nokogiri 1.16.8-java → 1.17.0-java

data/ext/java/nokogiri/internals/ParserContext.java

@@ -63,7 +63,7 @@ public abstract class ParserContext extends RubyObject
     Ruby ruby = context.getRuntime();
 
     if (!(data.respondsTo("read"))) {
-      throw ruby.newTypeError("must respond to :read");
+      throw ruby.newTypeError("argument expected to respond to :read");
     }
 
     source.setByteStream(new IOInputStream(data));
@@ -80,8 +80,11 @@ public abstract class ParserContext extends RubyObject
 
     Ruby ruby = context.getRuntime();
 
+    if (data.isNil()) {
+      throw ruby.newTypeError("wrong argument type nil (expected String)");
+    }
     if (!(data instanceof RubyString)) {
-      throw ruby.newTypeError("must be kind_of String");
+      throw ruby.newTypeError("wrong argument type " + data.getMetaClass() + " (expected String)");
     }
 
     RubyString stringData = (RubyString) data;
@@ -102,6 +105,33 @@ public abstract class ParserContext extends RubyObject
     source.setEncoding(java_encoding);
   }
 
+  public void
+  setStringInputSourceNoEnc(ThreadContext context, IRubyObject data, IRubyObject url)
+  {
+    source = new InputSource();
+    ParserContext.setUrl(context, source, url);
+
+    Ruby ruby = context.getRuntime();
+
+    if (data.isNil()) {
+      throw ruby.newTypeError("wrong argument type nil (expected String)");
+    }
+    if (!(data instanceof RubyString)) {
+      throw ruby.newTypeError("wrong argument type " + data.getMetaClass() + " (expected String)");
+    }
+
+    RubyString stringData = (RubyString) data;
+
+    ByteList bytes = stringData.getByteList();
+
+    stringDataSize = bytes.length() - bytes.begin();
+    if (stringDataSize == 0) {
+      throw context.runtime.newRuntimeError("input string cannot be empty");
+    }
+    ByteArrayInputStream stream = new ByteArrayInputStream(bytes.unsafeBytes(), bytes.begin(), bytes.length());
+    source.setByteStream(stream);
+  }
+
   public static void
   setUrl(ThreadContext context, InputSource source, IRubyObject url)
   {
@@ -179,23 +209,23 @@ public abstract class ParserContext extends RubyObject
     protected static final long NOCDATA = 16384;
     protected static final long NOXINCNODE = 32768;
 
-    public final boolean strict;
-    public final boolean recover;
-    public final boolean noEnt;
-    public final boolean dtdLoad;
-    public final boolean dtdAttr;
-    public final boolean dtdValid;
-    public final boolean noError;
-    public final boolean noWarning;
-    public final boolean pedantic;
-    public final boolean noBlanks;
-    public final boolean sax1;
-    public final boolean xInclude;
-    public final boolean noNet;
-    public final boolean noDict;
-    public final boolean nsClean;
-    public final boolean noCdata;
-    public final boolean noXIncNode;
+    public boolean strict;
+    public boolean recover;
+    public boolean noEnt;
+    public boolean dtdLoad;
+    public boolean dtdAttr;
+    public boolean dtdValid;
+    public boolean noError;
+    public boolean noWarning;
+    public boolean pedantic;
+    public boolean noBlanks;
+    public boolean sax1;
+    public boolean xInclude;
+    public boolean noNet;
+    public boolean noDict;
+    public boolean nsClean;
+    public boolean noCdata;
+    public boolean noXIncNode;
 
     protected static boolean
     test(long options, long mask)
@@ -227,9 +257,9 @@ public abstract class ParserContext extends RubyObject
   }
 
   /*
-  public static class NokogiriXInlcudeEntityResolver implements org.xml.sax.EntityResolver {
+  public static class NokogiriXIncludeEntityResolver implements org.xml.sax.EntityResolver {
       InputSource source;
-      public NokogiriXInlcudeEntityResolver(InputSource source) {
+      public NokogiriXIncludeEntityResolver(InputSource source) {
           this.source = source;
       }
 

data/ext/java/nokogiri/internals/ReaderNode.java

@@ -557,7 +557,7 @@ public abstract class ReaderNode
     public String
     getString()
     {
-      return value;
+      return encodeJavaString(value).toString();
     }
   }
 

data/ext/java/nokogiri/internals/XmlDomParserContext.java

@@ -91,28 +91,17 @@ public class XmlDomParserContext extends ParserContext
     // Fix for Issue#586.  This limits entity expansion up to 100000 and nodes up to 3000.
     setProperty(SECURITY_MANAGER, new org.apache.xerces.util.SecurityManager());
 
