From a8228522a99a02146106672a34c104adbda5c658 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Filip=20Jirs=C3=A1k?= Date: Sat, 11 Apr 2020 19:06:44 +0200 Subject: [PATCH] SAXReader uses system default XMLReader with its defaults. New factory method SAXReader.createDefault() sets more secure defaults. --- src/java/org/dom4j/DocumentHelper.java | 65 +- src/java/org/dom4j/io/SAXHelper.java | 37 +- src/java/org/dom4j/io/SAXReader.java | 1824 ++++++++++--------- 3 files changed, 973 insertions(+), 953 deletions(-) Index: dom4j/src/java/org/dom4j/io/SAXHelper.java =================================================================== --- dom4j.orig/src/java/org/dom4j/io/SAXHelper.java +++ dom4j/src/java/org/dom4j/io/SAXHelper.java @@ -13,6 +13,8 @@ import org.xml.sax.SAXNotSupportedExcept import org.xml.sax.XMLReader; import org.xml.sax.helpers.XMLReaderFactory; +import javax.xml.parsers.SAXParserFactory; + /** *

* SAXHelper contains some helper methods for working with SAX @@ -59,9 +61,18 @@ class SAXHelper { } /** - * Creats a default XMLReader via the org.xml.sax.driver system property or + * Creates a default XMLReader via the org.xml.sax.driver system property or * JAXP if the system property is not set. * + * This method internally calls {@link SAXParserFactory}{@code .newInstance().newSAXParser().getXMLReader()} or {@link XMLReaderFactory#createXMLReader()}. + * Be sure to configure returned reader if the default configuration does not suit you. Consider setting the following properties: + * + * 

+     * reader.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
+     * reader.setFeature("http://xml.org/sax/features/external-general-entities", false);
+     * reader.setFeature("http://xml.org/sax/features/external-parameter-entities", false);
+     *
+ * * @param validating * DOCUMENT ME! * Index: dom4j/src/java/org/dom4j/io/SAXReader.java =================================================================== --- dom4j.orig/src/java/org/dom4j/io/SAXReader.java +++ dom4j/src/java/org/dom4j/io/SAXReader.java @@ -30,6 +30,8 @@ import org.xml.sax.XMLReader; import org.xml.sax.helpers.DefaultHandler; import org.xml.sax.helpers.XMLReaderFactory; +import javax.xml.parsers.SAXParserFactory; + /** *

* SAXReader creates a DOM4J tree from SAX parsing events. @@ -135,17 +137,76 @@ public class SAXReader { /** The SAX filter used to filter SAX events */ private XMLFilter xmlFilter; + public static SAXReader createDefault() { + SAXReader reader = new SAXReader(); + try { + reader.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false); + reader.setFeature("http://xml.org/sax/features/external-general-entities", false); + reader.setFeature("http://xml.org/sax/features/external-parameter-entities", false); + } catch (SAXException e) { + // nothing to do, incompatible reader + } + return reader; + } + + /** + * This method internally calls {@link SAXParserFactory}{@code .newInstance().newSAXParser().getXMLReader()} or {@link XMLReaderFactory#createXMLReader()}. + * Be sure to configure returned reader if the default configuration does not suit you. Consider setting the following properties: + * + * 

+     * reader.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
+     * reader.setFeature("http://xml.org/sax/features/external-general-entities", false);
+     * reader.setFeature("http://xml.org/sax/features/external-parameter-entities", false);
+     *
+ */ public SAXReader() { } + /** + * This method internally calls {@link SAXParserFactory}{@code .newInstance().newSAXParser().getXMLReader()} or {@link XMLReaderFactory#createXMLReader()}. + * Be sure to configure returned reader if the default configuration does not suit you. Consider setting the following properties: + * + * 
+     * reader.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
+     * reader.setFeature("http://xml.org/sax/features/external-general-entities", false);
+     * reader.setFeature("http://xml.org/sax/features/external-parameter-entities", false);
+     *
+ * + * @param validating + */ public SAXReader(boolean validating) { this.validating = validating; } + /** + * This method internally calls {@link SAXParserFactory}{@code .newInstance().newSAXParser().getXMLReader()} or {@link XMLReaderFactory#createXMLReader()}. + * Be sure to configure returned reader if the default configuration does not suit you. Consider setting the following properties: + * + * 
+     * reader.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
+     * reader.setFeature("http://xml.org/sax/features/external-general-entities", false);
+     * reader.setFeature("http://xml.org/sax/features/external-parameter-entities", false);
+     *
+ * + * @param factory + */ public SAXReader(DocumentFactory factory) { this.factory = factory; } + /** + * This method internally calls {@link SAXParserFactory}{@code .newInstance().newSAXParser().getXMLReader()} or {@link XMLReaderFactory#createXMLReader()}. + * Be sure to configure returned reader if the default configuration does not suit you. Consider setting the following properties: + * + * 
+     * reader.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
+     * reader.setFeature("http://xml.org/sax/features/external-general-entities", false);
+     * reader.setFeature("http://xml.org/sax/features/external-parameter-entities", false);
+     *
+ * + * @param factory + * @param validating + */ public SAXReader(DocumentFactory factory, boolean validating) { this.factory = factory; this.validating = validating; @@ -185,14 +246,10 @@ public class SAXReader { * this method is to correctly configure an XMLReader object instance and * call the {@link #setXMLReader(XMLReader)}method * - * @param name - * is the SAX property name - * @param value - * is the value of the SAX property - * - * @throws SAXException - * if the XMLReader could not be created or the property could - * not be changed. + * @param name is the SAX property name + * @param value is the value of the SAX property + * @throws SAXException if the XMLReader could not be created or the property could + * not be changed. */ public void setProperty(String name, Object value) throws SAXException { getXMLReader().setProperty(name, value); @@ -205,14 +262,10 @@ public class SAXReader { * calling this method is to correctly configure an XMLReader object * instance and call the {@link #setXMLReader(XMLReader)}method * - * @param name - * is the SAX feature name - * @param value - * is the value of the SAX feature - * - * @throws SAXException - * if the XMLReader could not be created or the feature could - * not be changed. + * @param name is the SAX feature name + * @param value is the value of the SAX feature + * @throws SAXException if the XMLReader could not be created or the feature could + * not be changed. */ public void setFeature(String name, boolean value) throws SAXException { getXMLReader().setFeature(name, value); @@ -223,13 +276,9 @@ public class SAXReader { * Reads a Document from the given File *

