From b07649d05102f1478d54ce22f96e8cdb02dea6d3 Mon Sep 17 00:00:00 2001
From: piyush kumar sadangi <piyushkumarsadangi@MacBook-Air.local>
Date: Fri, 11 Oct 2024 07:28:19 +0530
Subject: [PATCH 1/2] Issue #141: Some config results in OOM, reduce list of
 project in config

---
 .../example/extractor/ConfigSerializer.java   | 69 ++++++++++++++++++-
 1 file changed, 67 insertions(+), 2 deletions(-)

diff --git a/extractor/src/main/java/com/example/extractor/ConfigSerializer.java b/extractor/src/main/java/com/example/extractor/ConfigSerializer.java
index e8e8c68cf..770fd98be 100644
--- a/extractor/src/main/java/com/example/extractor/ConfigSerializer.java
+++ b/extractor/src/main/java/com/example/extractor/ConfigSerializer.java
@@ -476,8 +476,73 @@ private static void appendProperty(final StringBuilder builder, final String ind
         if (builder.length() > 0) {
             builder.append('\n');
         }
-        builder.append(indent).append("<property name=\"").append(name)
-                .append("\" value=\"").append(value).append("\"/>");
+
+        // Check for quotes in the original, unescaped value
+        final boolean containsDoubleQuote = value.contains("\"");
+        final boolean containsSingleQuote = value.contains("'");
+
+        // Determine the appropriate quote character
+        final char quote;
+        if (containsDoubleQuote && !containsSingleQuote) {
+            // Use single quotes as delimiters
+            quote = '\'';
+        }
+        else {
+            // Use double quotes as delimiters in all other cases
+            quote = '"';
+        }
+
+        // Escape the value based on the selected quote character
+        final String escapedValue = escapeXmlAttributeValue(value, quote);
+
+        // Append the property to the builder
+        builder.append(indent)
+                .append("<property name=\"")
+                .append(escapeXml(name))
+                .append("\" value=")
+                .append(quote)
+                .append(escapedValue)
+                .append(quote)
+                .append("/>");
+    }
+
+    /**
+     * Escapes special XML characters in the input string.
+     * Replaces &, <, >, ", and ' with their corresponding XML entities.
+     * Returns the original input if null or empty.
+     *
+     * @param input the string to escape
+     * @return the escaped string or the original if null/empty
+     */
+    private static String escapeXml(final String input) {
+        String result = input;
+        if (input != null && !input.isEmpty()) {
+            result = input.replace("\"", "&quot;")
+                    .replace("'", "&apos;");
+        }
+        return result;
+    }
+
+    /**
+     * Escapes special characters in an XML attribute value.
+     * Replaces &, <, > with their corresponding XML entities.
+     * Depending on the delimiter, either ' or " is also escaped.
+     *
+     * @param input     the string to escape
+     * @param delimiter the delimiter used for the attribute (' or ")
+     * @return the escaped string or the original if null/empty
+     */
+    private static String escapeXmlAttributeValue(final String input, final char delimiter) {
+        String result = input;
+        if (input != null && !input.isEmpty()) {
+            if (delimiter == '\'') {
+                result = result.replace("'", "&apos;");
+            }
+            else {
+                result = result.replace("\"", "&quot;");
+            }
+        }
+        return result;
     }
 
     /**

From 6400987c8e15bc4ac8dfa41269caefb0bd6f7a54 Mon Sep 17 00:00:00 2001
From: piyush kumar sadangi <piyushkumarsadangi@MacBook-Air.local>
Date: Fri, 11 Oct 2024 07:28:28 +0530
Subject: [PATCH 2/2] Changes

---
 IllegalTokenText/Example3/config.xml                  | 2 +-
 IllegalTokenText/all-examples-in-one/config.xml       | 2 +-
 MultipleStringLiterals/Example3/config.xml            | 2 +-
 MultipleStringLiterals/all-examples-in-one/config.xml | 2 +-
 Regexp/Example12/config.xml                           | 2 +-
 Regexp/Example13/config.xml                           | 2 +-
 Regexp/all-examples-in-one/config.xml                 | 4 ++--
 7 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/IllegalTokenText/Example3/config.xml b/IllegalTokenText/Example3/config.xml
index 1d81b2a6c..6cb71c37b 100644
--- a/IllegalTokenText/Example3/config.xml
+++ b/IllegalTokenText/Example3/config.xml
@@ -23,7 +23,7 @@
         <property name="javaParseExceptionSeverity" value="ignore"/>
 