-    if (options.noBlanks) {
-      setFeature(FEATURE_INCLUDE_IGNORABLE_WHITESPACE, false);
-    }
-
-    if (options.recover) {
-      setFeature(CONTINUE_AFTER_FATAL_ERROR, true);
-    }
+    setFeature(FEATURE_INCLUDE_IGNORABLE_WHITESPACE, !options.noBlanks);
+    setFeature(CONTINUE_AFTER_FATAL_ERROR, options.recover);
+    setFeature(FEATURE_VALIDATION, options.dtdValid);
+    setFeature(FEATURE_NOT_EXPAND_ENTITY, !options.noEnt);
 
-    if (options.dtdValid) {
-      setFeature(FEATURE_VALIDATION, true);
-    }
-
-    if (!options.noEnt) {
-      setFeature(FEATURE_NOT_EXPAND_ENTITY, true);
-    }
     // If we turn off loading of external DTDs complete, we don't
-    // getthe publicID.  Instead of turning off completely, we use
+    // get the publicID.  Instead of turning off completely, we use
     // an entity resolver that returns empty documents.
-    if (options.dtdLoad) {
-      setFeature(FEATURE_LOAD_EXTERNAL_DTD, true);
-      setFeature(FEATURE_LOAD_DTD_GRAMMAR, true);
-    }
+    setFeature(FEATURE_LOAD_EXTERNAL_DTD, options.dtdLoad);
+    setFeature(FEATURE_LOAD_DTD_GRAMMAR, options.dtdLoad);
+
     parser.setEntityResolver(new NokogiriEntityResolver(runtime, errorHandler, options));
   }
 

data/ext/java/nokogiri/internals/c14n/Canonicalizer11.java

@@ -600,7 +600,7 @@ public abstract class Canonicalizer11 extends CanonicalizerBase
         // that from the input buffer else if the input buffer consists
         // only of ".." and if the output buffer does not contain only
         // the root slash "/", then move the ".." to the output buffer
-        // else delte it.; otherwise,
+        // else delete it.; otherwise,
       } else if (input.equals(".")) {
         input = "";
         printStep("2D", output, input);

data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315Excl.java

@@ -222,7 +222,7 @@ public abstract class Canonicalizer20010315Excl extends CanonicalizerBase
         if (!XMLNS_URI.equals(attribute.getNamespaceURI())) {
           if (isVisible(attribute) && isOutputElement) {
             // The Element is output element, add the prefix (if used)
-            // to visibyUtilized
+            // to visiblyUtilized
             String prefix = attribute.getPrefix();
             if (prefix != null && !(prefix.equals(XML) || prefix.equals(XMLNS))) {
               visiblyUtilized.add(prefix);

data/ext/java/nokogiri/internals/c14n/CanonicalizerBase.java

@@ -28,7 +28,6 @@ import java.util.Iterator;
 import java.util.List;
 import java.util.ListIterator;
 import java.util.Map;
-import java.util.Set;
 
 import javax.xml.parsers.DocumentBuilder;
 import javax.xml.parsers.DocumentBuilderFactory;
@@ -90,7 +89,7 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
   //private Set<Node> xpathNodeSet;
   /**
    * The node to be skipped/excluded from the DOM tree
-   * in subtree canonicalizations.
+   * in subtree canonicalization.
    */
   private Node excludeNode;
   private OutputStream writer = new ByteArrayOutputStream();
@@ -243,7 +242,7 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
           ns.outputNodePush();
           writer.write('<');
           String name = currentElement.getTagName();
-          UtfHelpper.writeByte(name, writer, cache);
+          UtfHelper.writeByte(name, writer, cache);
 
