| Classes in this File | Line Coverage | Branch Coverage | Complexity | ||||
| SAXBuilder |
|
| 2.235294117647059;2.235 |
| 1 | /*-- | |
| 2 | ||
| 3 | Copyright (C) 2000-2012 Jason Hunter & Brett McLaughlin. | |
| 4 | All rights reserved. | |
| 5 | ||
| 6 | Redistribution and use in source and binary forms, with or without | |
| 7 | modification, are permitted provided that the following conditions | |
| 8 | are met: | |
| 9 | ||
| 10 | 1. Redistributions of source code must retain the above copyright | |
| 11 | notice, this list of conditions, and the following disclaimer. | |
| 12 | ||
| 13 | 2. Redistributions in binary form must reproduce the above copyright | |
| 14 | notice, this list of conditions, and the disclaimer that follows | |
| 15 | these conditions in the documentation and/or other materials | |
| 16 | provided with the distribution. | |
| 17 | ||
| 18 | 3. The name "JDOM" must not be used to endorse or promote products | |
| 19 | derived from this software without prior written permission. For | |
| 20 | written permission, please contact <request_AT_jdom_DOT_org>. | |
| 21 | ||
| 22 | 4. Products derived from this software may not be called "JDOM", nor | |
| 23 | may "JDOM" appear in their name, without prior written permission | |
| 24 | from the JDOM Project Management <request_AT_jdom_DOT_org>. | |
| 25 | ||
| 26 | In addition, we request (but do not require) that you include in the | |
| 27 | end-user documentation provided with the redistribution and/or in the | |
| 28 | software itself an acknowledgement equivalent to the following: | |
| 29 | "This product includes software developed by the | |
| 30 | JDOM Project (http://www.jdom.org/)." | |
| 31 | Alternatively, the acknowledgment may be graphical using the logos | |
| 32 | available at http://www.jdom.org/images/logos. | |
| 33 | ||
| 34 | THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED | |
| 35 | WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES | |
| 36 | OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE | |
| 37 | DISCLAIMED. IN NO EVENT SHALL THE JDOM AUTHORS OR THE PROJECT | |
| 38 | CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, | |
| 39 | SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT | |
| 40 | LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF | |
| 41 | USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND | |
| 42 | ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, | |
| 43 | OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT | |
| 44 | OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF | |
| 45 | SUCH DAMAGE. | |
| 46 | ||
| 47 | This software consists of voluntary contributions made by many | |
| 48 | individuals on behalf of the JDOM Project and was originally | |
| 49 | created by Jason Hunter <jhunter_AT_jdom_DOT_org> and | |
| 50 | Brett McLaughlin <brett_AT_jdom_DOT_org>. For more information | |
| 51 | on the JDOM Project, please see <http://www.jdom.org/>. | |
| 52 | ||
| 53 | */ | |
| 54 | ||
| 55 | package org.jdom2.input; | |
| 56 | ||
| 57 | import static org.jdom2.JDOMConstants.SAX_FEATURE_EXTERNAL_ENT; | |
| 58 | import static org.jdom2.JDOMConstants.SAX_PROPERTY_DECLARATION_HANDLER; | |
| 59 | import static org.jdom2.JDOMConstants.SAX_PROPERTY_LEXICAL_HANDLER; | |
| 60 | import static org.jdom2.JDOMConstants.SAX_PROPERTY_LEXICAL_HANDLER_ALT; | |
| 61 | ||
| 62 | import java.io.File; | |
| 63 | import java.io.IOException; | |
| 64 | import java.io.InputStream; | |
| 65 | import java.io.Reader; | |
| 66 | import java.net.MalformedURLException; | |
| 67 | import java.net.URL; | |
| 68 | import java.util.HashMap; | |
| 69 | import java.util.Map; | |
| 70 | ||
| 71 | import org.xml.sax.DTDHandler; | |
| 72 | import org.xml.sax.EntityResolver; | |
| 73 | import org.xml.sax.ErrorHandler; | |
| 74 | import org.xml.sax.InputSource; | |
| 75 | import org.xml.sax.SAXException; | |
| 76 | import org.xml.sax.SAXNotRecognizedException; | |
| 77 | import org.xml.sax.SAXNotSupportedException; | |
| 78 | import org.xml.sax.XMLFilter; | |
| 79 | import org.xml.sax.XMLReader; | |
| 80 | ||
| 81 | import org.jdom2.DefaultJDOMFactory; | |
| 82 | import org.jdom2.DocType; | |
| 83 | import org.jdom2.Document; | |
| 84 | import org.jdom2.EntityRef; | |
| 85 | import org.jdom2.JDOMException; | |
| 86 | import org.jdom2.JDOMFactory; | |
| 87 | import org.jdom2.Verifier; | |
| 88 | import org.jdom2.input.sax.BuilderErrorHandler; | |
| 89 | import org.jdom2.input.sax.DefaultSAXHandlerFactory; | |
| 90 | import org.jdom2.input.sax.SAXBuilderEngine; | |
| 91 | import org.jdom2.input.sax.SAXEngine; | |
| 92 | import org.jdom2.input.sax.SAXHandler; | |
| 93 | import org.jdom2.input.sax.SAXHandlerFactory; | |
| 94 | import org.jdom2.input.sax.XMLReaderJDOMFactory; | |
| 95 | import org.jdom2.input.sax.XMLReaderSAX2Factory; | |
| 96 | import org.jdom2.input.sax.XMLReaders; | |
| 97 | ||
| 98 | /** | |
| 99 | * Builds a JDOM Document using a SAX parser. | |
| 100 | * <p> | |
| 101 | * SAXbuilder uses a third-party SAX parser (chosen by JAXP by default, or you | |
| 102 | * can configure it manually) to handle the parsing duties and uses an instance | |
| 103 | * of a SAXHandler to listen to the SAX events in order to construct a document | |
| 104 | * with JDOM content using a JDOMFactory. Information about SAX can be found at | |
| 105 | * <a href="http://www.saxproject.org">http://www.saxproject.org</a>. | |
| 106 | * <p> | |
| 107 | * For a complete description of how SAXBuilder is used, and how to customise | |
| 108 | * the process you should look at the {@link org.jdom2.input.sax} package | |
| 109 | * documentation. | |
| 110 | * <p> | |
| 111 | * JDOM users needing to customise the SAX parsing process have traditionally | |
| 112 | * sub-classed this SAXBuilder class. In JDOM2 this should never be necessary. | |
| 113 | * Please read the full documentation of this class, {@link SAXHandler}, | |
| 114 | * {@link SAXHandlerFactory}, {@link JDOMFactory}, and the package documentation | |
| 115 | * for {@link org.jdom2.input.sax} before overriding this class. Future versions | |
| 116 | * of JDOM2 may make this class 'final'. I you feel you have a good reason to | |
| 117 | * subclass SAXBuilder please mention it on <a | |
| 118 | * href="http://www.jdom.org/involved/lists.html">jdom-interest</a> mailing list | |
| 119 | * so that SAXBuilder can be extended or adapted to handle your use-case. | |
| 120 | * <p> | |
| 121 | * Neither SAXBuilder nor anything derived from SAXBuilder is thread-safe. You | |
| 122 | * must ensure that SAXBuilder is used in a single thread, or that sufficient | |
| 123 | * locking is in place to ensure that SAXBuilder is not concurrently accessed. | |
| 124 | * See the special note on {@link #buildEngine()}. | |
| 125 | * <p> | |
| 126 | * Known issues: | |
| 127 | * <ul> | |
| 128 | * <li>Relative paths for a {@link DocType} or {@link EntityRef} may be | |
| 129 | * converted by the SAX parser into absolute paths. | |
