Add emoji stripping to StringManipulatorTool for SOAP compatibility

Co-authored-by: MrHinsh <[email protected]>

Author: Copilot

docs/content/docs/reference/tools/stringmanipulatortool/index.md

@@ -99,14 +99,14 @@ Each manipulator supports these properties:
 
 ### Removing Invalid Characters
 
-Remove control characters that may cause issues while preserving Unicode content:
+Remove control characters and emojis while preserving Unicode content:
 
 ```json
 {
   "$type": "RegexStringManipulator",
-  "Description": "Remove control characters but preserve Unicode letters and symbols",
+  "Description": "Remove control characters and emojis but preserve Unicode letters and symbols",
   "Enabled": true,
-  "Pattern": "[\\x00-\\x08\\x0B\\x0C\\x0E-\\x1F\\x7F-\\x9F]+",
+  "Pattern": "[\\x00-\\x08\\x0B\\x0C\\x0E-\\x1F\\x7F-\\x9F]|[\\uD800-\\uDBFF][\\uDC00-\\uDFFF]|\\uFE0F",
   "Replacement": ""
 }
 ```
@@ -151,6 +151,25 @@ Remove or clean HTML tags from text fields:
 }
 ```
 
+### Removing Emojis for SOAP Compatibility
+
+Remove emojis that can cause issues with SOAP interfaces while preserving other Unicode symbols:
+
+```json
+{
+  "$type": "RegexStringManipulator",
+  "Description": "Remove emojis but preserve Unicode letters and symbols",
+  "Enabled": true,
+  "Pattern": "[\\uD800-\\uDBFF][\\uDC00-\\uDFFF]|\\uFE0F",
+  "Replacement": ""
+}
+```
+
+This pattern removes:
+- Emoji surrogate pairs (😀🔥💻🇺🇸)
+- Variation selectors that control emoji presentation
+- But preserves mathematical symbols (∑), arrows (→), checkmarks (✓), stars (★), and accented letters (café)
+
 ### Fixing Encoding Issues
 
 Replace common encoding artifacts:

src/MigrationTools.Tests/ProcessorEnrichers/StringManipulatorEnricherTests.cs

@@ -221,6 +221,30 @@ public void StringManipulatorTool_DefaultManipulator_ExpectedBehavior(string val
             Assert.AreEqual(expected, newValue);
         }
 
+        [DataTestMethod(), TestCategory("L1")]
+        [DataRow("Hello 😀 World", "Hello  World")]           // Basic emoticons should be stripped (surrogate pairs)
+        [DataRow("Test 🔥 Fire", "Test  Fire")]              // Fire emoji should be stripped (surrogate pairs)
+        [DataRow("Code 💻 Work", "Code  Work")]              // Laptop emoji should be stripped (surrogate pairs)  
+        [DataRow("Heart ❤️ Love", "Heart ❤ Love")]           // Variation selector stripped, heart symbol preserved
+        [DataRow("Flag 🇺🇸 Country", "Flag  Country")]        // Regional indicators stripped (surrogate pairs)
+        [DataRow("Math ∑ Symbol", "Math ∑ Symbol")]           // Mathematical symbols preserved (not surrogate pairs)
+        [DataRow("Arrow → Direction", "Arrow → Direction")]    // Arrows preserved (not surrogate pairs)
+        [DataRow("Check ✓ Mark", "Check ✓ Mark")]             // Useful dingbats preserved (not surrogate pairs)
+        [DataRow("Star ★ Rating", "Star ★ Rating")]           // Miscellaneous symbols preserved (not surrogate pairs)
+        [DataRow("Café résumé", "Café résumé")]              // Regular Unicode letters preserved
+        [DataRow("Test\u0001\u0002", "Test")]                // Control chars should be removed
+        public void StringManipulatorTool_DefaultManipulator_EmojiStripping(string value, string expected)
+        {
+            var options = new StringManipulatorToolOptions();
+            options.Enabled = true;
+            options.MaxStringLength = 1000;
+            // No manipulators set - should use default (which should strip emojis)
+            var x = GetStringManipulatorTool(options);
+
+            string? newValue = x.ProcessString(value);
+            Assert.AreEqual(expected, newValue);
+        }
+
         private static StringManipulatorTool GetStringManipulatorTool(StringManipulatorToolOptions options)
         {
             var services = new ServiceCollection();

src/MigrationTools/Tools/StringManipulatorTool.cs

@@ -73,8 +73,8 @@ private void AddDefaultManipulator()
             Options.Manipulators.Add(new RegexStringManipulator()
             {
                 Enabled = true,
-                Description = "Default: Removes control characters but preserves Unicode letters and symbols",
-                Pattern = @"[\x00-\x08\x0B\x0C\x0E-\x1F\x7F-\x9F]+",
+                Description = "Default: Removes control characters and emojis but preserves Unicode letters and symbols",
+                Pattern = @"[\x00-\x08\x0B\x0C\x0E-\x1F\x7F-\x9F]|[\uD800-\uDBFF][\uDC00-\uDFFF]|\uFE0F",
                 Replacement = ""
             });
         }