nokogiri 1.11.1-java → 1.11.2-java

data/ext/java/nokogiri/internals/ClosedStreamException.java

@@ -1,9 +1,12 @@
 package nokogiri.internals;
 
 @SuppressWarnings("serial")
-public class ClosedStreamException extends Exception {
+public class ClosedStreamException extends Exception
+{
 
-  public ClosedStreamException(String message) {
+  public
+  ClosedStreamException(String message)
+  {
     super(message);
   }
 

data/ext/java/nokogiri/internals/HtmlDomParserContext.java

@@ -17,10 +17,10 @@
  * distribute, sublicense, and/or sell copies of the Software, and to
  * permit persons to whom the Software is furnished to do so, subject to
  * the following conditions:
- * 
+ *
  * The above copyright notice and this permission notice shall be
  * included in all copies or substantial portions of the Software.
- * 
+ *
  * THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
  * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
  * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
@@ -52,6 +52,7 @@ import org.cyberneko.html.filters.DefaultFilter;
 import org.jruby.Ruby;
 import org.jruby.RubyClass;
 import org.jruby.runtime.ThreadContext;
+import org.jruby.runtime.Helpers;
 import org.jruby.runtime.builtin.IRubyObject;
 import org.w3c.dom.Document;
 import org.w3c.dom.NamedNodeMap;
@@ -60,193 +61,223 @@ import org.w3c.dom.NodeList;
 
 /**
  * Parser for HtmlDocument. This class actually parses HtmlDocument using NekoHtml.
- * 
+ *
  * @author sergio
  * @author Patrick Mahoney <pat@polycrystal.org>
  * @author Yoko Harada <yokolet@gmail.com>
  */
-public class HtmlDomParserContext extends XmlDomParserContext {
+public class HtmlDomParserContext extends XmlDomParserContext
+{
 
-    public HtmlDomParserContext(Ruby runtime, IRubyObject options) {
-        this(runtime, runtime.getNil(), options);
-    }
+  public
+  HtmlDomParserContext(Ruby runtime, IRubyObject options)
+  {
+    this(runtime, runtime.getNil(), options);
+  }
 
-    public HtmlDomParserContext(Ruby runtime, IRubyObject encoding, IRubyObject options) {
-        super(runtime, encoding, options);
-        java_encoding = NokogiriHelpers.getValidEncoding(encoding);
-    }
+  public
+  HtmlDomParserContext(Ruby runtime, IRubyObject encoding, IRubyObject options)
+  {
+    super(runtime, encoding, options);
+    java_encoding = NokogiriHelpers.getValidEncoding(encoding);
+  }
 
-    @Override
-    protected void initParser(Ruby runtime) {
-        XMLParserConfiguration config = new HTMLConfiguration();
-        //XMLDocumentFilter removeNSAttrsFilter = new RemoveNSAttrsFilter();
-        XMLDocumentFilter elementValidityCheckFilter = new ElementValidityCheckFilter(errorHandler);
-        //XMLDocumentFilter[] filters = { removeNSAttrsFilter,  elementValidityCheckFilter};
-        XMLDocumentFilter[] filters = { elementValidityCheckFilter};
-
-        config.setErrorHandler(this.errorHandler);
-
-        parser = new NokogiriDomParser(config);
-
-        // see http://nekohtml.sourceforge.net/settings.html for details
-        setProperty("http://cyberneko.org/html/properties/default-encoding", java_encoding);
-        setProperty("http://cyberneko.org/html/properties/names/elems", "lower");
-        setProperty("http://cyberneko.org/html/properties/names/attrs", "lower");
-        setProperty("http://cyberneko.org/html/properties/filters", filters);
-        setFeature("http://cyberneko.org/html/features/report-errors", true);
-        setFeature("http://xml.org/sax/features/namespaces", false);
-    }
-    
-    @Override
-    public void setEncoding(String encoding) {
-        super.setEncoding(encoding);
-    }
+  @Override
+  protected void
+  initParser(Ruby runtime)
+  {
+    XMLParserConfiguration config = new HTMLConfiguration();
+    //XMLDocumentFilter removeNSAttrsFilter = new RemoveNSAttrsFilter();
+    XMLDocumentFilter elementValidityCheckFilter = new ElementValidityCheckFilter(errorHandler);
+    //XMLDocumentFilter[] filters = { removeNSAttrsFilter,  elementValidityCheckFilter};
+    XMLDocumentFilter[] filters = { elementValidityCheckFilter};
 
