Fix typos (#3166)

**What problem is this PR intended to solve?**
Fix typos found via `codespell -S test,tmp,ports,coverage,googletest -L
te,reencode,ocur` and `typos --format brief`

**Have you included adequate test coverage?**
Existing tests are sufficient.

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

CHANGELOG.md

@@ -2178,7 +2178,7 @@ Repackaging of 1.5.1 with a gemspec that is compatible with older Rubies. [#631,
 * `XML::Node#namespace=` takes nil as a parameter
 * `XML::Node#xpath` returns things other than `NodeSet` objects. [#208]
 * `XSLT::StyleSheet#transform` accepts hashes for parameters. [#223]
-* Psuedo selectors inside `not()` work. [#205]
+* Pseudo selectors inside `not()` work. [#205]
 * `XML::Builder` doesn't break when nodes are unlinked. [#228] (vihai)
 * Encoding can be forced on the SAX parser. [#204] (Eugene Pimenov)
 * `XML::DocumentFragment` uses `XML::Node#parse` to determine children.
@@ -2202,7 +2202,7 @@ Repackaging of 1.5.1 with a gemspec that is compatible with older Rubies. [#631,
 * Added fragment support to `Node#add_child`, `Node#add_next_sibling`, `Node#add_previous_sibling`, and `Node#replace`.
 * `XML::Node#previous_element` implemented
 * Rubinius support
-* Ths CSS selector engine now supports `:has()`
+* The CSS selector engine now supports `:has()`
 * `XML::NodeSet#filter()` was added
 * `XML::Node.next=` and .previous= are aliases for add_next_sibling and add_previous_sibling. [#183]
 

SECURITY.md

@@ -2,7 +2,7 @@
 
 The Nokogiri Core Contributors take security very seriously and investigate all reported vulnerabilities.
 
-If you would like to report a vulnerablity or have a security concern regarding Nokogiri or how Nokogiri is using any of its underlying platform-specific libraries (such as libxml2 or xerces), please [report it via HackerOne](https://hackerone.com/nokogiri/reports/new).
+If you would like to report a vulnerability or have a security concern regarding Nokogiri or how Nokogiri is using any of its underlying platform-specific libraries (such as libxml2 or xerces), please [report it via HackerOne](https://hackerone.com/nokogiri/reports/new).
 
 Your report will be acknowledged within 24 hours, and you'll receive a more detailed response within 72 hours indicating next steps in handling your report.
 

ext/java/nokogiri/Html4Document.java

@@ -30,7 +30,7 @@ public class Html4Document extends XmlDocument
 
   private static final String DEFAULT_CONTENT_TYPE = "html";
   private static final String DEFAULT_PUBLIC_ID = "-//W3C//DTD HTML 4.01//EN";
-  private static final String DEFAULT_SYTEM_ID = "http://www.w3.org/TR/html4/strict.dtd";
+  private static final String DEFAULT_SYSTEM_ID = "http://www.w3.org/TR/html4/strict.dtd";
 
   private String parsed_encoding = null;
 
@@ -88,7 +88,7 @@ public class Html4Document extends XmlDocument
                                        getDocument(),
                                        context.getRuntime().newString(DEFAULT_CONTENT_TYPE),
                                        context.getRuntime().newString(DEFAULT_PUBLIC_ID),
-                                       context.getRuntime().newString(DEFAULT_SYTEM_ID));
+                                       context.getRuntime().newString(DEFAULT_SYSTEM_ID));
       setInternalSubset(internalSubset);
     }
 

ext/java/nokogiri/NokogiriService.java

@@ -37,7 +37,7 @@ public class NokogiriService implements BasicLibraryService
   }
 
