherwise the default implementation, if present, is returned.
  92      * </li>
  93      * </ul>
  94      * <p>
  95      * In case of {@link java.util.ServiceConfigurationError service
  96      * configuration error}, or if no implementation is found,
  97      * a {@link javax.xml.parsers.FactoryConfigurationError}
  98      * will be thrown.
  99      * </p>
 100      *
 101      * Once an application has obtained a reference to a
 102      * <code>DocumentBuilderFactory</code> it can use the factory to
 103      * configure and obtain parser instances.
 104      *
 105      *
 106      * <h2>Tip for Trouble-shooting</h2>
 107      * <p>Setting the <code>jaxp.debug</code> system property will cause
 108      * this method to print a lot of debug messages
 109      * to <code>System.err</code> about what it is doing and where it is looking at.</p>
 110      *
 111      * <p> If you have problems loading {@link DocumentBuilder}s, try:</p>
 112      * <pre>
 113      * java -Djaxp.debug=1 YourProgram ....
 114      * </pre>
 115      *
 116      * @return New instance of a <code>DocumentBuilderFactory</code>
 117      *
 118      * @throws FactoryConfigurationError if the implementation is not
 119      *   available or cannot be instantiated.
 120      */
 121     public static DocumentBuilderFactory newInstance() {
 122         return FactoryFinder.find(
 123                 /* The default property name according to the JAXP spec */
 124                 DocumentBuilderFactory.class, // "javax.xml.parsers.DocumentBuilderFactory"
 125                 /* The fallback implementation class name */
 126                 "com.sun.org.apache.xerces.internal.jaxp.DocumentBuilderFactoryImpl");
 127     }
 128 
 129     /**
 130      * <p>Obtain a new instance of a <code>DocumentBuilderFactory</code> from class name.
 131      * This function is useful when there are multiple providers in the classpath.
 132      * It gives more control to the application as it can specify which provider
 133      * should be loaded.</p>
 134      *
 135      * <p>Once an application has obtained a reference to a <code>DocumentBuilderFactory</code>
 136      * it can use the factory to configure and obtain parser instances.</p>
 137      *
 138      *
 139      * <h2>Tip for Trouble-shooting</h2>
 140      * <p>Setting the <code>jaxp.debug</code> system property will cause
 141      * this method to print a lot of debug messages
 142      * to <code>System.err</code> about what it is doing and where it is looking at.</p>
 143      *
 144      * <p> If you have problems try:</p>
 145      * <pre>
 146      * java -Djaxp.debug=1 YourProgram ....
 147      * </pre>
 148      *
 149      * @param factoryClassName fully qualified factory class name that provides implementation of <code>javax.xml.parsers.DocumentBuilderFactory</code>.
 150      *
 151      * @param classLoader <code>ClassLoader</code> used to load the factory class. If <code>null</code>
 152      *                     current <code>Thread</code>'s context classLoader is used to load the factory class.
 153      *
 154      * @return New instance of a <code>DocumentBuilderFactory</code>
 155      *
 156      * @throws FactoryConfigurationError if <code>factoryClassName</code> is <code>null</code>, or
 157      *                                   the factory class cannot be loaded, instantiated.
 158      *
 159      * @see #newInstance()
 160      *
 161      * @since 1.6
 162      */
 163     public static DocumentBuilderFactory newInstance(String factoryClassName, ClassLoader classLoader){
 164             //do not fallback if given classloader can't find the class, throw exception
 165             return (DocumentBuilderFactory) FactoryFinder.newInstance(factoryClassName, classLoader, false);
 166     }
 167 
 168     /**
 169      * Creates a new instance of a {@link javax.xml.parsers.DocumentBuilder}
 170      * using the currently configured parameters.
 171      *
 172      * @return A new instance of a DocumentBuilder.
 173      *
 174      * @throws ParserConfigurationException if a DocumentBuilder
 175      *   cannot be created which satisfies the configuration requested.
 176      */
 177 
 178     public abstract DocumentBuilder newDocumentBuilder()
 179         throws ParserConfigurationException;
 180 
 181 
 182     /**
 183      * Specifies that the parser produced by this code will
 184      * provide support for XML namespaces. By default the value of this is set
 185      * to <code>false</code>
 186      *
 187      * @param awareness true if the parser produced will provide support
 188      *                  for XML namespaces; false otherwise.
 189      */
 190 
 191     public void setNamespaceAware(boolean awareness) {
 192         this.namespaceAware = awareness;
 193     }
 194 
 195     /**
 196      * Specifies that the parser produced by this code will
 197      * validate documents as they are parsed. By default the value of this
 198      * is set to <code>false</code>.
 199      *
 200      * <p>
 201      * Note that "the validation" here means
 202      * <a href="http://www.w3.org/TR/REC-xml#proc-types">a validating
 203      * parser</a> as defined in the XML recommendation.