| 130 | * <li>SAX does not recognise whitespace character content outside the root | |
| 131 | * element (nor does JDOM) so any formatting outside the root Element will be | |
| 132 | * lost. | |
| 133 | * </ul> | |
| 134 | * | |
| 135 | * @see org.jdom2.input.sax | |
| 136 | * @author Jason Hunter | |
| 137 | * @author Brett McLaughlin | |
| 138 | * @author Dan Schaffer | |
| 139 | * @author Philip Nelson | |
| 140 | * @author Alex Rosen | |
| 141 | * @author Rolf Lear | |
| 142 | */ | |
| 143 | public class SAXBuilder implements SAXEngine { | |
| 144 | ||
| 145 | /** Default source of SAXHandlers */ | |
| 146 | 1 | private static final SAXHandlerFactory DEFAULTSAXHANDLERFAC = |
| 147 | new DefaultSAXHandlerFactory(); | |
| 148 | ||
| 149 | /** Default source of JDOM Content */ | |
| 150 | 1 | private static final JDOMFactory DEFAULTJDOMFAC = new DefaultJDOMFactory(); |
| 151 | ||
| 152 | /* | |
| 153 | * ==================================================================== | |
| 154 | */ | |
| 155 | ||
| 156 | /** | |
| 157 | * The XMLReader pillar of SAXBuilder | |
| 158 | */ | |
| 159 | 145 | private XMLReaderJDOMFactory readerfac = null; |
| 160 | ||
| 161 | /** | |
| 162 | * The SAXHandler pillar of SAXBuilder | |
| 163 | */ | |
| 164 | 145 | private SAXHandlerFactory handlerfac = null; |
| 165 | ||
| 166 | /** | |
| 167 | * The JDOMFactory pillar for creating new JDOM objects | |
| 168 | */ | |
| 169 | 145 | private JDOMFactory jdomfac = null; |
| 170 | ||
| 171 | /* | |
| 172 | * ======================================================================== | |
| 173 | * Configuration settings for SAX parsing. | |
| 174 | * ======================================================================== | |
| 175 | */ | |
| 176 | ||
| 177 | /** User-specified features to be set on the SAX parser */ | |
| 178 | 145 | private final HashMap<String, Boolean> features = new HashMap<String, Boolean>(5); |
| 179 | ||
| 180 | /** User-specified properties to be set on the SAX parser */ | |
| 181 | 145 | private final HashMap<String, Object> properties = new HashMap<String, Object>(5); |
| 182 | ||
| 183 | /** ErrorHandler class to use */ | |
| 184 | 145 | private ErrorHandler saxErrorHandler = null; |
| 185 | ||
| 186 | /** EntityResolver class to use */ | |
| 187 | 145 | private EntityResolver saxEntityResolver = null; |
| 188 | ||
| 189 | /** DTDHandler class to use */ | |
| 190 | 145 | private DTDHandler saxDTDHandler = null; |
| 191 | ||
| 192 | /** XMLFilter instance to use */ | |
| 193 | 145 | private XMLFilter saxXMLFilter = null; |
| 194 | ||
| 195 | /** Whether expansion of entities should occur */ | |
| 196 | 145 | private boolean expand = true; |
| 197 | ||
| 198 | /** Whether to ignore ignorable whitespace */ | |
| 199 | 145 | private boolean ignoringWhite = false; |
| 200 | ||
| 201 | /** Whether to ignore all whitespace content */ | |
| 202 | 145 | private boolean ignoringBoundaryWhite = false; |
| 203 | ||
| 204 | /** Whether parser reuse is allowed. */ | |
| 205 | 145 | private boolean reuseParser = true; |
| 206 | ||
| 207 | /** The current SAX parser, if parser reuse has been activated. */ | |
| 208 | 145 | private SAXEngine engine = null; |
| 209 | ||
| 210 | /** | |
| 211 | * Creates a new JAXP-based SAXBuilder. The underlying parser will not | |
| 212 | * validate. | |
| 213 | * | |
| 214 | * @see SAXBuilder#SAXBuilder(XMLReaderJDOMFactory, SAXHandlerFactory, | |
| 215 | * JDOMFactory) | |
| 216 | * @see XMLReaders#NONVALIDATING | |
| 217 | * @see DefaultSAXHandlerFactory | |
| 218 | * @see DefaultJDOMFactory | |
| 219 | */ | |
| 220 | public SAXBuilder() { | |
| 221 | 89 | this(null, null, null); |
| 222 | 89 | } |
| 223 | ||
| 224 | /** | |
| 225 | * Creates a new JAXP-based SAXBuilder. The underlying parser will validate | |
| 226 | * (using DTD) or not according to the given parameter. If you want Schema | |
| 227 | * validation then use SAXBuilder(XMLReaders.XSDVALIDATOR) | |
| 228 | * | |
| 229 | * @see SAXBuilder#SAXBuilder(XMLReaderJDOMFactory, SAXHandlerFactory, | |
| 230 | * JDOMFactory) | |
| 231 | * @see XMLReaders#NONVALIDATING | |
| 232 | * @see XMLReaders#DTDVALIDATING | |
| 233 | * @see DefaultSAXHandlerFactory | |
| 234 | * @see DefaultJDOMFactory | |
| 235 | * @see org.jdom2.input.sax for important details on SAXBuilder | |
| 236 | * @param validate | |
| 237 | * <code>boolean</code> indicating if DTD validation should occur. | |
| 238 | * @deprecated use {@link SAXBuilder#SAXBuilder(XMLReaderJDOMFactory)} with | |
| 239 | * either {@link XMLReaders#DTDVALIDATING} | |
| 240 | * or {@link XMLReaders#NONVALIDATING} | |
| 241 | */ | |
| 242 | @Deprecated | |
| 243 | public SAXBuilder(final boolean validate) { | |
| 244 | 26 | this(validate |
| 245 | ? XMLReaders.DTDVALIDATING | |
| 246 | : XMLReaders.NONVALIDATING, | |
| 247 | null, null); | |
| 248 | 26 | } |
| 249 | ||
| 250 | /** | |
| 251 | * Creates a new SAXBuilder using the specified SAX parser. The underlying | |
| 252 | * parser will not validate. | |
| 253 | * | |
| 254 | * @see SAXBuilder#SAXBuilder(XMLReaderJDOMFactory, SAXHandlerFactory, | |
| 255 | * JDOMFactory) | |
| 256 | * @see XMLReaderSAX2Factory | |
| 257 | * @see DefaultSAXHandlerFactory | |
| 258 | * @see DefaultJDOMFactory | |
| 259 | * @see org.jdom2.input.sax for important details on SAXBuilder | |
| 260 | * @param saxDriverClass | |
| 261 | * <code>String</code> name of SAX Driver to use for parsing. | |
| 262 | * @deprecated use {@link SAXBuilder#SAXBuilder(XMLReaderJDOMFactory)} with | |
| 263 | * {@link XMLReaderSAX2Factory#XMLReaderSAX2Factory(boolean, String)} | |
| 264 | */ | |
| 265 | @Deprecated | |
| 266 | public SAXBuilder(final String saxDriverClass) { | |
| 267 | 3 | this(saxDriverClass, false); |
| 268 | 3 | } |
| 269 | ||
| 270 | /** | |
| 271 | * Creates a new SAXBuilder using the specified SAX2.0 parser source. The | |
| 272 | * underlying parser will validate or not according to the given parameter. | |
| 273 | * | |
| 274 | * @see SAXBuilder#SAXBuilder(XMLReaderJDOMFactory, SAXHandlerFactory, | |
| 275 | * JDOMFactory) | |
| 276 | * @see XMLReaderSAX2Factory | |
| 277 | * @see DefaultSAXHandlerFactory | |
| 278 | * @see DefaultJDOMFactory | |
| 279 | * @see org.jdom2.input.sax for important details on SAXBuilder | |
| 280 | * @param saxDriverClass | |
| 281 | * <code>String</code> name of SAX Driver to use for parsing. | |
| 282 | * @param validate | |
| 283 | * <code>boolean</code> indicating if validation should occur. | |
| 284 | * @deprecated use {@link SAXBuilder#SAXBuilder(XMLReaderJDOMFactory)} with | |
| 285 | * {@link XMLReaderSAX2Factory#XMLReaderSAX2Factory(boolean, String)} | |
| 286 | */ | |
| 287 | @Deprecated | |
| 288 | public SAXBuilder(final String saxDriverClass, final boolean validate) { | |
| 289 | 5 | this(new XMLReaderSAX2Factory(validate, saxDriverClass), null, null); |
| 290 | 5 | } |
| 291 | ||
| 292 | /** | |
| 293 | * Creates a new SAXBuilder with the specified XMLReaderJDOMFactory. | |