* - * @param file - * is the File to read from. - * + * @param file is the File to read from. * @return the newly created Document instance - * - * @throws DocumentException - * if an error occurs during parsing. + * @throws DocumentException if an error occurs during parsing. */ public Document read(File file) throws DocumentException { try { @@ -272,13 +321,9 @@ public class SAXReader { * Reads a Document from the given URL using SAX *

* - * @param url - * URL to read from. - * + * @param url URL to read from. * @return the newly created Document instance - * - * @throws DocumentException - * if an error occurs during parsing. + * @throws DocumentException if an error occurs during parsing. */ public Document read(URL url) throws DocumentException { String systemID = url.toExternalForm(); @@ -304,13 +349,9 @@ public class SAXReader { * String} to denote the source of the document. *

* - * @param systemId - * is a URL for a document or a file name. - * + * @param systemId is a URL for a document or a file name. * @return the newly created Document instance - * - * @throws DocumentException - * if an error occurs during parsing. + * @throws DocumentException if an error occurs during parsing. */ public Document read(String systemId) throws DocumentException { InputSource source = new InputSource(systemId); @@ -326,13 +367,9 @@ public class SAXReader { * Reads a Document from the given stream using SAX *

* - * @param in - * InputStream to read from. - * + * @param in InputStream to read from. * @return the newly created Document instance - * - * @throws DocumentException - * if an error occurs during parsing. + * @throws DocumentException if an error occurs during parsing. */ public Document read(InputStream in) throws DocumentException { InputSource source = new InputSource(in); @@ -348,13 +385,9 @@ public class SAXReader { * Reads a Document from the given Reader using SAX *

* - * @param reader - * is the reader for the input - * + * @param reader is the reader for the input * @return the newly created Document instance - * - * @throws DocumentException - * if an error occurs during parsing. + * @throws DocumentException if an error occurs during parsing. */ public Document read(Reader reader) throws DocumentException { InputSource source = new InputSource(reader); @@ -370,15 +403,10 @@ public class SAXReader { * Reads a Document from the given stream using SAX *

* - * @param in - * InputStream to read from. - * @param systemId - * is the URI for the input - * + * @param in InputStream to read from. + * @param systemId is the URI for the input * @return the newly created Document instance - * - * @throws DocumentException - * if an error occurs during parsing. + * @throws DocumentException if an error occurs during parsing. */ public Document read(InputStream in, String systemId) throws DocumentException { @@ -396,13 +424,9 @@ public class SAXReader { * Reads a Document from the given Reader using SAX *

* - * @param reader - * is the reader for the input - * @param systemId - * is the URI for the input - * + * @param reader is the reader for the input + * @param systemId is the URI for the input * @return the newly created Document instance - * * @throws DocumentException * if an error occurs during parsing. */ @@ -422,13 +446,9 @@ public class SAXReader { * Reads a Document from the given InputSource using SAX *