         <module name="IllegalTokenText">
-            <property name="format" value="""/>
+            <property name="format" value='"'/>
             <property name="tokens" value="TEXT_BLOCK_CONTENT"/>
         </module>
 
diff --git a/IllegalTokenText/all-examples-in-one/config.xml b/IllegalTokenText/all-examples-in-one/config.xml
index d750aea2a..0bfbb6c07 100644
--- a/IllegalTokenText/all-examples-in-one/config.xml
+++ b/IllegalTokenText/all-examples-in-one/config.xml
@@ -36,7 +36,7 @@
         </module>
 
         <module name="IllegalTokenText">
-            <property name="format" value="""/>
+            <property name="format" value='"'/>
             <property name="id" value="example3"/>
             <property name="tokens" value="TEXT_BLOCK_CONTENT"/>
         </module>
diff --git a/MultipleStringLiterals/Example3/config.xml b/MultipleStringLiterals/Example3/config.xml
index 620ce087b..b90a3ea3f 100644
--- a/MultipleStringLiterals/Example3/config.xml
+++ b/MultipleStringLiterals/Example3/config.xml
@@ -23,7 +23,7 @@
         <property name="javaParseExceptionSeverity" value="ignore"/>
 
         <module name="MultipleStringLiterals">
-            <property name="ignoreStringsRegexp" value="^(("")|(", "))$"/>
+            <property name="ignoreStringsRegexp" value='^(("")|(", "))$'/>
         </module>
 
         <!-- suppress javadoc parsing errors, as we test Check not a parser -->
diff --git a/MultipleStringLiterals/all-examples-in-one/config.xml b/MultipleStringLiterals/all-examples-in-one/config.xml
index 741a0b702..27fe1a3b5 100644
--- a/MultipleStringLiterals/all-examples-in-one/config.xml
+++ b/MultipleStringLiterals/all-examples-in-one/config.xml
@@ -33,7 +33,7 @@
 
         <module name="MultipleStringLiterals">
             <property name="id" value="example3"/>
-            <property name="ignoreStringsRegexp" value="^(("")|(", "))$"/>
+            <property name="ignoreStringsRegexp" value='^(("")|(", "))$'/>
         </module>
 
         <module name="MultipleStringLiterals">
diff --git a/Regexp/Example12/config.xml b/Regexp/Example12/config.xml
index 0a0e01215..1d6823de5 100644
--- a/Regexp/Example12/config.xml
+++ b/Regexp/Example12/config.xml
@@ -23,7 +23,7 @@
         <property name="javaParseExceptionSeverity" value="ignore"/>
 