| 294 | * <p> | |
| 295 | * | |
| 296 | * @see SAXBuilder#SAXBuilder(XMLReaderJDOMFactory, SAXHandlerFactory, | |
| 297 | * JDOMFactory) | |
| 298 | * @see XMLReaderJDOMFactory | |
| 299 | * @see XMLReaders#NONVALIDATING | |
| 300 | * @see DefaultSAXHandlerFactory | |
| 301 | * @see DefaultJDOMFactory | |
| 302 | * @see org.jdom2.input.sax for important details on SAXBuilder | |
| 303 | * @param readersouce | |
| 304 | * the {@link XMLReaderJDOMFactory} that supplies XMLReaders. If the | |
| 305 | * value is null then a Non-Validating JAXP-based SAX2.0 parser will | |
| 306 | * be used. | |
| 307 | */ | |
| 308 | public SAXBuilder(final XMLReaderJDOMFactory readersouce) { | |
| 309 | 25 | this(readersouce, null, null); |
| 310 | 25 | } |
| 311 | ||
| 312 | /** | |
| 313 | * Creates a new SAXBuilder. This is the base constructor for all other | |
| 314 | * SAXBuilder constructors: they all find a way to create a | |
| 315 | * JDOMXMLReaderFactory and then call this constructor with that factory, | |
| 316 | * and the {@link DefaultSAXHandlerFactory} and {@link DefaultJDOMFactory}. | |
| 317 | * <p> | |
| 318 | * | |
| 319 | * @see XMLReaderJDOMFactory | |
| 320 | * @see XMLReaders#NONVALIDATING | |
| 321 | * @see SAXHandlerFactory | |
| 322 | * @see DefaultSAXHandlerFactory | |
| 323 | * @see JDOMFactory | |
| 324 | * @see DefaultJDOMFactory | |
| 325 | * @see org.jdom2.input.sax for important details on SAXBuilder | |
| 326 | * @param xmlreaderfactory | |
| 327 | * a {@link XMLReaderJDOMFactory} that creates XMLReaders. Specify | |
| 328 | * null for the default. | |
| 329 | * @param handlerfactory | |
| 330 | * a {@link SAXHandlerFactory} that creates SAXHandlers Specify null | |
| 331 | * for the default. | |
| 332 | * @param jdomfactory | |
| 333 | * a {@link JDOMFactory} that creates JDOM Content. Specify null for | |
| 334 | * the default. | |
| 335 | */ | |
| 336 | public SAXBuilder(final XMLReaderJDOMFactory xmlreaderfactory, final SAXHandlerFactory handlerfactory, | |
| 337 | 145 | final JDOMFactory jdomfactory) { |
| 338 | 145 | this.readerfac = xmlreaderfactory == null |
| 339 | ? XMLReaders.NONVALIDATING | |
| 340 | : xmlreaderfactory; | |
| 341 | 145 | this.handlerfac = handlerfactory == null |
| 342 | ? DEFAULTSAXHANDLERFAC | |
| 343 | : handlerfactory; | |
| 344 | 145 | this.jdomfac = jdomfactory == null |
| 345 | ? DEFAULTJDOMFAC | |
| 346 | : jdomfactory; | |
| 347 | 145 | } |
| 348 | ||
| 349 | /** | |
| 350 | * Returns the driver class assigned in the constructor, or null if none. | |
| 351 | * The driver class is only available if a SAX2 source was specified. This | |
| 352 | * method is available for backward-compatibility with JDOM 1.x | |
| 353 | * | |
| 354 | * @return the driver class assigned in the constructor | |
| 355 | * @deprecated as the driver class is only available in limited situations | |
| 356 | * and anyway it had to be supplied in a constructor as either a | |
| 357 | * direct value or as an {@link XMLReaderSAX2Factory} instance. | |
| 358 | */ | |
| 359 | @Deprecated | |
| 360 | public String getDriverClass() { | |
| 361 | 14 | if (readerfac instanceof XMLReaderSAX2Factory) { |
| 362 | 6 | return ((XMLReaderSAX2Factory) readerfac).getDriverClassName(); |
| 363 | } | |
| 364 | 8 | return null; |
| 365 | } | |
| 366 | ||
| 367 | /** | |
| 368 | * Returns the current {@link org.jdom2.JDOMFactory} in use. | |
| 369 | * | |
| 370 | * @return the factory in use | |
| 371 | * @deprecated as it is replaced by {@link #getJDOMFactory()} | |
| 372 | */ | |
| 373 | @Deprecated | |
| 374 | public JDOMFactory getFactory() { | |
| 375 | 1 | return getJDOMFactory(); |
| 376 | } | |
| 377 | ||
| 378 | /** | |
| 379 | * Returns the current {@link org.jdom2.JDOMFactory} in use. | |
| 380 | * | |
| 381 | * @return the factory in use | |
| 382 | */ | |
| 383 | @Override | |
| 384 | public JDOMFactory getJDOMFactory() { | |
| 385 | 6 | return jdomfac; |
| 386 | } | |
| 387 | ||
| 388 | /** | |
| 389 | * This sets a custom JDOMFactory for the builder. Use this to build the | |
| 390 | * tree with your own subclasses of the JDOM classes. | |
| 391 | * | |
| 392 | * @param factory | |
| 393 | * <code>JDOMFactory</code> to use | |
| 394 | * @deprecated as it is replaced by {@link #setJDOMFactory(JDOMFactory)} | |
| 395 | */ | |
| 396 | @Deprecated | |
| 397 | public void setFactory(final JDOMFactory factory) { | |
| 398 | 1 | setJDOMFactory(factory); |
| 399 | 1 | } |
| 400 | ||
| 401 | /** | |
| 402 | * This sets a custom JDOMFactory for the builder. Use this to build the | |
| 403 | * tree with your own subclasses of the JDOM classes. | |
| 404 | * | |
| 405 | * @param factory | |
| 406 | * <code>JDOMFactory</code> to use | |
| 407 | */ | |
| 408 | public void setJDOMFactory(final JDOMFactory factory) { | |
| 409 | 3 | this.jdomfac = factory; |
| 410 | 3 | engine = null; |
| 411 | 3 | } |
| 412 | ||
| 413 | /** | |
| 414 | * Get the current XMLReader factory. | |
| 415 | * | |
| 416 | * @return the current JDOMXMLReaderFactory | |
| 417 | */ | |
| 418 | public XMLReaderJDOMFactory getXMLReaderFactory() { | |
| 419 | 2 | return readerfac; |
| 420 | } | |
| 421 | ||
| 422 | /** | |
| 423 | * Set the current XMLReader factory. | |
| 424 | * | |
| 425 | * @param rfac | |
| 426 | * the JDOMXMLReaderFactory to set. A null rfac will indicate the | |
| 427 | * default {@link XMLReaders#NONVALIDATING} | |
| 428 | */ | |
| 429 | public void setXMLReaderFactory(final XMLReaderJDOMFactory rfac) { | |
| 430 | 4 | readerfac = rfac == null |
| 431 | ? XMLReaders.NONVALIDATING | |
| 432 | : rfac; | |
| 433 | 4 | engine = null; |
| 434 | 4 | } |
| 435 | ||
| 436 | /** | |
| 437 | * Get the SAXHandlerFactory used to supply SAXHandlers to this SAXBuilder. | |
| 438 | * | |
| 439 | * @return the current SAXHandlerFactory (never null). | |
| 440 | */ | |
| 441 | public SAXHandlerFactory getSAXHandlerFactory() { | |
| 442 | 5 | return handlerfac; |
| 443 | } | |
| 444 | ||
| 445 | /** | |
| 446 | * Set the SAXHandlerFactory to be used by this SAXBuilder. | |
| 447 | * | |
| 448 | * @param factory | |
| 449 | * the required SAXHandlerFactory. A null input factory will request | |
| 450 | * the {@link DefaultSAXHandlerFactory}. | |
| 451 | */ | |
| 452 | public void setSAXHandlerFactory(final SAXHandlerFactory factory) { | |
| 453 | 3 | this.handlerfac = factory == null ? DEFAULTSAXHANDLERFAC : factory; |
| 454 | 3 | engine = null; |
| 455 | 3 | } |
| 456 | ||
| 457 | /** | |
| 458 | * Returns whether validation is to be performed during the build. | |
| 459 | * | |
| 460 | * @return whether validation is to be performed during the build | |
| 461 | * @deprecated in lieu of {@link #isValidating()} | |
| 462 | */ | |
| 463 | @Deprecated | |
| 464 | public boolean getValidation() { | |
| 465 | 5 | return isValidating(); |
| 466 | } | |
| 467 | ||
| 468 | /** | |
| 469 | * Returns whether validation is to be performed during the build. | |
| 470 | * | |