   private static Map<String, RubyClass>
-  populateNokogiriClassCahce(Ruby ruby)
+  populateNokogiriClassCache(Ruby ruby)
   {
     Map<String, RubyClass> nokogiriClassCache = new HashMap<String, RubyClass>();
     nokogiriClassCache.put("Nokogiri::HTML4::Document", (RubyClass)ruby.getClassFromPath("Nokogiri::HTML4::Document"));
@@ -91,7 +91,7 @@ public class NokogiriService implements BasicLibraryService
     createDocuments(ruby, xmlModule, htmlModule, xmlNode);
     createSaxModule(ruby, xmlSaxModule, htmlSaxModule);
     createXsltModule(ruby, xsltModule);
-    nokogiri.setInternalVariable("cache", populateNokogiriClassCahce(ruby));
+    nokogiri.setInternalVariable("cache", populateNokogiriClassCache(ruby));
   }
 
   private void

ext/java/nokogiri/XmlNode.java

@@ -287,7 +287,7 @@ public class XmlNode extends RubyObject
    * args but not for an exact number.  Any extra args will then be
    * passed to 'initialize'.  The way 'new' and this 'init' function
    * interact means that subclasses cannot arbitrarily change the
-   * require aruments by defining an 'initialize' method.  This is
+   * require arguments by defining an 'initialize' method.  This is
    * how the C libxml wrapper works also.
    *
    * As written it performs initialization for a new Element with
@@ -407,7 +407,7 @@ public class XmlNode extends RubyObject
   /**
    * This method should be called after a node has been adopted in a new
    * document. This method will ensure that the node is renamed with the
-   * appriopriate NS uri. First the prefix of the node is extracted, then is
+   * appropriate NS uri. First the prefix of the node is extracted, then is
    * used to lookup the namespace uri in the new document starting at the
    * current node and traversing the ancestors. If the namespace uri wasn't
    * empty (or null) all children and the node has attributes and/or children

ext/java/nokogiri/internals/NokogiriBlockingQueueInputStream.java

@@ -87,7 +87,7 @@ public Void call() throws Exception {
 
   /**
    * This method shouldn't be called unless the parser has finished parsing or
-   * threw an exception while doing so, otherwise, there'll be the protential
+   * threw an exception while doing so, otherwise, there'll be the potential
    * that the read method will block indefinitely.
    */
   @Override

ext/java/nokogiri/internals/NokogiriDomParser.java

@@ -66,7 +66,7 @@ public class NokogiriDomParser extends DOMParser
   {
     dtd.reset();
     if (xInclude) {
-      setEntityResolver(new NokogiriXInlcudeEntityResolver(source));
+      setEntityResolver(new NokogiriXIncludeEntityResolver(source));
     }
     super.parse(source);
     Document doc = getDocument();
@@ -77,11 +77,11 @@ public class NokogiriDomParser extends DOMParser
     doc.setUserData(XmlDocument.DTD_RAW_DOCUMENT, dtd.getDocument(), null);
   }
 
-  private static class NokogiriXInlcudeEntityResolver implements org.xml.sax.EntityResolver
+  private static class NokogiriXIncludeEntityResolver implements org.xml.sax.EntityResolver
   {
     InputSource source;
     private
-    NokogiriXInlcudeEntityResolver(InputSource source)
+    NokogiriXIncludeEntityResolver(InputSource source)
     {
       this.source = source;
     }

ext/java/nokogiri/internals/ParserContext.java

@@ -227,9 +227,9 @@ public static class Options
   }
 
   /*
-  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;
       }
 

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

@@ -600,7 +600,7 @@ static class XmlsStackElement
         // 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);

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

@@ -90,7 +90,7 @@ 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();

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

@@ -44,15 +44,15 @@ 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.*/
   private List<SymbMap> level;
   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

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

@@ -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 @@ else if (PROCESSING_INSTRUCTION_NODE == nexttype) {
   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 @@ else if (PROCESSING_INSTRUCTION_NODE == nexttype) {
   /** 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 @@ else if (PROCESSING_INSTRUCTION_NODE == nexttype) {
    *
    * @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 @@ else if (PROCESSING_INSTRUCTION_NODE == nexttype) {
   /**
    * 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,

