LUCENE-9080: this jflex file got corrupted somehow during previous commit. I regenerated it with ant, along with the final java file. I also added a crlf normalization, encoding and forced-regeneration to ant because it didn't work before.

lucene/analysis/common/build.xml

@@ -41,6 +41,7 @@
 
   <target name="-jflex-HTMLStripCharFilter" depends="-install-jflex,generate-jflex-html-char-entities">
     <run-jflex dir="src/java/org/apache/lucene/analysis/charfilter" name="HTMLStripCharFilter"/>
+    <fixcrlf  file="src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.java" encoding="UTF-8" eol="lf"/>
   </target>
 
   <target name="generate-jflex-html-char-entities">
@@ -51,7 +52,7 @@
       <arg value="-B"/>
       <arg value="htmlentity.py"/>
     </exec>
-    <fixcrlf file="src/java/org/apache/lucene/analysis/charfilter/HTMLCharacterEntities.jflex" encoding="UTF-8"/>
+    <fixcrlf file="src/java/org/apache/lucene/analysis/charfilter/HTMLCharacterEntities.jflex" encoding="UTF-8" eol="lf"/>
   </target>
 
   <target name="-jflex-wiki-tokenizer" depends="-install-jflex">

lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLCharacterEntities.jflex

@@ -60,7 +60,7 @@ CharacterEntities = ( "AElig" | "Aacute" | "Acirc" | "Agrave" | "Alpha"
                     | "times" | "trade" | "uArr" | "uacute" | "uarr" | "ucirc"
                     | "ugrave" | "uml" | "upsih" | "upsilon" | "uuml"
                     | "weierp" | "xi" | "yacute" | "yen" | "yuml" | "zeta"
-('                    | "zwj" | "zwnj"', ')')
+                    | "zwj" | "zwnj" )
 %{
   private static final Map<String,String> upperCaseVariantsAccepted
       = new HashMap<>();

lucene/common-build.xml

@@ -2584,7 +2584,9 @@ The following arguments can be provided to ant to alter its behaviour and target
       <!-- The default skeleton is specified here to work around a JFlex ant task bug:    -->
       <!-- invocations with a non-default skeleton will cause following invocations to    -->
       <!-- use the same skeleton, though not specified, unless the default is configured. -->
+      <delete file="@{dir}/@{name}.java" />
       <jflex file="@{dir}/@{name}.jflex" outdir="@{dir}" nobak="on"
+             encoding="UTF-8"
              skeleton="${common.dir}/core/src/data/jflex/skeleton.default"/>
     </sequential>
   </macrodef>
@@ -2595,6 +2597,7 @@ The following arguments can be provided to ant to alter its behaviour and target
     <sequential>
       <!-- LUCENE-5897: Disallow scanner buffer expansion -->
       <jflex file="@{dir}/@{name}.jflex" outdir="@{dir}" nobak="on"
+             encoding="UTF-8"
              skeleton="${common.dir}/core/src/data/jflex/skeleton.disable.buffer.expansion.txt"/>
       <!-- Since the ZZ_BUFFERSIZE declaration is generated rather than in the skeleton, we have to transform it here. -->
       <replaceregexp file="@{dir}/@{name}.java"