| 471 | * @return whether validation is to be performed during the build | |
| 472 | */ | |
| 473 | @Override | |
| 474 | public boolean isValidating() { | |
| 475 | 29 | return readerfac.isValidating(); |
| 476 | } | |
| 477 | ||
| 478 | /** | |
| 479 | * This sets validation for the builder. | |
| 480 | * <p> | |
| 481 | * <b>Do Not Use</b> | |
| 482 | * <p> | |
| 483 | * JDOM2 introduces the concept of XMLReader factories. The XMLReader is | |
| 484 | * what determines the type of validation. A simple boolean is not enough to | |
| 485 | * indicate what sort of validation is required. The | |
| 486 | * {@link #setXMLReaderFactory(XMLReaderJDOMFactory)} method provides a | |
| 487 | * means to be more specific about validation. | |
| 488 | * <p> | |
| 489 | * For backward compatibility this method has been retained, but its use is | |
| 490 | * discouraged. It does make some logical choices though. The code is | |
| 491 | * equivalent to: | |
| 492 | * <p> | |
| 493 | * | |
| 494 | * <pre> | |
| 495 | * setXMLReaderFactory(XMLReaders.DTDVALIDATING) | |
| 496 | * </pre> | |
| 497 | * | |
| 498 | * for true, and | |
| 499 | * | |
| 500 | * <pre> | |
| 501 | * setXMLReaderFactory(XMLReaders.NONVALIDATING) | |
| 502 | * </pre> | |
| 503 | * | |
| 504 | * for false. | |
| 505 | * | |
| 506 | * @see #setXMLReaderFactory(XMLReaderJDOMFactory) | |
| 507 | * @see XMLReaders#NONVALIDATING | |
| 508 | * @see XMLReaders#DTDVALIDATING | |
| 509 | * @param validate | |
| 510 | * <code>boolean</code> indicating whether validation should occur. | |
| 511 | * @deprecated use {@link #setXMLReaderFactory(XMLReaderJDOMFactory)} | |
| 512 | */ | |
| 513 | @Deprecated | |
| 514 | public void setValidation(final boolean validate) { | |
| 515 | 2 | setXMLReaderFactory(validate |
| 516 | ? XMLReaders.DTDVALIDATING | |
| 517 | : XMLReaders.NONVALIDATING); | |
| 518 | 2 | } |
| 519 | ||
| 520 | /** | |
| 521 | * Returns the {@link ErrorHandler} assigned, or null if none. When the | |
| 522 | * SAXBuilder parses a document it will always have an ErrorHandler but it | |
| 523 | * will be an instance of {@link BuilderErrorHandler} unless you specify a | |
| 524 | * different ErrorHandler in {@link #setErrorHandler(ErrorHandler)}. In | |
| 525 | * other words, a null return value from here indicates a default will be | |
| 526 | * used. | |
| 527 | * | |
| 528 | * @return the ErrorHandler assigned, or null if SAXBuilder will create a | |
| 529 | * default ErrorHandler when needed. | |
| 530 | */ | |
| 531 | @Override | |
| 532 | public ErrorHandler getErrorHandler() { | |
| 533 | 9 | return saxErrorHandler; |
| 534 | } | |
| 535 | ||
| 536 | /** | |
| 537 | * This sets custom ErrorHandler for the Builder. Setting a null value will | |
| 538 | * indicate SAXBuilder should create a default ErrorHandler when needed. | |
| 539 | * | |
| 540 | * @param errorHandler | |
| 541 | * <code>ErrorHandler</code> | |
| 542 | */ | |
| 543 | public void setErrorHandler(final ErrorHandler errorHandler) { | |
| 544 | 1 | saxErrorHandler = errorHandler; |
| 545 | 1 | engine = null; |
| 546 | 1 | } |
| 547 | ||
| 548 | /** | |
| 549 | * Returns the {@link EntityResolver} assigned, or null if none. | |
| 550 | * | |
| 551 | * @return the EntityResolver assigned | |
| 552 | */ | |
| 553 | @Override | |
| 554 | public EntityResolver getEntityResolver() { | |
| 555 | 21 | return saxEntityResolver; |
| 556 | } | |
| 557 | ||
| 558 | /** | |
| 559 | * This sets custom EntityResolver for the <code>Builder</code>. | |
| 560 | * | |
| 561 | * @param entityResolver | |
| 562 | * <code>EntityResolver</code> | |
| 563 | */ | |
| 564 | public void setEntityResolver(final EntityResolver entityResolver) { | |
| 565 | 1 | saxEntityResolver = entityResolver; |
| 566 | 1 | engine = null; |
| 567 | 1 | } |
| 568 | ||
| 569 | /** | |
| 570 | * Returns the {@link DTDHandler} assigned, or null if the assigned | |
| 571 | * {@link SAXHandler} will be used for DTD SAX events. | |
| 572 | * | |
| 573 | * @return the DTDHandler assigned | |
| 574 | */ | |
| 575 | @Override | |
| 576 | public DTDHandler getDTDHandler() { | |
| 577 | 21 | return saxDTDHandler; |
| 578 | } | |
| 579 | ||
| 580 | /** | |
| 581 | * This sets custom DTDHandler for the <code>Builder</code>. Setting a null | |
| 582 | * value indicates that SAXBuilder should use the assigned SAXHandler for | |
| 583 | * DTD processing. | |
| 584 | * | |
| 585 | * @param dtdHandler | |
| 586 | * <code>DTDHandler</code> | |
| 587 | */ | |
| 588 | public void setDTDHandler(final DTDHandler dtdHandler) { | |
| 589 | 1 | saxDTDHandler = dtdHandler; |
| 590 | 1 | engine = null; |
| 591 | 1 | } |
| 592 | ||
| 593 | /** | |
| 594 | * Returns the {@link XMLFilter} used during parsing, or null if none. | |
| 595 | * | |
| 596 | * @return the XMLFilter used during parsing | |
| 597 | */ | |
| 598 | public XMLFilter getXMLFilter() { | |
| 599 | 21 | return saxXMLFilter; |
| 600 | } | |
| 601 | ||
| 602 | /** | |
| 603 | * This sets a custom {@link org.xml.sax.XMLFilter} for the builder. | |
| 604 | * <p> | |
| 605 | * Care should be taken to ensure that the specified xmlFilter is reentrant | |
| 606 | * and thread-safe. | |
| 607 | * <p> | |
| 608 | * SAXBuilder will set this instance as the parent instance for all | |
| 609 | * XMLReaders that may be created, and these may (depending on SAXBuilder | |
| 610 | * usage) be accessed concurrently. It is the responsibility of the JDOM | |
| 611 | * user to ensure that if the XMLFilter is not thread-safe then neither the | |
| 612 | * SAXBuilder nor any of it's SAXEngines are accessed concurrently. | |
| 613 | * | |
| 614 | * @param xmlFilter | |
| 615 | * the XMLFilter to use | |
| 616 | */ | |
| 617 | public void setXMLFilter(final XMLFilter xmlFilter) { | |
| 618 | 1 | saxXMLFilter = xmlFilter; |
| 619 | 1 | engine = null; |
| 620 | 1 | } |
| 621 | ||
| 622 | /** | |
| 623 | * Returns whether element content whitespace is to be ignored during the | |
| 624 | * build. | |
| 625 | * | |
| 626 | * @return whether element content whitespace is to be ignored during the | |
| 627 | * build | |
| 628 | */ | |
| 629 | @Override | |
| 630 | public boolean getIgnoringElementContentWhitespace() { | |
| 631 | 2 | return ignoringWhite; |
| 632 | } | |
| 633 | ||
| 634 | /** | |
| 635 | * Specifies whether or not the parser should eliminate whitespace in | |
| 636 | * element content (sometimes known as "ignorable whitespace") when building | |
| 637 | * the document. Only whitespace which is contained within element content | |
| 638 | * that has an element only content model will be eliminated (see XML Rec | |
| 639 | * 3.2.1). For this setting to take effect requires that validation be | |
| 640 | * turned on. The default value of this setting is <code>false</code>. | |
| 641 | * | |
| 642 | * @param ignoringWhite | |
| 643 | * Whether to ignore ignorable whitespace | |
| 644 | */ | |
| 645 | public void setIgnoringElementContentWhitespace(final boolean ignoringWhite) { | |
| 646 | 2 | this.ignoringWhite = ignoringWhite; |
