Typo fixes (#3194)

**What problem is this PR intended to solve?**

Fix various typos - some found via `codespell` and `typos` CLI (h/t
@kianmeng with PR #3166)

**Have you included adequate test coverage?**

This PR does not change test coverage - existing tests should suffice.

**Does this change affect the behavior of either the C or the Java
implementations?**

This PR does not introduce any changes in behavior.

CHANGELOG.md

@@ -1509,7 +1509,7 @@ Several changes were made to improve performance:
 * [JRuby] fix slow add_child [#692]
 * [JRuby] fix load errors when deploying to JRuby/Torquebox [#1114] (@atambo and @jvshahid)
 * [JRuby] fix NPE when inspecting nodes returned by `NodeSet#drop` [#1042] (@mkristian)
-* [JRuby] fix nil attriubte node's namespace in reader [#1327] (@codekitchen)
+* [JRuby] fix nil attribute node's namespace in reader [#1327] (@codekitchen)
 * [JRuby] fix Nokogiri munging unicode characters that require more than 2 bytes [#1113] (@mkristian)
 * [JRuby] allow unlinking an unparented node (#1112, #1152) (@esse)
 * [JRuby] allow Fragment parsing on a frozen string (#444, #1077)

ext/java/nokogiri/Html4Document.java

@@ -132,7 +132,7 @@ public class Html4Document extends XmlDocument
   }
 
   public String
-  getPraedEncoding()
+  getParsedEncoding()
   {
     return parsed_encoding;
   }

ext/java/nokogiri/XmlDocumentFragment.java

@@ -62,7 +62,7 @@ public class XmlDocumentFragment extends XmlNode
 
     XmlDocument doc = (XmlDocument) args[0];
 
-    // make wellformed fragment, ignore invalid namespace, or add appropriate namespace to parse
+    // make well-formed fragment, ignore invalid namespace, or add appropriate namespace to parse
     if (args.length > 1 && args[1] instanceof RubyString) {
       final RubyString arg1 = (RubyString) args[1];
       if (XmlDocumentFragment.isTag(arg1)) {

ext/java/nokogiri/XmlDtd.java

@@ -141,7 +141,7 @@ public class XmlDtd extends XmlNode
    *
    * NekoDTD parser returns a new document node containing elements
    * representing the dtd declarations. The plan is to get the root
-   * element and adopt it into the correct document, stipping the
+   * element and adopt it into the correct document, stripping the
    * Document provided by NekoDTD.
    *
    */
@@ -454,7 +454,7 @@ public class XmlDtd extends XmlNode
    * This recursive function will not descend into an
    * 'externalSubset' node, thus for an internal subset it only
    * extracts nodes in the internal subset, and for an external
-   * subset it extracts everything and assumess <code>node</code>
+   * subset it extracts everything and assumes <code>node</code>
    * and all children are part of the external subset.
    */
   protected IRubyObject[]

ext/java/nokogiri/internals/NokogiriHelpers.java

@@ -724,7 +724,7 @@ public class NokogiriHelpers
   convertEncodingByNKFIfNecessary(ThreadContext context, XmlDocument doc, CharSequence str)
   {
     if (!(doc instanceof Html4Document)) { return str; }
-    String parsed_encoding = ((Html4Document)doc).getPraedEncoding();
+    String parsed_encoding = ((Html4Document)doc).getParsedEncoding();
     if (parsed_encoding == null) { return str; }
     String ruby_encoding = rubyStringToString(doc.getEncoding());
     if (ruby_encoding == null) { return str; }

ext/java/nokogiri/internals/XmlDomParserContext.java

@@ -107,7 +107,7 @@ public class XmlDomParserContext extends ParserContext
       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);

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);

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

@@ -28,7 +28,6 @@
 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;
@@ -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 @@ abstract Iterator<Attr> handleAttributesSubtree(Element element, NameSpaceSymbTa
   ) 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 @@ abstract Iterator<Attr> handleAttributesSubtree(Element element, NameSpaceSymbTa
           if (c < 0x80) {
             writer.write(c);
           } else {
-            UtfHelpper.writeCharToUtf8(c, writer);
+            UtfHelper.writeCharToUtf8(c, writer);
           }
           continue;
       }
@@ -543,7 +542,7 @@ abstract Iterator<Attr> handleAttributesSubtree(Element element, NameSpaceSymbTa
         if (c < 0x80) {
           writer.write(c);
         } else {
-          UtfHelpper.writeCharToUtf8(c, writer);
+          UtfHelper.writeCharToUtf8(c, writer);
         }
       }
     }
@@ -560,7 +559,7 @@ abstract Iterator<Attr> handleAttributesSubtree(Element element, NameSpaceSymbTa
         if (c == 0x0D) {
           writer.write(XD);
         } else {
-          UtfHelpper.writeCharToUtf8(c, writer);
+          UtfHelper.writeCharToUtf8(c, writer);
         }
       }
     }
@@ -599,7 +598,7 @@ abstract Iterator<Attr> handleAttributesSubtree(Element element, NameSpaceSymbTa
         if (c < 0x80) {
           writer.write(c);
         } else {
-          UtfHelpper.writeCharToUtf8(c, writer);
+          UtfHelper.writeCharToUtf8(c, writer);
         }
       }
     }
@@ -649,7 +648,7 @@ abstract Iterator<Attr> handleAttributesSubtree(Element element, NameSpaceSymbTa
           if (c < 0x80) {
             writer.write(c);
           } else {
-            UtfHelpper.writeCharToUtf8(c, writer);
+            UtfHelper.writeCharToUtf8(c, writer);
           }
           continue;
       }