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

@@ -573,7 +573,7 @@ else if (!getBaseURI().equals(((NodeImpl) arg).getBaseURI())) {
    * <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 @@ else if (!getBaseURI().equals(((NodeImpl) arg).getBaseURI())) {
   public String
   getTextContent() throws DOMException
   {
-    return getNodeValue();  // overriden in some subclasses
+    return getNodeValue();  // overridden in some subclasses
   }
 
   /**

ext/nokogiri/html4_element_description.c

@@ -245,7 +245,7 @@ implied_start_tag_eh(VALUE self)
  * call-seq:
  *  name
  *
- * Get the tag name for this ElemementDescription
+ * Get the tag name for this ElementDescription
  */
 static VALUE
 name(VALUE self)
@@ -261,7 +261,7 @@ name(VALUE self)
  * call-seq:
  *  [](tag_name)
  *
- * Get ElemementDescription for +tag_name+
+ * Get ElementDescription for +tag_name+
  */
 static VALUE
 get_description(VALUE klass, VALUE tag_name)

gumbo-parser/src/nokogiri_gumbo.h

@@ -791,7 +791,7 @@ extern const GumboOptions kGumboDefaultOptions;
  */
 typedef enum {
   /**
-   * Indicates that parsing completed successfuly. The resulting tree
+   * Indicates that parsing completed successfully. The resulting tree
    * will be a complete document.
    */
   GUMBO_STATUS_OK,
@@ -841,7 +841,7 @@ typedef struct GumboInternalOutput {
   GumboVector /* GumboError */ errors;
 
   /**
-   * True if the parser encounted an error.
+   * True if the parser encountered an error.
    *
    * This can be true and `errors` an empty `GumboVector` if the `max_errors`
    * option was set to 0.

gumbo-parser/src/parser.c

@@ -4513,7 +4513,7 @@ static void handle_in_foreign_content(GumboParser* parser, GumboToken* token) {
   if (i == 0)
     return;
   // We can't call handle_token directly because the current node is still in
-  // a foriegn namespace, so it would re-enter this and result in infinite
+  // a foreign namespace, so it would re-enter this and result in infinite
   // recursion.
   handle_html_content(parser, token);
 }

gumbo-parser/src/tokenizer.c

@@ -340,7 +340,7 @@ static void reset_token_start_point(GumboTokenizerState* tokenizer) {
 
 // Sets the tag buffer original text and start point to the current iterator
 // position. This is necessary because attribute names & values may have
-// whitespace preceeding them, and so we can't assume that the actual token
+// whitespace preceding them, and so we can't assume that the actual token
 // starting point was the end of the last tag buffer usage.
 static void reset_tag_buffer_start_point(GumboParser* parser) {
   GumboTokenizerState* tokenizer = parser->_tokenizer_state;

lib/nokogiri/css/parser_extras.rb

@@ -16,7 +16,7 @@ def cache_on?
           !Thread.current[CACHE_SWITCH_NAME]
         end
 
-        # Set a thread-local boolean to turn cacheing on and off. Truthy values turn the cache on, falsey values turn the cache off.
+        # Set a thread-local boolean to turn caching on and off. Truthy values turn the cache on, falsey values turn the cache off.
         def set_cache(value) # rubocop:disable Naming/AccessorMethodName
           Thread.current[CACHE_SWITCH_NAME] = !value
         end

lib/nokogiri/xml.rb

@@ -19,7 +19,7 @@ module XML
     class << self
       ###
       # Parse an XML document using the Nokogiri::XML::Reader API.  See
-      # Nokogiri::XML::Reader for mor information
+      # Nokogiri::XML::Reader for more information
       def Reader(string_or_io, url = nil, encoding = nil, options = ParseOptions::STRICT)
         options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
         yield options if block_given?