| 647 | 2 | engine = null; |
| 648 | 2 | } |
| 649 | ||
| 650 | /** | |
| 651 | * Returns whether or not the parser will eliminate element content | |
| 652 | * containing only whitespace. | |
| 653 | * | |
| 654 | * @return <code>boolean</code> - whether only whitespace content will be | |
| 655 | * ignored during build. | |
| 656 | * @see #setIgnoringBoundaryWhitespace | |
| 657 | */ | |
| 658 | @Override | |
| 659 | public boolean getIgnoringBoundaryWhitespace() { | |
| 660 | 2 | return ignoringBoundaryWhite; |
| 661 | } | |
| 662 | ||
| 663 | /** | |
| 664 | * Specifies whether or not the parser should elminate boundary whitespace, | |
| 665 | * a term that indicates whitespace-only text between element tags. This | |
| 666 | * feature is a lot like | |
| 667 | * {@link #setIgnoringElementContentWhitespace(boolean)} but this feature is | |
| 668 | * more aggressive and doesn't require validation be turned on. The | |
| 669 | * {@link #setIgnoringElementContentWhitespace(boolean)} call impacts the | |
| 670 | * SAX parse process while this method impacts the JDOM build process, so it | |
| 671 | * can be beneficial to turn both on for efficiency. For implementation | |
| 672 | * efficiency, this method actually removes all whitespace-only text() | |
| 673 | * nodes. That can, in some cases (like between an element tag and a | |
| 674 | * comment) include whitespace that isn't just boundary whitespace. The | |
| 675 | * default is <code>false</code>. | |
| 676 | * | |
| 677 | * @param ignoringBoundaryWhite | |
| 678 | * Whether to ignore whitespace-only text nodes | |
| 679 | */ | |
| 680 | public void setIgnoringBoundaryWhitespace(final boolean ignoringBoundaryWhite) { | |
| 681 | 2 | this.ignoringBoundaryWhite = ignoringBoundaryWhite; |
| 682 | 2 | engine = null; |
| 683 | 2 | } |
| 684 | ||
| 685 | /** | |
| 686 | * Returns whether or not entities are being expanded into normal text | |
| 687 | * content. | |
| 688 | * | |
| 689 | * @return whether entities are being expanded | |
| 690 | */ | |
| 691 | @Override | |
| 692 | public boolean getExpandEntities() { | |
| 693 | 24 | return expand; |
| 694 | } | |
| 695 | ||
| 696 | /** | |
| 697 | * <p> | |
| 698 | * This sets whether or not to expand entities for the builder. A true means | |
| 699 | * to expand entities as normal content. A false means to leave entities | |
| 700 | * unexpanded as <code>EntityRef</code> objects. The default is true. | |
| 701 | * </p> | |
| 702 | * <p> | |
| 703 | * When this setting is false, the internal DTD subset is retained; when | |
| 704 | * this setting is true, the internal DTD subset is not retained. | |
| 705 | * </p> | |
| 706 | * <p> | |
| 707 | * Note that Xerces (at least up to 1.4.4) has a bug where entities in | |
| 708 | * attribute values will be incorrectly reported if this flag is turned off, | |
| 709 | * resulting in entities appearing within element content. When turning | |
| 710 | * entity expansion off either avoid entities in attribute values, or use | |
| 711 | * another parser like Crimson. | |
| 712 | * http://nagoya.apache.org/bugzilla/show_bug.cgi?id=6111 | |
| 713 | * </p> | |
| 714 | * | |
| 715 | * @param expand | |
| 716 | * <code>boolean</code> indicating whether entity expansion should | |
| 717 | * occur. | |
| 718 | */ | |
| 719 | public void setExpandEntities(final boolean expand) { | |
| 720 | 75 | this.expand = expand; |
| 721 | 75 | engine = null; |
| 722 | 75 | } |
| 723 | ||
| 724 | /** | |
| 725 | * Returns whether the contained SAX parser instance is reused across | |
| 726 | * multiple parses. The default is true. | |
| 727 | * | |
| 728 | * @return whether the contained SAX parser instance is reused across | |
| 729 | * multiple parses | |
| 730 | */ | |
| 731 | public boolean getReuseParser() { | |
| 732 | 2 | return reuseParser; |
| 733 | } | |
| 734 | ||
| 735 | /** | |
| 736 | * Specifies whether this builder will reuse the same SAX parser when | |
| 737 | * performing subsequent parses or allocate a new parser for each parse. The | |
| 738 | * default value of this setting is <code>true</code> (parser reuse). | |
| 739 | * <p> | |
| 740 | * <strong>Note</strong>: SAX parser instances are not thread safe (they are | |
| 741 | * not even reentrant), and nor are SAXBuilder instances. Setting parser | |
| 742 | * reuse does not imply the parser is thread-safe. | |
| 743 | * </p> | |
| 744 | * | |
| 745 | * @param reuseParser | |
| 746 | * Whether to reuse the SAX parser. | |
| 747 | */ | |
| 748 | public void setReuseParser(final boolean reuseParser) { | |
| 749 | 10 | this.reuseParser = reuseParser; |
| 750 | 10 | if (!reuseParser) { |
| 751 | 9 | engine = null; |
| 752 | } | |
| 753 | 10 | } |
| 754 | ||
| 755 | /** | |
| 756 | * Specifies whether this builder will do fast reconfiguration of the | |
| 757 | * underlying SAX parser when reuseParser is true. This improves performance | |
| 758 | * in cases where SAXBuilders are reused and lots of small documents are | |
| 759 | * frequently parsed. This avoids attempting to set features on the SAX | |
| 760 | * parser each time build() is called which result in | |
| 761 | * SaxNotRecognizedExceptions. This should ONLY be set for builders where | |
| 762 | * this specific case is an issue. The default value of this setting is | |
| 763 | * <code>false</code> (no fast reconfiguration). If reuseParser is false, | |
| 764 | * calling this has no effect. | |
| 765 | * | |
| 766 | * @param fastReconfigure | |
| 767 | * Whether to do a fast reconfiguration of the parser | |
| 768 | * @deprecated All reused Parsers are now fast-reconfigured. No need to set | |
| 769 | * it. | |
| 770 | */ | |
| 771 | @Deprecated | |
| 772 | public void setFastReconfigure(final boolean fastReconfigure) { | |
| 773 | // do nothing | |
| 774 | 1 | } |
| 775 | ||
| 776 | /** | |
| 777 | * This sets a feature on the SAX parser. See the SAX documentation for | |
| 778 | * more information. </p> | |
| 779 | * <p> | |
| 780 | * NOTE: SAXBuilder requires that some particular features of the SAX parser | |
| 781 | * be set up in certain ways for it to work properly. The list of such | |
| 782 | * features may change in the future. Therefore, the use of this method may | |
| 783 | * cause parsing to break, and even if it doesn't break anything today it | |
| 784 | * might break parsing in a future JDOM version, because what JDOM parsers | |
| 785 | * require may change over time. Use with caution. | |
| 786 | * </p> | |
| 787 | * JDOM uses {@link XMLReaderJDOMFactory} instances to provide XMLReader | |
| 788 | * instances. If you require special configuration on your XMLReader you | |
| 789 | * should consider extending or implementing an XMLReaderJDOMFactory in the | |
| 790 | * {@link org.jdom2.input.sax} package. | |
| 791 | * | |
| 792 | * @param name | |
| 793 | * The feature name, which is a fully-qualified URI. | |
| 794 | * @param value | |
| 795 | * The requested state of the feature (true or false). | |