 204      * In other words, it essentially just controls the DTD validation.
 205      * (except the legacy two properties defined in JAXP 1.2.)
 206      * </p>
 207      *
 208      * <p>
 209      * To use modern schema languages such as W3C XML Schema or
 210      * RELAX NG instead of DTD, you can configure your parser to be
 211      * a non-validating parser by leaving the {@link #setValidating(boolean)}
 212      * method <code>false</code>, then use the {@link #setSchema(Schema)}
 213      * method to associate a schema to a parser.
 214      * </p>
 215      *
 216      * @param validating true if the parser produced will validate documents
 217      *                   as they are parsed; false otherwise.
 218      */
 219 
 220     public void setValidating(boolean validating) {
 221         this.validating = validating;
 222     }
 223 
 224     /**
 225      * Specifies that the parsers created by this  factory must eliminate
 226      * whitespace in element content (sometimes known loosely as
 227      * 'ignorable whitespace') when parsing XML documents (see XML Rec
 228      * 2.10). Note that only whitespace which is directly contained within
 229      * element content that has an element only content model (see XML
 230      * Rec 3.2.1) will be eliminated. Due to reliance on the content model
 231      * this setting requires the parser to be in validating mode. By default
 232      * the value of this is set to <code>false</code>.
 233      *
 234      * @param whitespace true if the parser created must eliminate whitespace
 235      *                   in the element content when parsing XML documents;
 236      *                   false otherwise.
 237      */
 238 
 239     public void setIgnoringElementContentWhitespace(boolean whitespace) {
 240         this.whitespace = whitespace;
 241     }
 242 
 243     /**
 244      * Specifies that the parser produced by this code will
 245      * expand entity reference nodes. By default the value of this is set to
 246      * <code>true</code>
 247      *
 248      * @param expandEntityRef true if the parser produced will expand entity
 249      *                        reference nodes; false otherwise.
 250      */
 251 
 252     public void setExpandEntityReferences(boolean expandEntityRef) {
 253         this.expandEntityRef = expandEntityRef;
 254     }
 255 
 256     /**
 257      * <p>Specifies that the parser produced by this code will
 258      * ignore comments. By default the value of this is set to <code>false
 259      * </code>.</p>
 260      *
 261      * @param ignoreComments <code>boolean</code> value to ignore comments during processing
 262      */
 263 
 264     public void setIgnoringComments(boolean ignoreComments) {
 265         this.ignoreComments = ignoreComments;
 266     }
 267 
 268     /**
 269      * Specifies that the parser produced by this code will
 270      * convert CDATA nodes to Text nodes and append it to the
 271      * adjacent (if any) text node. By default the value of this is set to
 272      * <code>false</code>
 273      *
 274      * @param coalescing  true if the parser produced will convert CDATA nodes
 275      *                    to Text nodes and append it to the adjacent (if any)
 276      *                    text node; false otherwise.
 277      */
 278 
 279     public void setCoalescing(boolean coalescing) {
 280         this.coalescing = coalescing;
 281     }
 282 
 283     /**
 284      * Indicates whether or not the factory is configured to produce
 285      * parsers which are namespace aware.
 286      *
 287      * @return  true if the factory is configured to produce parsers which
 288      *          are namespace aware; false otherwise.
 289      */
 290 
 291     public boolean isNamespaceAware() {
 292         return namespaceAware;
 293     }
 294 
 295     /**
 296      * Indicates whether or not the factory is configured to produce
 297      * parsers which validate the XML content during parse.
 298      *
 299      * @return  true if the factory is configured to produce parsers
 300      *          which validate the XML content during parse; false otherwise.
 301      */
 302 
 303     public boolean isValidating() {
 304         return validating;
 305     }
 306 
 307     /**
 308      * Indicates whether or not the factory is configured to produce
 309      * parsers which ignore ignorable whitespace in element content.
 310      *
 311      * @return  true if the factory is configured to produce parsers
 312      *          which ignore ignorable whitespace in element content;
 313      *          false otherwise.
 314      */
 315 
 316     public boolean isIgnoringElementContentWhitespace() {
 317         return whitespace;
 318     }
 319 
 320     /**
 321      * Indicates whether or not the factory is configured to produce
 322      * parsers which expand entity reference nodes.
 323      *
 324      * @return  true if the factory is configured to produce parsers
 325      *          which expand entity reference nodes; false otherwise.
 326      */
 327 
 328     public boolean isExpandEntityReferences() {
 329         return expandEntityRef;
 330     }
 331 
 332     /**
 333      * Indicates whether or not the factory is configured to produce
 334      * parsers which ignores comments.
 335      *
 336      * @return  true if the factory is configured to produce parsers
 337      *          which ignores comments; false otherwise.