lib/nokogiri/xml/node_set.rb

@@ -425,7 +425,7 @@ def reverse
       end
 
       ###
-      # Return a nicely formated string representation
+      # Return a nicely formatted string representation
       def inspect
         "[#{map(&:inspect).join(", ")}]"
       end

test/helper.rb

@@ -154,7 +154,7 @@ def initialize_nokogiri_test_gc_level
           GC.compact
         rescue NotImplementedError
           @@gc_level = "normal"
-          warn("#{__FILE__}:#{__LINE__}: GC compaction not suppport by platform")
+          warn("#{__FILE__}:#{__LINE__}: GC compaction not supported by platform")
         end
       end
     end

test/html4/sax/test_parser.rb

@@ -41,7 +41,7 @@ def test_parse_file_nil_argument
           end
         end
 
-        def test_parse_file_non_existant
+        def test_parse_file_non_existent
           assert_raises(Errno::ENOENT) do
             @parser.parse_file("there_is_no_reasonable_way_this_file_exists")
           end

test/html4/test_comments.rb

@@ -149,7 +149,7 @@ class TestComment < Nokogiri::TestCase
       # https://html.spec.whatwg.org/multipage/parsing.html#parse-error-incorrectly-opened-comment
       #
       # This error occurs if the parser encounters the "<!" code point
-      # sequence that is not immidiately followed by two U+002D (-)
+      # sequence that is not immediately followed by two U+002D (-)
       # code points and that is not the start of a DOCTYPE or a CDATA
       # section. All content that follows the "<!" code point sequence
       # up to a U+003E (>) code point (if present) or to the end of
@@ -248,7 +248,7 @@ class TestComment < Nokogiri::TestCase
       #
       # This error occurs if the parser encounters a nested comment
       # (e.g., <!-- <!-- nested --> -->). Such a comment will be
-      # closed by the first occuring "-->" code point sequence and
+      # closed by the first occurring "-->" code point sequence and
       # everything that follows will be treated as markup.
       describe "nested comment" do
         let(:html) { "<html><body><div id=under-test><!-- outer <!-- inner --><div id=do-i-exist></div>--></div></body></html>" }

test/html4/test_node.rb

@@ -193,7 +193,7 @@ def test_GH_1042
         table = html.xpath("//table")[1]
         trs = table.xpath("tr").drop(1)
 
-        # the jruby inplementation of drop uses dup() on the IRubyObject (which
+        # the jruby implementation of drop uses dup() on the IRubyObject (which
         # is NOT the same dup() method on the ruby Object) which produces a
         # shallow clone. a shallow of valid XMLNode triggers several
         # NullPointerException on inspect() since loads of invariants

test/test_gem_platform.rb

@@ -26,7 +26,7 @@ class TestGemPlatform < Nokogiri::TestCase
   # [1]: https://arstechnica.com/gadgets/2020/06/this-is-apples-roadmap-for-moving-the-first-macs-away-from-intel/
   #
   # There seems to be a lot of uncertainty right now, so I'm writing
-  # some tests to express my expectations, and we're gonig to
+  # some tests to express my expectations, and we're going to
   # conservatively use `x86_64-darwin` as the platform name for the
   # native gem.
   let(:darwin_gem_platform) { Gem::Platform.new("x86_64-darwin") }

test/xml/test_entity_reference.rb

@@ -200,7 +200,7 @@ def setup
         end
         assert_equal(expected, doc.errors.map(&:to_s))
       end
-      # TODO: can we retreive a resource pointing to localhost when NONET is set to true ?
+      # TODO: can we retrieve a resource pointing to localhost when NONET is set to true ?
     end
 
     class TestSaxEntityReference < Nokogiri::SAX::TestCase

test/xml/test_node.rb

@@ -758,7 +758,7 @@ def test_serialize_with_block
           assert_equal(xml.serialize(nil, conf), string)
         end
 
-        def test_hold_refence_to_subnode
+        def test_hold_reference_to_subnode
           doc = Nokogiri::XML(<<~XML)
             <root>
               <a>