| 796 | */ | |
| 797 | public void setFeature(final String name, final boolean value) { | |
| 798 | // Save the specified feature for later. | |
| 799 | 5 | features.put(name, value ? Boolean.TRUE : Boolean.FALSE); |
| 800 | 5 | engine = null; |
| 801 | 5 | } |
| 802 | ||
| 803 | /** | |
| 804 | * This sets a property on the SAX parser. See the SAX documentation for | |
| 805 | * more information. | |
| 806 | * <p> | |
| 807 | * NOTE: SAXBuilder requires that some particular properties of the SAX | |
| 808 | * parser be set up in certain ways for it to work properly. The list of | |
| 809 | * such properties may change in the future. Therefore, the use of this | |
| 810 | * method may cause parsing to break, and even if it doesn't break anything | |
| 811 | * today it might break parsing in a future JDOM version, because what JDOM | |
| 812 | * parsers require may change over time. Use with caution. | |
| 813 | * </p> | |
| 814 | * JDOM uses {@link XMLReaderJDOMFactory} instances to provide XMLReader | |
| 815 | * instances. If you require special configuration on your XMLReader you | |
| 816 | * should consider extending or implementing an XMLReaderJDOMFactory in the | |
| 817 | * {@link org.jdom2.input.sax} package. | |
| 818 | * | |
| 819 | * @param name | |
| 820 | * The property name, which is a fully-qualified URI. | |
| 821 | * @param value | |
| 822 | * The requested value for the property. | |
| 823 | */ | |
| 824 | public void setProperty(final String name, final Object value) { | |
| 825 | // Save the specified property for later. | |
| 826 | 3 | properties.put(name, value); |
| 827 | 3 | engine = null; |
| 828 | 3 | } |
| 829 | ||
| 830 | /** | |
| 831 | * This method builds a new and reusable {@link SAXEngine}. | |
| 832 | * Each time this method is called a new instance of a SAXEngine will be | |
| 833 | * returned. | |
| 834 | * <p> | |
| 835 | * This method is used internally by the various SAXBuilder.build(*) methods | |
| 836 | * (if any configuration has changed) but can also be used as a mechanism | |
| 837 | * for creating SAXEngines to be used in parsing pools or other optimised | |
| 838 | * structures. | |
| 839 | * | |
| 840 | * @return a {@link SAXEngine} representing the current state of the | |
| 841 | * current SAXBuilder settings. | |
| 842 | * @throws JDOMException | |
| 843 | * if there is any problem initialising the engine. | |
| 844 | */ | |
| 845 | public SAXEngine buildEngine() throws JDOMException { | |
| 846 | ||
| 847 | // Create and configure the content handler. | |
| 848 | 156 | final SAXHandler contentHandler = handlerfac.createSAXHandler(jdomfac); |
| 849 | ||
| 850 | 156 | contentHandler.setExpandEntities(expand); |
| 851 | 156 | contentHandler.setIgnoringElementContentWhitespace(ignoringWhite); |
| 852 | 156 | contentHandler.setIgnoringBoundaryWhitespace(ignoringBoundaryWhite); |
| 853 | ||
| 854 | 156 | final XMLReader parser = createParser(); |
| 855 | // Configure parser | |
| 856 | 156 | configureParser(parser, contentHandler); |
| 857 | 156 | final boolean valid = readerfac.isValidating(); |
| 858 | ||
| 859 | 156 | return new SAXBuilderEngine(parser, contentHandler, valid); |
| 860 | } | |
| 861 | ||
| 862 | /** | |
| 863 | * Allow overriding classes access to the Parser before it is used in a | |
| 864 | * SAXBuilderEngine. | |
| 865 | * | |
| 866 | * @return a XMLReader parser. | |
| 867 | * @throws JDOMException | |
| 868 | * if there is a problem | |
| 869 | */ | |
| 870 | protected XMLReader createParser() throws JDOMException { | |
| 871 | 165 | XMLReader parser = readerfac.createXMLReader(); |
| 872 | ||
| 873 | // Install optional filter | |
| 874 | 165 | if (saxXMLFilter != null) { |
| 875 | // Connect filter chain to parser | |
| 876 | 1 | XMLFilter root = saxXMLFilter; |
| 877 | 2 | while (root.getParent() instanceof XMLFilter) { |
| 878 | 1 | root = (XMLFilter) root.getParent(); |
| 879 | } | |
| 880 | 1 | root.setParent(parser); |
| 881 | ||
| 882 | // Read from filter | |
| 883 | 1 | parser = saxXMLFilter; |
| 884 | } | |
| 885 | ||
| 886 | 165 | return parser; |
| 887 | } | |
| 888 | ||
| 889 | /** | |
| 890 | * This method retrieves (or builds) a SAXBuilderEngine that represents the | |
| 891 | * current SAXBuilder state. | |
| 892 | * | |
| 893 | * @return a {@link SAXBuilderEngine} representing the current state of the | |
| 894 | * current SAXBuilder settings. | |
| 895 | * @throws JDOMException | |
| 896 | * if there is any problem initializing the engine. | |
| 897 | */ | |
| 898 | private SAXEngine getEngine() throws JDOMException { | |
| 899 | ||
| 900 | 146 | if (engine != null) { |
| 901 | 8 | return engine; |
| 902 | } | |
| 903 | ||
| 904 | 138 | engine = buildEngine(); |
| 905 | 138 | return engine; |
| 906 | } | |
| 907 | ||
| 908 | /** | |
| 909 | * This configures the XMLReader to be used for reading the XML document. | |
| 910 | * <p> | |
| 911 | * The default implementation sets various options on the given XMLReader, | |
| 912 | * such as validation, DTD resolution, entity handlers, etc., according to | |
| 913 | * the options that were set (e.g. via <code>setEntityResolver</code>) and | |
| 914 | * set various SAX properties and features that are required for JDOM | |
| 915 | * internals. These features may change in future releases, so change this | |
| 916 | * behavior at your own risk. | |
| 917 | * </p> | |
| 918 | * | |
| 919 | * @param parser | |
| 920 | * the XMLReader to configure. | |
| 921 | * @param contentHandler | |
| 922 | * The SAXHandler to use for the XMLReader | |
| 923 | * @throws JDOMException | |
| 924 | * if configuration fails. | |
| 925 | */ | |
| 926 | protected void configureParser(final XMLReader parser, final SAXHandler contentHandler) | |
| 927 | throws JDOMException { | |
| 928 | ||
| 929 | // Setup SAX handlers. | |
| 930 | ||
| 931 | 166 | parser.setContentHandler(contentHandler); |
| 932 | ||
| 933 | 166 | if (saxEntityResolver != null) { |
| 934 | 0 | parser.setEntityResolver(saxEntityResolver); |
| 935 | } | |
| 936 | ||
| 937 | 166 | if (saxDTDHandler != null) { |
| 938 | 0 | parser.setDTDHandler(saxDTDHandler); |
| 939 | } else { | |
| 940 | 166 | parser.setDTDHandler(contentHandler); |
| 941 | } | |
| 942 | ||
| 943 | 166 | if (saxErrorHandler != null) { |
| 944 | 1 | parser.setErrorHandler(saxErrorHandler); |
| 945 | } else { | |
| 946 | 165 | parser.setErrorHandler(new BuilderErrorHandler()); |
| 947 | } | |
| 948 | ||
| 949 | 166 | boolean success = false; |
| 950 | ||
| 951 | try { | |
| 952 | 166 | parser.setProperty(SAX_PROPERTY_LEXICAL_HANDLER, |
| 953 | contentHandler); | |
| 954 | 166 | success = true; |
| 955 | 0 | } catch (final SAXNotSupportedException e) { |
| 956 | // No lexical reporting available | |
| 957 | 0 | } catch (final SAXNotRecognizedException e) { |
| 958 | // No lexical reporting available | |
| 959 | 166 | } |
| 960 | ||
| 961 | // Some parsers use alternate property for lexical handling (grr...) | |
| 962 | 166 | if (!success) { |