           Iterator<Attr> attrs = this.handleAttributesSubtree(currentElement, ns);
           if (attrs != null) {
@@ -257,7 +256,7 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
           sibling = currentNode.getFirstChild();
           if (sibling == null) {
             writer.write(END_TAG);
-            UtfHelpper.writeStringToUtf8(name, writer);
+            UtfHelper.writeStringToUtf8(name, writer);
             writer.write('>');
             //We finished with this level, pop to the previous definitions.
             ns.outputNodePop();
@@ -274,7 +273,7 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
       }
       while (sibling == null && parentNode != null) {
         writer.write(END_TAG);
-        UtfHelpper.writeByte(((Element)parentNode).getTagName(), writer, cache);
+        UtfHelper.writeByte(((Element)parentNode).getTagName(), writer, cache);
         writer.write('>');
         //We finished with this level, pop to the previous definitions.
         ns.outputNodePop();
@@ -467,7 +466,7 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
   ) throws IOException
   {
     writer.write(' ');
-    UtfHelpper.writeByte(name, writer, cache);
+    UtfHelper.writeByte(name, writer, cache);
     writer.write(equalsStr);
     byte[] toWrite;
     final int length = value.length();
@@ -505,7 +504,7 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
           if (c < 0x80) {
             writer.write(c);
           } else {
-            UtfHelpper.writeCharToUtf8(c, writer);
+            UtfHelper.writeCharToUtf8(c, writer);
           }
           continue;
       }
@@ -543,7 +542,7 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
         if (c < 0x80) {
           writer.write(c);
         } else {
-          UtfHelpper.writeCharToUtf8(c, writer);
+          UtfHelper.writeCharToUtf8(c, writer);
         }
       }
     }
@@ -560,7 +559,7 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
         if (c == 0x0D) {
           writer.write(XD);
         } else {
-          UtfHelpper.writeCharToUtf8(c, writer);
+          UtfHelper.writeCharToUtf8(c, writer);
         }
       }
     }
@@ -599,7 +598,7 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
         if (c < 0x80) {
           writer.write(c);
         } else {
-          UtfHelpper.writeCharToUtf8(c, writer);
+          UtfHelper.writeCharToUtf8(c, writer);
         }
       }
     }
@@ -649,7 +648,7 @@ public abstract class CanonicalizerBase extends CanonicalizerSpi
           if (c < 0x80) {
             writer.write(c);
           } else {
-            UtfHelpper.writeCharToUtf8(c, writer);
+            UtfHelper.writeCharToUtf8(c, writer);
           }
           continue;
       }

data/ext/java/nokogiri/internals/c14n/NameSpaceSymbTable.java

@@ -44,7 +44,7 @@ public class NameSpaceSymbTable
     initialMap.put(XMLNS, ne);
   }
 
-  /**The map betwen prefix-> entry table. */
+  /**The map between prefix-> entry table. */
   private SymbMap symb;
 
   /**The stacks for removing the definitions when doing pop.*/
@@ -52,7 +52,7 @@ public class NameSpaceSymbTable
   private boolean cloned = true;
 
   /**
-   * Default constractor
+   * Default constructor
    **/
   public
   NameSpaceSymbTable()
@@ -173,14 +173,14 @@ public class NameSpaceSymbTable
     symb.put(prefix, entry);
     entry.rendered = true;
     entry.lastrendered = entry.uri;
-    // Return the node for outputing.
+    // Return the node for outputting.
     return entry.n;
   }
 
   /**
    * Gets a definition without mark it as render.
    * For render in exclusive c14n the namespaces in the include prefixes.
-   * @param prefix The prefix whose definition is neaded.
+   * @param prefix The prefix whose definition is needed.
    * @return the attr to render, null if there is no need to render
    **/
   public Attr
@@ -217,7 +217,7 @@ public class NameSpaceSymbTable
     symb.put(prefix, ne);
     if (ob != null) {
       //We have a previous definition store it for the pop.
-      //Check if a previous definition(not the inmidiatly one) has been rendered.
+      //Check if a previous definition(not the immediate one) has been rendered.
       ne.lastrendered = ob.lastrendered;
       if ((ob.lastrendered != null) && (ob.lastrendered.equals(uri))) {
         //Yes it is. Mark as rendered.

data/ext/java/nokogiri/internals/c14n/{UtfHelpper.java → UtfHelper.java}

@@ -22,11 +22,11 @@ import java.io.IOException;
 import java.io.OutputStream;
 import java.util.Map;
 