-    /**
-     * Enable NekoHTML feature for balancing tags in a document fragment.
-     * 
-     * This method is used in XmlNode#in_context method.
-     */
-    public void enableDocumentFragment() {
-        setFeature("http://cyberneko.org/html/features/balance-tags/document-fragment", true);
+    config.setErrorHandler(this.errorHandler);
+
+    parser = new NokogiriDomParser(config);
+
+    // see http://nekohtml.sourceforge.net/settings.html for details
+    setProperty("http://cyberneko.org/html/properties/default-encoding", java_encoding);
+    setProperty("http://cyberneko.org/html/properties/names/elems", "lower");
+    setProperty("http://cyberneko.org/html/properties/names/attrs", "lower");
+    setProperty("http://cyberneko.org/html/properties/filters", filters);
+    setFeature("http://cyberneko.org/html/features/report-errors", true);
+    setFeature("http://xml.org/sax/features/namespaces", false);
+  }
+
+  @Override
+  public void
+  setEncoding(String encoding)
+  {
+    super.setEncoding(encoding);
+  }
+
+  /**
+   * Enable NekoHTML feature for balancing tags in a document fragment.
+   *
+   * This method is used in XmlNode#in_context method.
+   */
+  public void
+  enableDocumentFragment()
+  {
+    setFeature("http://cyberneko.org/html/features/balance-tags/document-fragment", true);
+  }
+
+  @Override
+  public XmlDocument
+  parse(ThreadContext context, RubyClass klass, IRubyObject url)
+  {
+    XmlDocument xmlDoc = super.parse(context, klass, url);
+
+    // let's be consistent in how we handle RECOVER and NORECOVER (a.k.a. STRICT)
+    // https://github.com/sparklemotion/nokogiri/issues/2130
+    if (!options.recover && errorHandler.getErrors().size() > 0) {
+      XmlSyntaxError xmlSyntaxError = XmlSyntaxError.createXMLSyntaxError(context.runtime);
+      String exceptionMsg = String.format("%s: '%s'",
+                                          "Parser without recover option encountered error or warning",
+                                          errorHandler.getErrors().get(0));
+      xmlSyntaxError.setException(new Exception(exceptionMsg));
+      throw xmlSyntaxError.toThrowable();
     }
 
-    @Override
-    public XmlDocument parse(ThreadContext context, RubyClass klass, IRubyObject url) {
-        XmlDocument xmlDoc = super.parse(context, klass, url);
-
-        // let's be consistent in how we handle RECOVER and NORECOVER (a.k.a. STRICT)
-        // https://github.com/sparklemotion/nokogiri/issues/2130
-        if (!options.recover && errorHandler.getErrors().size() > 0) {
-            XmlSyntaxError xmlSyntaxError = XmlSyntaxError.createXMLSyntaxError(context.runtime);
-            String exceptionMsg = String.format("%s: '%s'",
-                                                "Parser without recover option encountered error or warning",
-                                                errorHandler.getErrors().get(0));
-            xmlSyntaxError.setException(new Exception(exceptionMsg));
-            throw xmlSyntaxError.toThrowable();
-        }
+    return xmlDoc;
+  }
 
-        return xmlDoc;
+  @Override
+  protected XmlDocument
+  wrapDocument(ThreadContext context, RubyClass klass, Document document)
+  {
+    HtmlDocument htmlDocument = new HtmlDocument(context.runtime, klass, document);
+    htmlDocument.setDocumentNode(context.runtime, document);
+    Helpers.invoke(context, htmlDocument, "initialize");
+
+    if (ruby_encoding.isNil()) {
+      // ruby_encoding might have detected by HtmlDocument::EncodingReader
+      if (detected_encoding != null && !detected_encoding.isNil()) {
+        ruby_encoding = detected_encoding;
+      } else {
+        // no encoding given & no encoding detected, then try to get it
+        String charset = tryGetCharsetFromHtml5MetaTag(document);
+        ruby_encoding = stringOrNil(context.runtime, charset);
+      }
     }
+    htmlDocument.setEncoding(ruby_encoding);
+    htmlDocument.setParsedEncoding(java_encoding);
+    return htmlDocument;
+  }
 