         <module name="Regexp">
-            <property name="format" value="\A/\*\n \* (\w*)\.java\n \*\n \* Copyright \(c\)        \d\d\d\d ACME\n \* 123 Some St\.\n \* Somewhere\.\n \*\n        \* This software is the confidential and proprietary information        of ACME\.\n \* \("Confidential Information"\)\. You        shall not disclose such\n \* Confidential Information and shall        use it only in accordance with\n \* the terms of the license        agreement you entered into with ACME\.\n \*\n        \* \$Log: config_misc\.xml,v $        \* Revision 1\.7  2007/01/16 12:16:35  oburn        \* Removing all reference to mailing lists        \* \        \* Revision 1.6  2005/12/25 16:13:10  o_sukhodolsky        \* Fix for rfe 1248106 \(TYPECAST is now accepted by NoWhitespaceAfter\)        \* \        \* Fix for rfe 953266 \(thanks to Paul Guyot \(pguyot\) for submitting patch\)        \* IllegalType can be configured to accept some abstract classes which        \* matches to regexp of illegal type names \(property legalAbstractClassNames\)        \*        \* TrailingComment now can be configured to accept some trailing comments        \* \(such as NOI18N\) \(property legalComment, rfe 1385344\).        \*        \* Revision 1.5  2005/11/06 11:54:12  oburn        \* Incorporate excellent patch \[ 1344344 \] Consolidation of regexp checks.        \* \\n(.*\n)*([\w|\s]*( class | interface )\1)"/>
+            <property name="format" value='\A/\*\n \* (\w*)\.java\n \*\n \* Copyright \(c\)        \d\d\d\d ACME\n \* 123 Some St\.\n \* Somewhere\.\n \*\n        \* This software is the confidential and proprietary information        of ACME\.\n \* \("Confidential Information"\)\. You        shall not disclose such\n \* Confidential Information and shall        use it only in accordance with\n \* the terms of the license        agreement you entered into with ACME\.\n \*\n        \* \$Log: config_misc\.xml,v $        \* Revision 1\.7  2007/01/16 12:16:35  oburn        \* Removing all reference to mailing lists        \* \        \* Revision 1.6  2005/12/25 16:13:10  o_sukhodolsky        \* Fix for rfe 1248106 \(TYPECAST is now accepted by NoWhitespaceAfter\)        \* \        \* Fix for rfe 953266 \(thanks to Paul Guyot \(pguyot\) for submitting patch\)        \* IllegalType can be configured to accept some abstract classes which        \* matches to regexp of illegal type names \(property legalAbstractClassNames\)        \*        \* TrailingComment now can be configured to accept some trailing comments        \* \(such as NOI18N\) \(property legalComment, rfe 1385344\).        \*        \* Revision 1.5  2005/11/06 11:54:12  oburn        \* Incorporate excellent patch \[ 1344344 \] Consolidation of regexp checks.        \* \\n(.*\n)*([\w|\s]*( class | interface )\1)'/>
             <property name="message" value="Correct header not found"/>
         </module>
 
diff --git a/Regexp/Example13/config.xml b/Regexp/Example13/config.xml
index b1d1c1f78..ead2954cb 100644
--- a/Regexp/Example13/config.xml
+++ b/Regexp/Example13/config.xml
@@ -24,7 +24,7 @@
 
         <module name="Regexp">
             <property name="duplicateLimit" value="0"/>
-            <property name="format" value="(/\*\*\n)( \*.*\n)*( \* <P>\n \*   <I>        This software is the confidential and proprietary information of\n        \*   ACME \(<B>"Confidential Information"</B>        \)\. You shall not\n \*   disclose such Confidential Information        and shall use it only in\n \*   accordance with the terms of the        license agreement you entered into\n \*   with ACME\.</I>\n        \* </P>\n \*\n \* © copyright \d\d\d\d ACME\n        \*\n \* @author .*)(\n\s\*.*)*/\n[\w|\s]*( class | interface )"/>
+            <property name="format" value='(/\*\*\n)( \*.*\n)*( \* <P>\n \*   <I>        This software is the confidential and proprietary information of\n        \*   ACME \(<B>"Confidential Information"</B>        \)\. You shall not\n \*   disclose such Confidential Information        and shall use it only in\n \*   accordance with the terms of the        license agreement you entered into\n \*   with ACME\.</I>\n        \* </P>\n \*\n \* © copyright \d\d\d\d ACME\n        \*\n \* @author .*)(\n\s\*.*)*/\n[\w|\s]*( class | interface )'/>
             <property name="message" value="Copyright in class/interface Javadoc"/>
         </module>
 
diff --git a/Regexp/all-examples-in-one/config.xml b/Regexp/all-examples-in-one/config.xml
index 1affd6c40..551ba5702 100644
--- a/Regexp/all-examples-in-one/config.xml
+++ b/Regexp/all-examples-in-one/config.xml
@@ -88,14 +88,14 @@
         </module>
 
