cleanup, jdoc and replace some call to equalsIgnoreCase with equals

Author: rbri

src/main/java/org/htmlunit/cyberneko/HTMLNamedEntitiesParser.java

@@ -402,7 +402,7 @@ protected void optimize() {
             if (offset_ > 0) {
                 // that is just for later to tell us that we don't understand our
                 // own code anymore and called that incorrectly
-                throw new RuntimeException("Optimiize was called twice");
+                throw new RuntimeException("Optimize was called twice");
             }
 
             // ok, smallest char is the start

src/main/java/org/htmlunit/cyberneko/HTMLScanner.java

@@ -874,7 +874,6 @@ public void setProperty(final String propertyId, final Object value) throws XMLC
      * @throws IOException Thrown on i/o error.
      */
     public void setInputSource(final XMLInputSource source) throws IOException {
-
         // reset state
         fElementCount = 0;
         fElementDepth = -1;
@@ -947,14 +946,15 @@ public void setInputSource(final XMLInputSource source) throws IOException {
 
         // set scanner and state
         if (fFragmentSpecialScannerTag_ != null) {
-            if ("script".equalsIgnoreCase(fFragmentSpecialScannerTag_)) {
+            final String scannerTagLC = fFragmentSpecialScannerTag_.toLowerCase(Locale.ROOT);
+            if ("script".equals(scannerTagLC)) {
                 setScanner(fScriptScanner);
             }
-            else if ("plaintext".equalsIgnoreCase(fFragmentSpecialScannerTag_)) {
+            else if ("plaintext".equals(scannerTagLC)) {
                 setScanner(new PlainTextScanner());
             }
             else {
-                setScanner(fSpecialScanner.setElementName(fFragmentSpecialScannerTag_));
+                setScanner(fSpecialScanner.setElementName(fFragmentSpecialScannerTag_, scannerTagLC));
                 setScannerState(STATE_CONTENT);
             }
 
@@ -2367,7 +2367,7 @@ else if (ename != null) {
                                 final Element elem =
                                         htmlConfiguration_.getHtmlElements().getElementLC(enameLC, null);
                                 if (elem != null && elem.isSpecial()) {
-                                    setScanner(fSpecialScanner.setElementName(ename));
+                                    setScanner(fSpecialScanner.setElementName(ename, enameLC));
                                     setScannerState(STATE_CONTENT);
                                     return SCAN_TRUE;
                                 }
@@ -3436,11 +3436,11 @@ public class SpecialScanner implements Scanner {
         private final XMLString charBuffer_ = new XMLString();
 
         // Sets the element name.
-        public Scanner setElementName(final String ename) {
+        public Scanner setElementName(final String ename, final String enameLC) {
             fElementName = ename;
-            fStyle = "style".equalsIgnoreCase(fElementName);
-            fTextarea = "textarea".equalsIgnoreCase(fElementName);
-            fTitle = "title".equalsIgnoreCase(fElementName);
+            fStyle = "style".equals(enameLC);
+            fTextarea = "textarea".equals(enameLC);
+            fTitle = "title".equals(enameLC);
             return this;
         }
 

src/main/java/org/htmlunit/cyberneko/HTMLTagBalancer.java

@@ -18,6 +18,7 @@
 import java.util.ArrayList;
 import java.util.Iterator;
 import java.util.List;
+import java.util.Locale;
 
 import org.htmlunit.cyberneko.HTMLElements.Element;
 import org.htmlunit.cyberneko.filters.NamespaceBinder;
@@ -352,21 +353,22 @@ public void reset(final XMLComponentManager manager)
             // use indexed loop to avoid Iterator allocation
             for (int i = 0; i < fragmentContextStack_.length; i++) {
                 final QName qname = fragmentContextStack_[i];
-                if ("html".equalsIgnoreCase(qname.getLocalpart())) {
+                final String qnameLocalpartLC = qname.getLocalpart().toLowerCase(Locale.ROOT);
+                if ("html".equals(qnameLocalpartLC)) {
                     fSeenRootElement = true;
                     fSeenRealHtmlElement = true;
                 }
-                else if ("body".equalsIgnoreCase(qname.getLocalpart())) {
+                else if ("body".equals(qnameLocalpartLC)) {
                     fSeenHeadElement = true;
                     fSeenBodyElement = true;
                 }
-                else if ("form".equalsIgnoreCase(qname.getLocalpart())) {
+                else if ("form".equals(qnameLocalpartLC)) {
                     fOpenedForm = true;
                 }
-                else if ("select".equalsIgnoreCase(qname.getLocalpart())) {
+                else if ("select".equals(qnameLocalpartLC)) {
                     fOpenedSelect = true;
                 }
-                else if ("svg".equalsIgnoreCase(qname.getLocalpart())) {
+                else if ("svg".equals(qnameLocalpartLC)) {
                     fOpenedSvg = true;
                 }
             }
@@ -549,7 +551,7 @@ public void endDocument(final Augmentations augs) throws XNIException {
     }
 