-    @Override
-    protected XmlDocument wrapDocument(ThreadContext context, RubyClass klass, Document document) {
-        HtmlDocument htmlDocument = new HtmlDocument(context.runtime, klass, document);
-        htmlDocument.setDocumentNode(context.runtime, document);
-        if (ruby_encoding.isNil()) {
-            // ruby_encoding might have detected by HtmlDocument::EncodingReader
-            if (detected_encoding != null && !detected_encoding.isNil()) {
-                ruby_encoding = detected_encoding;
-            } else {
-                // no encoding given & no encoding detected, then try to get it
-                String charset = tryGetCharsetFromHtml5MetaTag(document);
-                ruby_encoding = stringOrNil(context.runtime, charset);
+  // NekoHtml doesn't understand HTML5 meta tag format. This fails to detect charset
+  // from an HTML5 style meta tag. Luckily, the meta tag and charset exists in DOM tree
+  // so, this method attempts to find the charset.
+  private static String
+  tryGetCharsetFromHtml5MetaTag(Document document)
+  {
+    if (!"html".equalsIgnoreCase(document.getDocumentElement().getNodeName())) { return null; }
+    NodeList list = document.getDocumentElement().getChildNodes();
+    Node item;
+    for (int i = 0; i < list.getLength(); i++) {
+      if ("head".equalsIgnoreCase((item = list.item(i)).getNodeName())) {
+        NodeList headers = item.getChildNodes();
+        for (int j = 0; j < headers.getLength(); j++) {
+          if ("meta".equalsIgnoreCase((item = headers.item(j)).getNodeName())) {
+            NamedNodeMap nodeMap = item.getAttributes();
+            for (int k = 0; k < nodeMap.getLength(); k++) {
+              if ("charset".equalsIgnoreCase((item = nodeMap.item(k)).getNodeName())) {
+                return item.getNodeValue();
+              }
             }
+          }
         }
-        htmlDocument.setEncoding(ruby_encoding);
-        htmlDocument.setParsedEncoding(java_encoding);
-        return htmlDocument;
+      }
     }
-    
-    // NekoHtml doesn't understand HTML5 meta tag format. This fails to detect charset
-    // from an HTML5 style meta tag. Luckily, the meta tag and charset exists in DOM tree
-    // so, this method attempts to find the charset.
-    private static String tryGetCharsetFromHtml5MetaTag(Document document) {
-        if (!"html".equalsIgnoreCase(document.getDocumentElement().getNodeName())) return null;
-        NodeList list = document.getDocumentElement().getChildNodes(); Node item;
-        for (int i = 0; i < list.getLength(); i++) {
-            if ("head".equalsIgnoreCase((item = list.item(i)).getNodeName())) {
-                NodeList headers = item.getChildNodes();
-                for (int j = 0; j < headers.getLength(); j++) {
-                    if ("meta".equalsIgnoreCase((item = headers.item(j)).getNodeName())) {
-                        NamedNodeMap nodeMap = item.getAttributes();
-                        for (int k = 0; k < nodeMap.getLength(); k++) {
-                            if ("charset".equalsIgnoreCase((item = nodeMap.item(k)).getNodeName())) {
-                                return item.getNodeValue();
-                            }
-                        }
-                    }
-                }
-            }
+    return null;
+  }
+
+  /**
+   * Filter to strip out attributes that pertain to XML namespaces.
+   */
+  public static class RemoveNSAttrsFilter extends DefaultFilter
+  {
+    @Override
+    public void
+    startElement(QName element, XMLAttributes attrs,
+                 Augmentations augs) throws XNIException
+    {
+      int i;
+      for (i = 0; i < attrs.getLength(); ++i) {
+        if (isNamespace(attrs.getQName(i))) {
+          attrs.removeAttributeAt(i);
+          --i;
         }
-        return null;
+      }
+
+      element.uri = null;
+      super.startElement(element, attrs, augs);
     }
+  }
 
-    /**
-     * Filter to strip out attributes that pertain to XML namespaces.
-     */
-    public static class RemoveNSAttrsFilter extends DefaultFilter {
-        @Override
-        public void startElement(QName element, XMLAttributes attrs,
-                                 Augmentations augs) throws XNIException {
-            int i;
-            for (i = 0; i < attrs.getLength(); ++i) {
-                if (isNamespace(attrs.getQName(i))) {
-                    attrs.removeAttributeAt(i);
-                    --i;
-                }
-            }
+  public static class ElementValidityCheckFilter extends DefaultFilter
+  {
+    private NokogiriErrorHandler errorHandler;
 