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

@@ -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.

ext/java/nokogiri/internals/c14n/UtfHelpper.java → ext/java/nokogiri/internals/c14n/UtfHelper.java

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

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

@@ -51,7 +51,7 @@
  * 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;

gumbo-parser/src/tokenizer.c

@@ -569,17 +569,17 @@ static StateResult emit_from_mark(GumboParser* parser, GumboToken* output) {
 }
 
 // Appends a codepoint to the current tag buffer. If
-// reinitilize_position_on_first is set, this also initializes the tag buffer
+// reinitialize_position_on_first is set, this also initializes the tag buffer
 // start point; the only time you would *not* want to pass true for this
 // parameter is if you want the original_text to include character (like an
 // opening quote) that doesn't appear in the value.
 static void append_char_to_tag_buffer (
   GumboParser* parser,
   int codepoint,
-  bool reinitilize_position_on_first
+  bool reinitialize_position_on_first
 ) {
   GumboStringBuffer* buffer = &parser->_tokenizer_state->_tag_state._buffer;
-  if (buffer->length == 0 && reinitilize_position_on_first) {
+  if (buffer->length == 0 && reinitialize_position_on_first) {
     reset_tag_buffer_start_point(parser);
   }
   gumbo_string_buffer_append_codepoint(codepoint, buffer);
@@ -589,10 +589,10 @@ static void append_char_to_tag_buffer (
 static void append_string_to_tag_buffer (
   GumboParser* parser,
   GumboStringPiece* str,
-  bool reinitilize_position_on_first
+  bool reinitialize_position_on_first
 ) {
   GumboStringBuffer* buffer = &parser->_tokenizer_state->_tag_state._buffer;
-  if (buffer->length == 0 && reinitilize_position_on_first) {
+  if (buffer->length == 0 && reinitialize_position_on_first) {
     reset_tag_buffer_start_point(parser);
   }
   gumbo_string_buffer_append_string(str, buffer);

lib/nokogiri/xml/document.rb

@@ -403,7 +403,7 @@ def decorate(node)
         @decorators.each do |klass, list|
           next unless node.is_a?(klass)
 
-          list.each { |moodule| node.extend(moodule) }
+          list.each { |mod| node.extend(mod) }
         end
       end
 

nokogiri.gemspec

@@ -141,7 +141,7 @@ Gem::Specification.new do |spec|
     "ext/java/nokogiri/internals/c14n/InvalidCanonicalizerException.java",
     "ext/java/nokogiri/internals/c14n/NameSpaceSymbTable.java",
     "ext/java/nokogiri/internals/c14n/NodeFilter.java",
-    "ext/java/nokogiri/internals/c14n/UtfHelpper.java",
+    "ext/java/nokogiri/internals/c14n/UtfHelper.java",
     "ext/java/nokogiri/internals/c14n/XMLUtils.java",
     "ext/java/nokogiri/internals/dom2dtm/DOM2DTM.java",
     "ext/java/nokogiri/internals/dom2dtm/DOM2DTMdefaultNamespaceDeclarationNode.java",

test/html5/test_encoding.rb

@@ -112,7 +112,7 @@ def test_charset_sniff_to_html
   # I'm happy to change them. I'm just pasting them in here so I'm pretty sure
   # the right-to-left languages are backward. Corrections welcome.
   ENCODINGS = [
-    ["UTF-8",          "Let's concatentate all of these for UTF-8"], # English
+    ["UTF-8",          "Let's concatenate all of these for UTF-8"], # English
     ["IBM866",         "А дело бывало -- и коза волка съедала"], # Russian
     ["ISO-8859-2",     "Co můžeš udělat dnes, neodkládej na zítřek."], # Czech
     ["ISO-8859-3",     "Yukarda mavi gök, asağıda yağız yer yaratıldıkta"], # Turkish

test/test_xslt_transforms.rb

@@ -225,7 +225,7 @@ def test_exslt
         check_params(result_doc, params)
       end
 
-      def test_xslt_paramaters
+      def test_xslt_parameters
         # see http://yokolet.blogspot.com/2010/10/pure-java-nokogiri-xslt-extension.html")
         skip_unless_libxml2("cannot get it working on JRuby")