Merge branch 'main' into carlosff/json/unwrappedtables

src/libraries/Microsoft.PowerFx.Core/Localization/Strings.cs

@@ -528,6 +528,9 @@ internal static class TexlStrings
         public static StringGetter AboutEncodeUrl = (b) => StringResources.Get("AboutEncodeUrl", b);
         public static StringGetter EncodeUrlArg1 = (b) => StringResources.Get("EncodeUrlArg1", b);
 
+        public static StringGetter AboutEncodeHTML = (b) => StringResources.Get("AboutEncodeHTML", b);
+        public static StringGetter EncodeHTMLArg1 = (b) => StringResources.Get("EncodeHTMLArg1", b);
+
         public static StringGetter AboutPlainText = (b) => StringResources.Get("AboutPlainText", b);
         public static StringGetter PlainTextArg1 = (b) => StringResources.Get("PlainTextArg1", b);
 

src/libraries/Microsoft.PowerFx.Core/Texl/BuiltinFunctionsCore.cs

@@ -96,6 +96,7 @@ internal class BuiltinFunctionsCore
         public static readonly TexlFunction DropColumns = _library.Add(new DropColumnsFunction());
         public static readonly TexlFunction EDate = _library.Add(new EDateFunction());
         public static readonly TexlFunction EOMonth = _library.Add(new EOMonthFunction());
+        public static readonly TexlFunction EncodeHTML = _library.Add(new EncodeHTMLFunction());
         public static readonly TexlFunction EncodeUrl = _library.Add(new EncodeUrlFunction());
         public static readonly TexlFunction EndsWith = _library.Add(new EndsWithFunction());
         public static readonly TexlFunction Error = _library.Add(new ErrorFunction());

src/libraries/Microsoft.PowerFx.Core/Texl/Builtins/EncodeHTML.cs

@@ -0,0 +1,23 @@
+// Copyright (c) Microsoft Corporation.
+// Licensed under the MIT license.
+
+using System.Collections.Generic;
+using Microsoft.PowerFx.Core.Localization;
+using Microsoft.PowerFx.Core.Texl.Builtins;
+using Microsoft.PowerFx.Core.Types;
+
+namespace Microsoft.PowerFx.Core.Texl
+{
+    internal sealed class EncodeHTMLFunction : StringOneArgFunction
+    {
+        public EncodeHTMLFunction()
+                : base("EncodeHTML", TexlStrings.AboutEncodeHTML, FunctionCategories.Text)
+        {
+        }
+
+        public override IEnumerable<TexlStrings.StringGetter[]> GetSignatures()
+        {
+            yield return new[] { TexlStrings.EncodeHTMLArg1 };
+        }
+    }
+}

src/libraries/Microsoft.PowerFx.Interpreter/Functions/Library.cs

@@ -652,6 +652,17 @@ static Library()
                     returnBehavior: ReturnBehavior.AlwaysEvaluateAndReturnResult,
                     targetFunction: EOMonth)
             },
+            {
+                BuiltinFunctionsCore.EncodeHTML,
+                StandardErrorHandling<StringValue>(
+                    BuiltinFunctionsCore.EncodeUrl.Name,
+                    expandArguments: NoArgExpansion,
+                    replaceBlankValues: NoOpAlreadyHandledByIR,
+                    checkRuntimeTypes: ExactValueType<StringValue>,
+                    checkRuntimeValues: DeferRuntimeValueChecking,
+                    returnBehavior: ReturnBehavior.AlwaysEvaluateAndReturnResult,
+                    targetFunction: EncodeHTML)
+            },
             {
                 BuiltinFunctionsCore.EncodeUrl,
                 StandardErrorHandling<StringValue>(

src/libraries/Microsoft.PowerFx.Interpreter/Functions/LibraryText.cs

@@ -11,6 +11,7 @@
 using System.Text.RegularExpressions;
 using System.Threading;
 using System.Threading.Tasks;
+using System.Web;
 using Microsoft.PowerFx.Core.Functions;
 using Microsoft.PowerFx.Core.IR;
 using Microsoft.PowerFx.Core.Localization;
@@ -826,6 +827,12 @@ public static FormulaValue EncodeUrl(IRContext irContext, StringValue[] args)
             return new StringValue(irContext, Uri.EscapeDataString(args[0].Value));
         }
 