* - * @param in - * InputSource to read from. - * + * @param in InputSource to read from. * @return the newly created Document instance - * - * @throws DocumentException - * if an error occurs during parsing. + * @throws DocumentException if an error occurs during parsing. */ public Document read(InputSource in) throws DocumentException { try { @@ -695,8 +715,7 @@ public class SAXReader { /** * Sets the entity resolver used to resolve entities. * - * @param entityResolver - * DOCUMENT ME! + * @param entityResolver DOCUMENT ME! */ public void setEntityResolver(EntityResolver entityResolver) { this.entityResolver = entityResolver; @@ -706,9 +725,7 @@ public class SAXReader { * DOCUMENT ME! * * @return the XMLReader used to parse SAX events - * - * @throws SAXException - * DOCUMENT ME! + * @throws SAXException DOCUMENT ME! */ public XMLReader getXMLReader() throws SAXException { if (xmlReader == null) { @@ -721,8 +738,7 @@ public class SAXReader { /** * Sets the XMLReader used to parse SAX events * - * @param reader - * is the XMLReader to parse SAX events + * @param reader is the XMLReader to parse SAX events */ public void setXMLReader(XMLReader reader) { this.xmlReader = reader; @@ -742,8 +758,7 @@ public class SAXReader { /** * Sets encoding used for InputSource (null means system default encoding) * - * @param encoding - * is encoding used for InputSource + * @param encoding is encoding used for InputSource */ public void setEncoding(String encoding) { this.encoding = encoding; @@ -753,12 +768,9 @@ public class SAXReader { * Sets the class name of the XMLReader to be used to parse * SAX events. * - * @param xmlReaderClassName - * is the class name of the XMLReader to parse SAX - * events - * - * @throws SAXException - * DOCUMENT ME! + * @param xmlReaderClassName is the class name of the XMLReader + * to parse SAX events + * @throws SAXException DOCUMENT ME! */ public void setXMLReaderClassName(String xmlReaderClassName) throws SAXException { @@ -769,11 +781,9 @@ public class SAXReader { * Adds the ElementHandler to be called when the specified * path is encounted. * - * @param path - * is the path to be handled - * @param handler - * is the ElementHandler to be called by the event - * based processor. + * @param path is the path to be handled + * @param handler is the ElementHandler to be called by the event + * based processor. */ public void addHandler(String path, ElementHandler handler) { getDispatchHandler().addHandler(path, handler); @@ -783,8 +793,7 @@ public class SAXReader { * Removes the ElementHandler from the event based processor, * for the specified path. * - * @param path - * is the path to remove the ElementHandler for. + * @param path is the path to remove the ElementHandler for. */ public void removeHandler(String path) { getDispatchHandler().removeHandler(path); @@ -795,9 +804,8 @@ public class SAXReader { * registered, this will set a default ElementHandler to be * called for any path which does NOT have a handler registered. * - * @param handler - * is the ElementHandler to be called by the event - * based processor. + * @param handler is the ElementHandler to be called by the event + * based processor. */ public void setDefaultHandler(ElementHandler handler) { getDispatchHandler().setDefaultHandler(handler); @@ -824,8 +832,7 @@ public class SAXReader { /** * Sets the SAX filter to be used when filtering SAX events * - * @param filter - * is the SAX filter to use or null to disable filtering + * @param filter is the SAX filter to use or null to disable filtering */ public void setXMLFilter(XMLFilter filter) { this.xmlFilter = filter; @@ -838,9 +845,7 @@ public class SAXReader { * Installs any XMLFilter objects required to allow the SAX event stream to * be filtered and preprocessed before it gets to dom4j. * - * @param reader - * DOCUMENT ME! - * + * @param reader DOCUMENT ME! * @return the new XMLFilter if applicable or the original XMLReader if no * filter is being used. */ @@ -886,9 +891,7 @@ public class SAXReader { * XMLReader objects * * @return DOCUMENT ME! - * - * @throws SAXException - * DOCUMENT ME! + * @throws SAXException DOCUMENT ME! */ protected XMLReader createXMLReader() throws SAXException { return SAXHelper.createXMLReader(isValidating()); @@ -897,13 +900,9 @@ public class SAXReader { /** * Configures the XMLReader before use * - * @param reader - * DOCUMENT ME! - * @param handler - * DOCUMENT ME! - * - * @throws DocumentException - * DOCUMENT ME! + * @param reader DOCUMENT ME! + * @param handler DOCUMENT ME! + * @throws DocumentException DOCUMENT ME! */ protected void configureReader(XMLReader reader, DefaultHandler handler) throws DocumentException { @@ -918,10 +917,11 @@ public class SAXReader { SAXHelper.setParserProperty(reader, SAX_DECL_HANDLER, handler); } - // configure namespace support - SAXHelper.setParserFeature(reader, SAX_NAMESPACES, true); + // // configure namespace support + // SAXHelper.setParserFeature(reader, SAX_NAMESPACES, true); - SAXHelper.setParserFeature(reader, SAX_NAMESPACE_PREFIXES, false); + // string interning + // SAXHelper.setParserFeature(reader, SAX_NAMESPACE_PREFIXES, false); // string interning SAXHelper.setParserFeature(reader, SAX_STRING_INTERNING, @@ -936,8 +936,8 @@ public class SAXReader { * includeExternalParameterEntities ); */ // use Locator2 if possible - SAXHelper.setParserFeature(reader, - "http://xml.org/sax/features/use-locator2", true); + // SAXHelper.setParserFeature(reader, + // "http://xml.org/sax/features/use-locator2", true); try { // configure validation support @@ -960,9 +960,7 @@ public class SAXReader { /** * Factory Method to allow user derived SAXContentHandler objects to be used * - * @param reader - * DOCUMENT ME! - * + * @param reader DOCUMENT ME! * @return DOCUMENT ME! */ protected SAXContentHandler createContentHandler(XMLReader reader) {