-            element.uri = null;
-            super.startElement(element, attrs, augs);
-        }
+    private
+    ElementValidityCheckFilter(NokogiriErrorHandler errorHandler)
+    {
+      this.errorHandler = errorHandler;
     }
-    
-    public static class ElementValidityCheckFilter extends DefaultFilter {
-        private NokogiriErrorHandler errorHandler;
-        
-        private ElementValidityCheckFilter(NokogiriErrorHandler errorHandler) {
-            this.errorHandler = errorHandler;
-        }
-        
-        // element names from xhtml1-strict.dtd
-        private static String[][] element_names = {
-            {"a", "abbr", "acronym", "address", "area"},
-            {"b", "base", "basefont", "bdo", "big", "blockquote", "body", "br", "button"},
-            {"caption", "cite", "code", "col", "colgroup"},
-            {"dd", "del", "dfn", "div", "dl", "dt"},
-            {"em"},
-            {"fieldset", "font", "form", "frame", "frameset"},
-            {}, // g
-            {"h1", "h2", "h3", "h4", "h5", "h6", "head", "hr", "html"},
-            {"i", "iframe", "img", "input", "ins"},
-            {}, // j
-            {"kbd"},
-            {"label", "legend", "li", "link"},
-            {"map", "meta"},
-            {"noframes", "noscript"},
-            {"object", "ol", "optgroup", "option"},
-            {"p", "param", "pre"},
-            {"q"},
-            {}, // r
-            {"s", "samp", "script", "select", "small", "span", "strike", "strong", "style", "sub", "sup"},
-            {"table", "tbody", "td", "textarea", "tfoot", "th", "thead", "title", "tr", "tt"},
-            {"u", "ul"},
-            {"var"},
-            {}, // w
-            {}, // x
-            {}, // y
-            {}  // z
-        };
-        
-        private static boolean isValid(final String name) {
-            int index = name.charAt(0) - 97;
-            if (index >= element_names.length) return false;
-            String[] elementNames = element_names[index];
-            for (int i=0; i<elementNames.length; i++) {
-                if (name.equals(elementNames[i])) {
-                    return true;
-                }
-            }
-            return false;
-        }
-        
-        @Override
-        public void startElement(QName name, XMLAttributes attrs, Augmentations augs) throws XNIException {
-            if (!isValid(name.rawname)) {
-                errorHandler.addError(new Exception("Tag " + name.rawname + " invalid"));
-            }
-            super.startElement(name, attrs, augs);
+
+    // element names from xhtml1-strict.dtd
+    private static String[][] element_names = {
+      {"a", "abbr", "acronym", "address", "area"},
+      {"b", "base", "basefont", "bdo", "big", "blockquote", "body", "br", "button"},
+      {"caption", "cite", "code", "col", "colgroup"},
+      {"dd", "del", "dfn", "div", "dl", "dt"},
+      {"em"},
+      {"fieldset", "font", "form", "frame", "frameset"},
+      {}, // g
+      {"h1", "h2", "h3", "h4", "h5", "h6", "head", "hr", "html"},
+      {"i", "iframe", "img", "input", "ins"},
+      {}, // j
+      {"kbd"},
+      {"label", "legend", "li", "link"},
+      {"map", "meta"},
+      {"noframes", "noscript"},
+      {"object", "ol", "optgroup", "option"},
+      {"p", "param", "pre"},
+      {"q"},
+      {}, // r
+      {"s", "samp", "script", "select", "small", "span", "strike", "strong", "style", "sub", "sup"},
+      {"table", "tbody", "td", "textarea", "tfoot", "th", "thead", "title", "tr", "tt"},
+      {"u", "ul"},
+      {"var"},
+      {}, // w
+      {}, // x
+      {}, // y
+      {}  // z
+    };
+
+    private static boolean
+    isValid(final String name)
+    {
+      int index = name.charAt(0) - 97;
+      if (index >= element_names.length) { return false; }
+      String[] elementNames = element_names[index];
+      for (int i = 0; i < elementNames.length; i++) {
+        if (name.equals(elementNames[i])) {
+          return true;
         }
+      }
+      return false;
+    }
+
+    @Override
+    public void
+    startElement(QName name, XMLAttributes attrs, Augmentations augs) throws XNIException
+    {
+      if (!isValid(name.rawname)) {
+        errorHandler.addError(new Exception("Tag " + name.rawname + " invalid"));
+      }
+      super.startElement(name, attrs, augs);
     }
+  }
 }

data/ext/java/nokogiri/internals/IgnoreSchemaErrorsErrorHandler.java

@@ -4,17 +4,24 @@ import org.xml.sax.ErrorHandler;
 import org.xml.sax.SAXException;
 import org.xml.sax.SAXParseException;
 
-public class IgnoreSchemaErrorsErrorHandler implements ErrorHandler {
+public class IgnoreSchemaErrorsErrorHandler implements ErrorHandler
+{
 
-    @Override
-    public void warning(SAXParseException exception) throws SAXException {
-    }
+  @Override
+  public void
+  warning(SAXParseException exception) throws SAXException
+  {
+  }
 
-    @Override
-    public void error(SAXParseException exception) throws SAXException {
-    }
+  @Override
+  public void
+  error(SAXParseException exception) throws SAXException
+  {
+  }
 
-    @Override
-    public void fatalError(SAXParseException exception) throws SAXException {
-    }
+  @Override
+  public void
+  fatalError(SAXParseException exception) throws SAXException
+  {
+  }
 }