 338      */
 339 
 340     public boolean isIgnoringComments() {
 341         return ignoreComments;
 342     }
 343 
 344     /**
 345      * Indicates whether or not the factory is configured to produce
 346      * parsers which converts CDATA nodes to Text nodes and appends it to
 347      * the adjacent (if any) Text node.
 348      *
 349      * @return  true if the factory is configured to produce parsers
 350      *          which converts CDATA nodes to Text nodes and appends it to
 351      *          the adjacent (if any) Text node; false otherwise.
 352      */
 353 
 354     public boolean isCoalescing() {
 355         return coalescing;
 356     }
 357 
 358     /**
 359      * Allows the user to set specific attributes on the underlying
 360      * implementation.
 361      *
 362      * @param name The name of the attribute.
 363      * @param value The value of the attribute.
 364      *
 365      * @throws IllegalArgumentException thrown if the underlying
 366      *   implementation doesn't recognize the attribute.
 367      */
 368     public abstract void setAttribute(String name, Object value)
 369                 throws IllegalArgumentException;
 370 
 371     /**
 372      * Allows the user to retrieve specific attributes on the underlying
 373      * implementation.
 374      *
 375      * @param name The name of the attribute.
 376      *
 377      * @return value The value of the attribute.
 378      *
 379      * @throws IllegalArgumentException thrown if the underlying
 380      *   implementation doesn't recognize the attribute.
 381      */
 382     public abstract Object getAttribute(String name)
 383                 throws IllegalArgumentException;
 384 
 385     /**
 386      * <p>Set a feature for this <code>DocumentBuilderFactory</code> and <code>DocumentBuilder</code>s created by this factory.</p>
 387      *
 388      * <p>
 389      * Feature names are fully qualified {@link java.net.URI}s.
 390      * Implementations may define their own features.
 391      * A {@link ParserConfigurationException} is thrown if this <code>DocumentBuilderFactory</code> or the
 392      * <code>DocumentBuilder</code>s it creates cannot support the feature.
 393      * It is possible for a <code>DocumentBuilderFactory</code> to expose a feature value but be unable to change its state.
 394      * </p>
 395      *
 396      * <p>
 397      * All implementations are required to support the {@link javax.xml.XMLConstants#FEATURE_SECURE_PROCESSING} feature.
 398      * When the feature is:</p>
 399      * <ul>
 400      *   <li>
 401      *     <code>true</code>: the implementation will limit XML processing to conform to implementation limits.
 402      *     Examples include enity expansion limits and XML Schema constructs that would consume large amounts of resources.
 403      *     If XML processing is limited for security reasons, it will be reported via a call to the registered
 404      *    {@link org.xml.sax.ErrorHandler#fatalError(SAXParseException exception)}.
 405      *     See {@link  DocumentBuilder#setErrorHandler(org.xml.sax.ErrorHandler errorHandler)}.
 406      *   </li>
 407      *   <li>
 408      *     <code>false</code>: the implementation will processing XML according to the XML specifications without
 409      *     regard to possible implementation limits.
 410      *   </li>
 411      * </ul>
 412      *
 413      * @param name Feature name.
 414      * @param value Is feature state <code>true</code> or <code>false</code>.
 415      *
 416      * @throws ParserConfigurationException if this <code>DocumentBuilderFactory</code> or the <code>DocumentBuilder</code>s
 417      *   it creates cannot support this feature.
 418      * @throws NullPointerException If the <code>name</code> parameter is null.
 419      */
 420     public abstract void setFeature(String name, boolean value)
 421             throws ParserConfigurationException;
 422 
 423     /**
 424      * <p>Get the state of the named feature.</p>
 425      *
 426      * <p>
 427      * Feature names are fully qualified {@link java.net.URI}s.
 428      * Implementations may define their own features.
 429      * An {@link ParserConfigurationException} is thrown if this <code>DocumentBuilderFactory</code> or the
 430      * <code>DocumentBuilder</code>s it creates cannot support the feature.
 431      * It is possible for an <code>DocumentBuilderFactory</code> to expose a feature value but be unable to change its state.
 432      * </p>
 433      *
 434      * @param name Feature name.
 435      *
 436      * @return State of the named feature.
 437      *
 438      * @throws ParserConfigurationException if this <code>DocumentBuilderFactory</code>
 439      *   or the <code>DocumentBuilder</code>s it creates cannot support this feature.
 440      */
 441     public abstract boolean getFeature(String name)
 442             throws ParserConfigurationException;
 443 
 444 
 445     /**
 446      * Gets the {@link Schema} object specified through
 447      * the {@link #setSchema(Schema schema)} method.
 448      *
 449      * @return
 450      *      the {@link Schema} object that was last set through
 451      *      the {@link #setSchema(Schema)} method, or null
 452      *      if the method was not invoked since a {@link DocumentBuilderFactory}
 453      *      is created.