| 963 | try { | |
| 964 | 0 | parser.setProperty(SAX_PROPERTY_LEXICAL_HANDLER_ALT, |
| 965 | contentHandler); | |
| 966 | 0 | success = true; |
| 967 | 0 | } catch (final SAXNotSupportedException e) { |
| 968 | // No lexical reporting available | |
| 969 | 0 | } catch (final SAXNotRecognizedException e) { |
| 970 | // No lexical reporting available | |
| 971 | 0 | } |
| 972 | } | |
| 973 | ||
| 974 | // Set any user-specified features on the parser. | |
| 975 | 166 | for (final Map.Entry<String, Boolean> me : features.entrySet()) { |
| 976 | 5 | internalSetFeature(parser, me.getKey(), me.getValue().booleanValue(), me.getKey()); |
| 977 | 5 | } |
| 978 | ||
| 979 | // Set any user-specified properties on the parser. | |
| 980 | 166 | for (final Map.Entry<String, Object> me : properties.entrySet()) { |
| 981 | 2 | internalSetProperty(parser, me.getKey(), me.getValue(), me.getKey()); |
| 982 | 1 | } |
| 983 | ||
| 984 | // Set entity expansion | |
| 985 | // Note SAXHandler can work regardless of how this is set, but when | |
| 986 | // entity expansion it's worth it to try to tell the parser not to | |
| 987 | // even bother with external general entities. | |
| 988 | // Apparently no parsers yet support this feature. | |
| 989 | // XXX It might make sense to setEntityResolver() with a resolver | |
| 990 | // that simply ignores external general entities | |
| 991 | try { | |
| 992 | 165 | if (parser.getFeature(SAX_FEATURE_EXTERNAL_ENT) != expand) { |
| 993 | 33 | parser.setFeature(SAX_FEATURE_EXTERNAL_ENT, expand); |
| 994 | } | |
| 995 | 0 | } catch (final SAXException e) { /* Ignore... */ |
| 996 | 165 | } |
| 997 | ||
| 998 | // Try setting the DeclHandler if entity expansion is off | |
| 999 | 165 | if (!expand) { |
| 1000 | try { | |
| 1001 | 33 | parser.setProperty(SAX_PROPERTY_DECLARATION_HANDLER, |
| 1002 | contentHandler); | |
| 1003 | 33 | success = true; |
| 1004 | 0 | } catch (final SAXNotSupportedException e) { |
| 1005 | // No lexical reporting available | |
| 1006 | 0 | } catch (final SAXNotRecognizedException e) { |
| 1007 | // No lexical reporting available | |
| 1008 | 33 | } |
| 1009 | } | |
| 1010 | ||
| 1011 | 165 | } |
| 1012 | ||
| 1013 | /** | |
| 1014 | * Tries to set a feature on the parser. If the feature cannot be set, | |
| 1015 | * throws a JDOMException describing the problem. | |
| 1016 | */ | |
| 1017 | private void internalSetFeature(final XMLReader parser, final String feature, | |
| 1018 | final boolean value, final String displayName) throws JDOMException { | |
| 1019 | try { | |
| 1020 | 5 | parser.setFeature(feature, value); |
| 1021 | 0 | } catch (final SAXNotSupportedException e) { |
| 1022 | 0 | throw new JDOMException( |
| 1023 | displayName + " feature not supported for SAX driver " + parser.getClass().getName()); | |
| 1024 | 0 | } catch (final SAXNotRecognizedException e) { |
| 1025 | 0 | throw new JDOMException( |
| 1026 | displayName + " feature not recognized for SAX driver " + parser.getClass().getName()); | |
| 1027 | 5 | } |
| 1028 | 5 | } |
| 1029 | ||
| 1030 | /** | |
| 1031 | * <p> | |
| 1032 | * Tries to set a property on the parser. If the property cannot be set, | |
| 1033 | * throws a JDOMException describing the problem. | |
| 1034 | * </p> | |
| 1035 | */ | |
| 1036 | private void internalSetProperty(final XMLReader parser, final String property, | |
| 1037 | final Object value, final String displayName) throws JDOMException { | |
| 1038 | try { | |
| 1039 | 2 | parser.setProperty(property, value); |
| 1040 | 1 | } catch (final SAXNotSupportedException e) { |
| 1041 | 1 | throw new JDOMException( |
| 1042 | displayName + " property not supported for SAX driver " + parser.getClass().getName()); | |
| 1043 | 0 | } catch (final SAXNotRecognizedException e) { |
| 1044 | 0 | throw new JDOMException( |
| 1045 | displayName + " property not recognized for SAX driver " + parser.getClass().getName()); | |
| 1046 | 1 | } |
| 1047 | 1 | } |
| 1048 | ||
| 1049 | /** | |
| 1050 | * This builds a document from the supplied input source. | |
| 1051 | * | |
| 1052 | * @param in | |
| 1053 | * <code>InputSource</code> to read from | |
| 1054 | * @return <code>Document</code> resultant Document object | |
| 1055 | * @throws JDOMException | |
| 1056 | * when errors occur in parsing | |
| 1057 | * @throws IOException | |
| 1058 | * when an I/O error prevents a document from being fully parsed | |
| 1059 | */ | |
| 1060 | @Override | |
| 1061 | public Document build(final InputSource in) | |
| 1062 | throws JDOMException, IOException { | |
| 1063 | ||
| 1064 | try { | |
| 1065 | 4 | return getEngine().build(in); |
| 1066 | } finally { | |
| 1067 | 4 | if (!reuseParser) { |
| 1068 | 2 | engine = null; |
| 1069 | } | |
| 1070 | } | |
| 1071 | ||
| 1072 | } | |
| 1073 | ||
| 1074 | /** | |
| 1075 | * <p> | |
| 1076 | * This builds a document from the supplied input stream. | |
| 1077 | * </p> | |
| 1078 | * | |
| 1079 | * @param in | |
| 1080 | * <code>InputStream</code> to read from | |
| 1081 | * @return <code>Document</code> resultant Document object | |
| 1082 | * @throws JDOMException | |
| 1083 | * when errors occur in parsing | |
| 1084 | * @throws IOException | |
| 1085 | * when an I/O error prevents a document from being fully parsed. | |
| 1086 | */ | |
| 1087 | @Override | |
| 1088 | public Document build(final InputStream in) | |
| 1089 | throws JDOMException, IOException { | |
| 1090 | try { | |
| 1091 | 17 | return getEngine().build(in); |
| 1092 | } finally { | |
| 1093 | 17 | if (!reuseParser) { |
| 1094 | 2 | engine = null; |
| 1095 | } | |
| 1096 | } | |
| 1097 | } | |
| 1098 | ||
| 1099 | /** | |
| 1100 | * <p> | |
| 1101 | * This builds a document from the supplied filename. | |
| 1102 | * </p> | |
| 1103 | * | |
| 1104 | * @param file | |
| 1105 | * <code>File</code> to read from | |
| 1106 | * @return <code>Document</code> resultant Document object | |
| 1107 | * @throws JDOMException | |
| 1108 | * when errors occur in parsing | |
| 1109 | * @throws IOException | |
| 1110 | * when an I/O error prevents a document from being fully parsed | |
| 1111 | */ | |
| 1112 | @Override | |
| 1113 | public Document build(final File file) | |
| 1114 | throws JDOMException, IOException { | |
| 1115 | try { | |
| 1116 | 4 | return getEngine().build(file); |
| 1117 | } finally { | |
| 1118 | 4 | if (!reuseParser) { |
| 1119 | 2 | engine = null; |
| 1120 | } | |
| 1121 | } | |
| 1122 | } | |
| 1123 | ||
| 1124 | /** | |
| 1125 | * <p> | |
| 1126 | * This builds a document from the supplied URL. | |
| 1127 | * </p> | |
| 1128 | * | |
| 1129 | * @param url | |
| 1130 | * <code>URL</code> to read from. | |
| 1131 | * @return <code>Document</code> - resultant Document object. | |
| 1132 | * @throws JDOMException | |
| 1133 | * when errors occur in parsing | |
| 1134 | * @throws IOException | |
| 1135 | * when an I/O error prevents a document from being fully parsed. | |
| 1136 | */ | |
| 1137 | @Override | |