     /**
-     * Consume elements that have been buffered, like </body></html> that are first consumed
+     * Consume elements that have been buffered, like &lt;/body&gt;&lt;/html&gt; that are first consumed
      * at the end of document
      */
     private void consumeBufferedEndElements() {

src/main/java/org/htmlunit/cyberneko/LostText.java

@@ -25,6 +25,7 @@
 /**
  * Container for text that should be hold and re-feed later like text before <html> that will be re-feed
  * in <body>
+ *
  * @author Marc Guillemot
  */
 class LostText {

src/main/java/org/htmlunit/cyberneko/util/StringUtils.java

@@ -16,35 +16,48 @@
 package org.htmlunit.cyberneko.util;
 
 /**
- * String utilities class for utility functions not covered by third party libraries.
+ * String utilities class providing utility functions not covered by third party libraries.
+ *
+ * <p>This class contains static utility methods for common string operations used
+ * throughout the HtmlUnit NekoHtml parser.  It focuses on lightweight, performance-oriented
+ * string checks that avoid creating unnecessary String objects or using expensive operations.</p>
  *
  * @author Ronald Brill
  */
 public final class StringUtils {
 
     /**
-     * Disallow instantiation of this class.
+     * Private constructor to prevent instantiation of this utility class.
      */
     private StringUtils() {
-        // Empty.
+        // Empty - utility class should not be instantiated
     }
 
     /**
-     * Returns true if the param is not null and empty. This is different from
-     * org.apache.commons.lang3.StringUtils#isEmpty(CharSequence) because
-     * this returns false if the provided string is null.
+     * Checks if the provided character sequence is not null and has zero length.
+     *
+     * <p>This method differs from {@code org.apache.commons.lang3.StringUtils#isEmpty(CharSequence)}
+     * in that it returns {@code false} if the provided string is {@code null}.</p>
      *
-     * @param s the string to check
-     * @return true if the param is not null and empty
+     * @param s the character sequence to check, may be null
+     * @return {@code true} if the sequence is not null AND has length of zero; {@code false} otherwise
      */
     public static boolean isEmptyString(final CharSequence s) {
         return s != null && s.length() == 0;
     }
 
     /**
-     * @param expected the char that we expect
-     * @param s the string to check
-     * @return true if the provided string has only one char and this matches the expectation
+     * Checks if the provided character sequence consists of exactly one character that matches
+     * the expected character.
+     *
+     * <p>This is an optimized equality check for single-character strings, avoiding the overhead
+     * of full string comparison.  It's particularly useful during HTML parsing when checking for
+     * single-character tokens or delimiters.</p>
+     *
+     * @param expected the character that we expect to match
+     * @param s the character sequence to check, may be null
+     * @return {@code true} if and only if the provided sequence is not null, has exactly one character,
+     *         and that character equals the expected character; {@code false} otherwise
      */
     public static boolean equalsChar(final char expected, final CharSequence s) {
         return s != null && s.length() == 1 && expected == s.charAt(0);

src/main/java/org/htmlunit/cyberneko/xerces/xni/XMLString.java

@@ -399,6 +399,7 @@ public boolean endsWith(final String s) {
      *
      * @deprecated Use the new method {@link #trimToContent(String, String)} instead.
      */
+    @Deprecated
     public XMLString reduceToContent(final String startMarker, final String endMarker) {
         return trimToContent(startMarker, endMarker);
     }