 454      *
 455      * @throws UnsupportedOperationException When implementation does not
 456      *   override this method.
 457      *
 458      * @since 1.5
 459      */
 460     public Schema getSchema() {
 461         throw new UnsupportedOperationException(
 462             "This parser does not support specification \""
 463             + this.getClass().getPackage().getSpecificationTitle()
 464             + "\" version \""
 465             + this.getClass().getPackage().getSpecificationVersion()
 466             + "\""
 467             );
 468 
 469     }
 470 
 471     /**
 472      * <p>Set the {@link Schema} to be used by parsers created
 473      * from this factory.
 474      *
 475      * <p>
 476      * When a {@link Schema} is non-null, a parser will use a validator
 477      * created from it to validate documents before it passes information
 478      * down to the application.
 479      *
 480      * <p>When errors are found by the validator, the parser is responsible
 481      * to report them to the user-specified {@link org.xml.sax.ErrorHandler}
 482      * (or if the error handler is not set, ignore them or throw them), just
 483      * like any other errors found by the parser itself.
 484      * In other words, if the user-specified {@link org.xml.sax.ErrorHandler}
 485      * is set, it must receive those errors, and if not, they must be
 486      * treated according to the implementation specific
 487      * default error handling rules.
 488      *
 489      * <p>
 490      * A validator may modify the outcome of a parse (for example by
 491      * adding default values that were missing in documents), and a parser
 492      * is responsible to make sure that the application will receive
 493      * modified DOM trees.
 494      *
 495      * <p>
 496      * Initialy, null is set as the {@link Schema}.
 497      *
 498      * <p>
 499      * This processing will take effect even if
 500      * the {@link #isValidating()} method returns <code>false</code>.
 501      *
 502      * <p>It is an error to use
 503      * the <code>http://java.sun.com/xml/jaxp/properties/schemaSource</code>
 504      * property and/or the <code>http://java.sun.com/xml/jaxp/properties/schemaLanguage</code>
 505      * property in conjunction with a {@link Schema} object.
 506      * Such configuration will cause a {@link ParserConfigurationException}
 507      * exception when the {@link #newDocumentBuilder()} is invoked.</p>
 508      *
 509      *
 510      * <h4>Note for implmentors</h4>
 511      *
 512      * <p>
 513      * A parser must be able to work with any {@link Schema}
 514      * implementation. However, parsers and schemas are allowed
 515      * to use implementation-specific custom mechanisms
 516      * as long as they yield the result described in the specification.
 517      * </p>
 518      *
 519      * @param schema <code>Schema</code> to use or <code>null</code>
 520      *   to remove a schema.
 521      *
 522      * @throws UnsupportedOperationException When implementation does not
 523      *   override this method.
 524      *
 525      * @since 1.5
 526      */
 527     public void setSchema(Schema schema) {
 528         throw new UnsupportedOperationException(
 529             "This parser does not support specification \""
 530             + this.getClass().getPackage().getSpecificationTitle()
 531             + "\" version \""
 532             + this.getClass().getPackage().getSpecificationVersion()
 533             + "\""
 534             );
 535     }
 536 
 537 
 538 
 539     /**
 540      * <p>Set state of XInclude processing.</p>
 541      *
 542      * <p>If XInclude markup is found in the document instance, should it be
 543      * processed as specified in <a href="http://www.w3.org/TR/xinclude/">
 544      * XML Inclusions (XInclude) Version 1.0</a>.</p>
 545      *
 546      * <p>XInclude processing defaults to <code>false</code>.</p>
 547      *
 548      * @param state Set XInclude processing to <code>true</code> or
 549      *   <code>false</code>
 550      *
 551      * @throws UnsupportedOperationException When implementation does not
 552      *   override this method.
 553      *
 554      * @since 1.5
 555      */
 556     public void setXIncludeAware(final boolean state) {
 557         if (state) {
 558             throw new UnsupportedOperationException(" setXIncludeAware " +
 559                 "is not supported on this JAXP" +
 560                 " implementation or earlier: " + this.getClass());
 561         }
 562     }
 563 
 564     /**
 565      * <p>Get state of XInclude processing.</p>
 566      *
 567      * @return current state of XInclude processing
 568      *
 569      * @throws UnsupportedOperationException When implementation does not
 570      *   override this method.
 571      *
 572      * @since 1.5
 573      */
 574     public boolean isXIncludeAware() {
 575         throw new UnsupportedOperationException(
 576             "This parser does not support specification \""
 577             + this.getClass().getPackage().getSpecificationTitle()
 578             + "\" version \""
 579             + this.getClass().getPackage().getSpecificationVersion()
 580             + "\""
 581             );
 582     }
 583 }