| 1138 | public Document build(final URL url) | |
| 1139 | throws JDOMException, IOException { | |
| 1140 | try { | |
| 1141 | 63 | return getEngine().build(url); |
| 1142 | } finally { | |
| 1143 | 63 | if (!reuseParser) { |
| 1144 | 2 | engine = null; |
| 1145 | } | |
| 1146 | } | |
| 1147 | } | |
| 1148 | ||
| 1149 | /** | |
| 1150 | * <p> | |
| 1151 | * This builds a document from the supplied input stream. | |
| 1152 | * </p> | |
| 1153 | * | |
| 1154 | * @param in | |
| 1155 | * <code>InputStream</code> to read from. | |
| 1156 | * @param systemId | |
| 1157 | * base for resolving relative URIs | |
| 1158 | * @return <code>Document</code> resultant Document object | |
| 1159 | * @throws JDOMException | |
| 1160 | * when errors occur in parsing | |
| 1161 | * @throws IOException | |
| 1162 | * when an I/O error prevents a document from being fully parsed | |
| 1163 | */ | |
| 1164 | @Override | |
| 1165 | public Document build(final InputStream in, final String systemId) | |
| 1166 | throws JDOMException, IOException { | |
| 1167 | try { | |
| 1168 | 4 | return getEngine().build(in, systemId); |
| 1169 | } finally { | |
| 1170 | 4 | if (!reuseParser) { |
| 1171 | 2 | engine = null; |
| 1172 | } | |
| 1173 | } | |
| 1174 | } | |
| 1175 | ||
| 1176 | /** | |
| 1177 | * <p> | |
| 1178 | * This builds a document from the supplied Reader. It's the programmer's | |
| 1179 | * responsibility to make sure the reader matches the encoding of the file. | |
| 1180 | * It's often easier and safer to use an InputStream rather than a Reader, | |
| 1181 | * and to let the parser auto-detect the encoding from the XML declaration. | |
| 1182 | * </p> | |
| 1183 | * | |
| 1184 | * @param characterStream | |
| 1185 | * <code>Reader</code> to read from | |
| 1186 | * @return <code>Document</code> resultant Document object | |
| 1187 | * @throws JDOMException | |
| 1188 | * when errors occur in parsing | |
| 1189 | * @throws IOException | |
| 1190 | * when an I/O error prevents a document from being fully parsed | |
| 1191 | */ | |
| 1192 | @Override | |
| 1193 | public Document build(final Reader characterStream) | |
| 1194 | throws JDOMException, IOException { | |
| 1195 | try { | |
| 1196 | 43 | return getEngine().build(characterStream); |
| 1197 | } finally { | |
| 1198 | 43 | if (!reuseParser) { |
| 1199 | 2 | engine = null; |
| 1200 | } | |
| 1201 | } | |
| 1202 | } | |
| 1203 | ||
| 1204 | /** | |
| 1205 | * <p> | |
| 1206 | * This builds a document from the supplied Reader. It's the programmer's | |
| 1207 | * responsibility to make sure the reader matches the encoding of the file. | |
| 1208 | * It's often easier and safer to use an InputStream rather than a Reader, | |
| 1209 | * and to let the parser auto-detect the encoding from the XML declaration. | |
| 1210 | * </p> | |
| 1211 | * | |
| 1212 | * @param characterStream | |
| 1213 | * <code>Reader</code> to read from. | |
| 1214 | * @param systemId | |
| 1215 | * base for resolving relative URIs | |
| 1216 | * @return <code>Document</code> resultant Document object | |
| 1217 | * @throws JDOMException | |
| 1218 | * when errors occur in parsing | |
| 1219 | * @throws IOException | |
| 1220 | * when an I/O error prevents a document from being fully parsed | |
| 1221 | */ | |
| 1222 | @Override | |
| 1223 | public Document build(final Reader characterStream, final String systemId) | |
| 1224 | throws JDOMException, IOException { | |
| 1225 | ||
| 1226 | try { | |
| 1227 | 4 | return getEngine().build(characterStream, systemId); |
| 1228 | } finally { | |
| 1229 | 4 | if (!reuseParser) { |
| 1230 | 2 | engine = null; |
| 1231 | } | |
| 1232 | } | |
| 1233 | } | |
| 1234 | ||
| 1235 | /** | |
| 1236 | * <p> | |
| 1237 | * This builds a document from the supplied URI. The URI is typically a file name, or a URL. | |
| 1238 | * Do not use this method for parsing XML content that is in a Java String variable. | |
| 1239 | * <p> | |
| 1240 | * <ul> | |
| 1241 | * <li><Strong>Right:</Strong> <code>....build("path/to/file.xml");</code> | |
| 1242 | * <li><Strong>Right:</Strong> <code>....build("http://my.example.com/xmlfile");</code> | |
| 1243 | * <li><Strong>Wrong:</Strong> <code>....build("<root>data</root>");</code> | |
| 1244 | * </ul> | |
| 1245 | * </p> | |
| 1246 | * If your XML content is in a Java String variable and you want to parse it, then use:<br/> | |
| 1247 | * <code> ....build(new StringReader("<root>data</root>"));</code> | |
| 1248 | * <p> | |
| 1249 | * | |
| 1250 | * @param systemId | |
| 1251 | * URI for the input | |
| 1252 | * @return <code>Document</code> resultant Document object | |
| 1253 | * @throws JDOMException | |
| 1254 | * when errors occur in parsing | |
| 1255 | * @throws IOException | |
| 1256 | * when an I/O error prevents a document from being fully parsed | |
| 1257 | */ | |
| 1258 | @Override | |
| 1259 | public Document build(final String systemId) | |
| 1260 | throws JDOMException, IOException { | |
| 1261 | 8 | if (systemId == null) { |
| 1262 | 1 | throw new NullPointerException( |
| 1263 | "Unable to build a URI from a null systemID."); | |
| 1264 | } | |
| 1265 | try { | |
| 1266 | 7 | return getEngine().build(systemId); |
| 1267 | 3 | } catch (IOException ioe) { |
| 1268 | // OK, Issue #63 | |
| 1269 | // it is common for people to pass in raw XML content instead of | |
| 1270 | // a SystemID. To make troubleshooting easier, we do a simple check | |
| 1271 | // all valid XML documents start with a '<' character. | |
| 1272 | // no URI ever has an '<' character. | |
| 1273 | // if we think an XML document was passed in, we wrap the exception | |
| 1274 | // Typically this problem causes a MalformedURLException to be | |
| 1275 | // thrown, but that is not particular specified that way. Of | |
| 1276 | // interest, depending on the broken systemID, you could get a | |
| 1277 | // FileNotFoundException which is also an IOException, which will | |
| 1278 | // also be processed by this handler.... | |
| 1279 | ||
| 1280 | 3 | final int len = systemId.length(); |
| 1281 | 3 | int i = 0; |
| 1282 | 7 | while (i < len && Verifier.isXMLWhitespace(systemId.charAt(i))) { |
| 1283 | 4 | i++; |
| 1284 | } | |
| 1285 | 3 | if (i < len && '<' == systemId.charAt(i)) { |
| 1286 | // our systemID URI has a '<' - this is likely the problem. | |
| 1287 | 2 | MalformedURLException mx = new MalformedURLException( |
| 1288 | "SAXBuilder.build(String) expects the String to be " + | |
| 1289 | "a systemID, but in this instance it appears to be " + | |
| 1290 | "actual XML data."); | |
| 1291 | // include the original problem for accountability, and perhaps | |
| 1292 | // a false positive.... though very unlikely | |
| 1293 | 2 | mx.initCause(ioe); |
| 1294 | 2 | throw mx; |
| 1295 | } | |
| 1296 | // it is likely not an XML document - re-throw the exception | |
| 1297 | 1 | throw ioe; |
| 1298 | } finally { | |
| 1299 | 7 | if (!reuseParser) { |
| 1300 | 2 | engine = null; |
| 1301 | } | |
| 1302 | } | |
| 1303 | } | |
| 1304 | ||
| 1305 | } |