+        public static FormulaValue EncodeHTML(IRContext irContext, StringValue[] args)
+        {
+            var encoded = HttpUtility.HtmlEncode(args[0].Value);
+            return new StringValue(irContext, encoded);
+        }
+
         public static FormulaValue Proper(EvalVisitor runner, EvalVisitorContext context, IRContext irContext, StringValue[] args)
         {
             return new StringValue(irContext, runner.CultureInfo.TextInfo.ToTitleCase(runner.CultureInfo.TextInfo.ToLower(args[0].Value)));

src/strings/PowerFxResources.en-US.resx

@@ -4136,6 +4136,17 @@
   <data name="AboutEncodeUrl_url" xml:space="preserve">
     <value>A url to be encoded.</value>
   </data>
+  <data name="AboutEncodeHTML" xml:space="preserve">
+    <value>Converts a text to an HTML-encoded text.</value>
+    <comment>Description of 'EncodeHTML' function.</comment>
+  </data>
+  <data name="EncodeHTMLArg1" xml:space="preserve">
+    <value>value</value>
+    <comment>Function_parameter - First parameter for the EncodeHTML function - the value (string) to encode.</comment>
+  </data>
+  <data name="AboutEncodeHTML_value" xml:space="preserve">
+    <value>A text to be encoded.</value>
+  </data>
   <data name="ErrUnimplementedFunction" xml:space="preserve">
     <value>'{0}' is a recognized but not supported function.</value>
     <comment>Error Message.</comment>

src/tests/Microsoft.PowerFx.Core.Tests/ExpressionTestCases/EncodeHTML.txt

@@ -0,0 +1,49 @@
+// Escaping
+>> EncodeHTML("<p>A paragraph</p>")
+"&lt;p&gt;A paragraph&lt;/p&gt;"
+
+// Multiple encodings
+>> EncodeHTML("<h1>Mac & cheese</h1>")
+"&lt;h1&gt;Mac &amp; cheese&lt;/h1&gt;"
+
+// Quotes
+>> EncodeHTML("A value with ""double"" and 'single' quotes")
+"A value with &quot;double&quot; and &#39;single&#39; quotes"
+
+// \u00A0 to \u00af - escaped
+>> EncodeHTML(Concat(Sequence(16, 160), UniChar(Value)))
+"&#160;&#161;&#162;&#163;&#164;&#165;&#166;&#167;&#168;&#169;&#170;&#171;&#172;&#173;&#174;&#175;"
+
+// \u0090 to \u009f - not escaped
+>> With({str:Concat(Sequence(16, 144), UniChar(Value))}, str = EncodeHTML(str))
+true
+
+// \u00A0 to \u00ff - escaped
+>> With({str:EncodeHTML(Concat(Sequence(96, 160), UniChar(Value))), expectedEscaped:Concat(Sequence(96, 160), $"&#{Value};")}, str = expectedEscaped)
+true
+
+// \u0100... not escaped
+>> EncodeHTML("<b>ĀāĂă</b>")
+"&lt;b&gt;ĀāĂă&lt;/b&gt;"
+
+// Blanks
+>> EncodeHTML(Blank())
+""
+
+>> EncodeHTML("")
+""
+
+// Errors
+>> EncodeHTML(Char(-1))
+Error({Kind:ErrorKind.InvalidArgument})
+
+// Escaping surrogate pairs
+>> EncodeHTML("<ul><li>not a pair: ❤</li><li>a surrogate pair: 💩</li></ul>")
+"&lt;ul&gt;&lt;li&gt;not a pair: ❤&lt;/li&gt;&lt;li&gt;a surrogate pair: &#128169;&lt;/li&gt;&lt;/ul&gt;"
+
+>> EncodeHTML("Osage alphabet (start): 𐒰𐒱𐒲𐒳𐒴𐒵𐒶")
+"Osage alphabet (start): &#66736;&#66737;&#66738;&#66739;&#66740;&#66741;&#66742;"
+
+// Unpaired surrogate characters become the replacement character U+FFFD
+>> EncodeHTML($"Unpaired: {Mid(UniChar(Hex2Dec("1f600")),1,1)} {Mid(UniChar(Hex2Dec("1f600")),2,1)}") = $"Unpaired: {UniChar(65533)} {UniChar(65533)}"
+true

src/tests/Microsoft.PowerFx.Interpreter.Tests/Docs/InterpreterBase.json

@@ -46,6 +46,7 @@
     "Distinct",
     "DropColumns",
     "EDate",
+    "EncodeHTML",
     "EncodeUrl",
     "EndsWith",
     "EOMonth",