-public final class UtfHelpper
+public final class UtfHelper
 {
 
   private
-  UtfHelpper()
+  UtfHelper()
   {
     // complete
   }

data/ext/java/nokogiri/internals/dom2dtm/DOM2DTM.java

@@ -51,7 +51,7 @@ import org.xml.sax.ContentHandler;
  * Note that it doesn't necessarily represent a full Document
  * tree. You can wrap a DOM2DTM around a specific node and its subtree
  * and the right things should happen. (I don't _think_ we currently
- * support DocumentFrgment nodes as roots, though that might be worth
+ * support DocumentFragment nodes as roots, though that might be worth
  * considering.)
  *
  * Note too that we do not currently attempt to track document
@@ -63,7 +63,7 @@ public class DOM2DTM extends DTMDefaultBaseIterators
 //    static final boolean JJK_DEBUG=false;
 //    static final boolean JJK_NEWCODE=true;
 
-  /** Manefest constant
+  /** Manifest constant
    */
   static final String NAMESPACE_DECL_NS = "http://www.w3.org/XML/1998/namespace";
 
@@ -330,7 +330,7 @@ public class DOM2DTM extends DTMDefaultBaseIterators
     }
 
     // %REVIEW% Is this local copy Really Useful from a performance
-    // point of view?  Or is this a false microoptimization?
+    // point of view?  Or is this a false micro-optimization?
     Node pos = m_pos;
     Node next = null;
     int nexttype = NULL;
@@ -453,7 +453,7 @@ public class DOM2DTM extends DTMDefaultBaseIterators
     // sequence. The lastTextNode value will be set to the last node in the
     // contiguous sequence, and -- AFTER the DTM addNode -- can be used to
     // advance next over this whole block. Should be simpler than special-casing
-    // the above loop for "Was the logically-preceeding sibling a text node".
+    // the above loop for "Was the logically-preceding sibling a text node".
     //
     // Finally, a DTM node should be considered a CDATASection only if all the
     // contiguous text it covers is CDATASections. The first Text should
@@ -1188,7 +1188,7 @@ public class DOM2DTM extends DTMDefaultBaseIterators
   getNodeValue(int nodeHandle)
   {
     // The _type(nodeHandle) call was taking the lion's share of our
-    // time, and was wrong anyway since it wasn't coverting handle to
+    // time, and was wrong anyway since it wasn't converting handle to
     // identity. Inlined it.
     int type = _exptype(makeNodeIdentity(nodeHandle));
     type = (NULL != type) ? getNodeType(nodeHandle) : NULL;
@@ -1436,7 +1436,7 @@ public class DOM2DTM extends DTMDefaultBaseIterators
   /** Bind an IncrementalSAXSource to this DTM. NOT RELEVANT for DOM2DTM, since
    * we're wrapped around an existing DOM.
    *
-   * @param source The IncrementalSAXSource that we want to recieve events from
+   * @param source The IncrementalSAXSource that we want to receive events from
    * on demand.
    */
   public void
@@ -1450,7 +1450,7 @@ public class DOM2DTM extends DTMDefaultBaseIterators
    *
    * @return null if this model doesn't respond to SAX events,
    * "this" if the DTM object has a built-in SAX ContentHandler,
-   * the IncrmentalSAXSource if we're bound to one and should receive
+   * the IncrementalSAXSource if we're bound to one and should receive
    * the SAX stream via it for incremental build purposes...
    * */
   public org.xml.sax.ContentHandler
@@ -1462,7 +1462,7 @@ public class DOM2DTM extends DTMDefaultBaseIterators
   /**
    * Return this DTM's lexical handler.
    *
-   * %REVIEW% Should this return null if constrution already done/begun?
+   * %REVIEW% Should this return null if construction already done/begun?
    *
    * @return null if this model doesn't respond to lexical SAX events,
    * "this" if the DTM object has a built-in SAX ContentHandler,

data/ext/java/nokogiri/internals/dom2dtm/DOM2DTMdefaultNamespaceDeclarationNode.java

@@ -573,7 +573,7 @@ public class DOM2DTMdefaultNamespaceDeclarationNode implements Attr, TypeInfo
    * <code>Node</code> references returned by the implementation reference
    * the same object. When two <code>Node</code> references are references
    * to the same object, even if through a proxy, the references may be
-   * used completely interchangably, such that all attributes have the
+   * used completely interchangeably, such that all attributes have the
    * same values and calling the same DOM method on either reference
    * always has exactly the same effect.
    * @param other The node to test against.
@@ -688,7 +688,7 @@ public class DOM2DTMdefaultNamespaceDeclarationNode implements Attr, TypeInfo
   public String
   getTextContent() throws DOMException
   {
-    return getNodeValue();  // overriden in some subclasses
+    return getNodeValue();  // overridden in some subclasses
   }
 
   /**