         <module name="Regexp">
-            <property name="format" value="\A/\*\n \* (\w*)\.java\n \*\n \* Copyright \(c\)        \d\d\d\d ACME\n \* 123 Some St\.\n \* Somewhere\.\n \*\n        \* This software is the confidential and proprietary information        of ACME\.\n \* \("Confidential Information"\)\. You        shall not disclose such\n \* Confidential Information and shall        use it only in accordance with\n \* the terms of the license        agreement you entered into with ACME\.\n \*\n        \* \$Log: config_misc\.xml,v $        \* Revision 1\.7  2007/01/16 12:16:35  oburn        \* Removing all reference to mailing lists        \* \        \* Revision 1.6  2005/12/25 16:13:10  o_sukhodolsky        \* Fix for rfe 1248106 \(TYPECAST is now accepted by NoWhitespaceAfter\)        \* \        \* Fix for rfe 953266 \(thanks to Paul Guyot \(pguyot\) for submitting patch\)        \* IllegalType can be configured to accept some abstract classes which        \* matches to regexp of illegal type names \(property legalAbstractClassNames\)        \*        \* TrailingComment now can be configured to accept some trailing comments        \* \(such as NOI18N\) \(property legalComment, rfe 1385344\).        \*        \* Revision 1.5  2005/11/06 11:54:12  oburn        \* Incorporate excellent patch \[ 1344344 \] Consolidation of regexp checks.        \* \\n(.*\n)*([\w|\s]*( class | interface )\1)"/>
+            <property name="format" value='\A/\*\n \* (\w*)\.java\n \*\n \* Copyright \(c\)        \d\d\d\d ACME\n \* 123 Some St\.\n \* Somewhere\.\n \*\n        \* This software is the confidential and proprietary information        of ACME\.\n \* \("Confidential Information"\)\. You        shall not disclose such\n \* Confidential Information and shall        use it only in accordance with\n \* the terms of the license        agreement you entered into with ACME\.\n \*\n        \* \$Log: config_misc\.xml,v $        \* Revision 1\.7  2007/01/16 12:16:35  oburn        \* Removing all reference to mailing lists        \* \        \* Revision 1.6  2005/12/25 16:13:10  o_sukhodolsky        \* Fix for rfe 1248106 \(TYPECAST is now accepted by NoWhitespaceAfter\)        \* \        \* Fix for rfe 953266 \(thanks to Paul Guyot \(pguyot\) for submitting patch\)        \* IllegalType can be configured to accept some abstract classes which        \* matches to regexp of illegal type names \(property legalAbstractClassNames\)        \*        \* TrailingComment now can be configured to accept some trailing comments        \* \(such as NOI18N\) \(property legalComment, rfe 1385344\).        \*        \* Revision 1.5  2005/11/06 11:54:12  oburn        \* Incorporate excellent patch \[ 1344344 \] Consolidation of regexp checks.        \* \\n(.*\n)*([\w|\s]*( class | interface )\1)'/>
             <property name="id" value="example12"/>
             <property name="message" value="Correct header not found"/>
         </module>
 
         <module name="Regexp">
             <property name="duplicateLimit" value="0"/>
-            <property name="format" value="(/\*\*\n)( \*.*\n)*( \* <P>\n \*   <I>        This software is the confidential and proprietary information of\n        \*   ACME \(<B>"Confidential Information"</B>        \)\. You shall not\n \*   disclose such Confidential Information        and shall use it only in\n \*   accordance with the terms of the        license agreement you entered into\n \*   with ACME\.</I>\n        \* </P>\n \*\n \* © copyright \d\d\d\d ACME\n        \*\n \* @author .*)(\n\s\*.*)*/\n[\w|\s]*( class | interface )"/>
+            <property name="format" value='(/\*\*\n)( \*.*\n)*( \* <P>\n \*   <I>        This software is the confidential and proprietary information of\n        \*   ACME \(<B>"Confidential Information"</B>        \)\. You shall not\n \*   disclose such Confidential Information        and shall use it only in\n \*   accordance with the terms of the        license agreement you entered into\n \*   with ACME\.</I>\n        \* </P>\n \*\n \* © copyright \d\d\d\d ACME\n        \*\n \* @author .*)(\n\s\*.*)*/\n[\w|\s]*( class | interface )'/>
             <property name="id" value="example13"/>
             <property name="message" value="Copyright in class/interface Javadoc"/>
         </module>