[Repo Assist] Fix #964: Comprehensive tests for emoji in FSX → HTML conversion (#992)

github-actions[bot] · Repo Assist · Copilot · web-flow · commit cbd975a084b8 · 2026-02-24T04:54:37.000Z
* Add comprehensive tests for emoji in FSX comments -> HTML conversion (issue #964) - Add 13 emoji tests to FSharp.Markdown.Tests covering all Unicode categories: supplementary plane (surrogate pairs), BMP, variation selectors, ZWJ sequences in paragraphs, headings, bold/italic, lists, links, inline code, fenced code - Add 17 emoji tests to FSharp.Literate.Tests covering full FSX -> HTML pipeline: ParseScriptString, file on disk, ConvertScriptFile HTML output, Markdown output, multiple doc comment blocks, multi-line, HTML escaping compatibility - Add emoji.fsx test fixture file - No code changes required: the pipeline already handles emoji correctly Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Apply Fantomas formatting to test files Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Repo Assist <repo-assist@github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
diff --git a/tests/FSharp.Literate.Tests/FSharp.Literate.Tests.fsproj b/tests/FSharp.Literate.Tests/FSharp.Literate.Tests.fsproj
@@ -7,6 +7,7 @@
   </PropertyGroup>
   <ItemGroup>
     <None Include="files/simple1.fsx" />
+    <None Include="files/emoji.fsx" />
     <None Include="files/simple2.md" />
     <None Include="files/template.html" />
     <None Include="files/docpage.html" />
diff --git a/tests/FSharp.Literate.Tests/LiterateTests.fs b/tests/FSharp.Literate.Tests/LiterateTests.fs
@@ -1767,3 +1767,186 @@ let ``Script transforms to markdown`` () =
     md |> shouldContainText "[substitute-in-href-text: simple1](http://google.com)"
     md |> shouldContainText "Another [hyperlink](simple2.md)"
     md |> shouldContainText "let hello ="
+
+// --------------------------------------------------------------------------------------
+// Emoji in FSX comments → HTML (Issue #964)
+// These tests verify that emoji characters are preserved throughout the full
+// FSX → Markdown → HTML conversion pipeline.
+// --------------------------------------------------------------------------------------
+
+// Supplementary plane emoji (U+1F389, stored as surrogate pair in UTF-16)
+let emojiParty = "\U0001F389" // 🎉 PARTY POPPER
+let emojiRocket = "\U0001F680" // 🚀 ROCKET
+let emojiConstruction = "\U0001F6A7" // 🚧 CONSTRUCTION SIGN
+// Basic multilingual plane emoji (single UTF-16 code unit)
+let emojiStar = "\u2B50" // ⭐ WHITE MEDIUM STAR
+let emojiCheck = "\u2705" // ✅ WHITE HEAVY CHECK MARK
+// Emoji with variation selector (two code points)
+let emojiWarning = "\u26A0\uFE0F" // ⚠️ WARNING SIGN + VS-16
+// ZWJ sequence (multiple code points joined with zero-width joiner)
+let emojiFamily = "\U0001F468\u200D\U0001F469\u200D\U0001F467\u200D\U0001F466" // 👨‍👩‍👧‍👦
+
+[<Test>]
+let ``Supplementary plane emoji in FSX doc comment are preserved in HTML`` () =
+    let fsx = sprintf "(**\nLike this %s and %s\n*)\nlet x = 42" emojiParty emojiRocket
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiParty
+    html |> shouldContainText emojiRocket
+
+[<Test>]
+let ``BMP emoji in FSX doc comment are preserved in HTML`` () =
+    let fsx = sprintf "(**\nStars %s and checks %s\n*)\nlet x = 42" emojiStar emojiCheck
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiStar
+    html |> shouldContainText emojiCheck
+
+[<Test>]
+let ``Variation selector emoji in FSX doc comment are preserved in HTML`` () =
+    let fsx = sprintf "(**\nWarning %s sign\n*)\nlet x = 42" emojiWarning
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiWarning
+
+[<Test>]
+let ``ZWJ emoji sequence in FSX doc comment are preserved in HTML`` () =
+    let fsx = sprintf "(**\nFamily %s emoji\n*)\nlet x = 42" emojiFamily
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiFamily
+
+[<Test>]
+let ``Emoji in FSX heading (H1) are preserved in HTML`` () =
+    let fsx = sprintf "(**\n# Heading %s Title\n*)\nlet x = 42" emojiParty
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiParty
+
+[<Test>]
+let ``Emoji in FSX heading (H2) are preserved in HTML`` () =
+    let fsx = sprintf "(**\n## Subheading %s\n*)\nlet x = 42" emojiRocket
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiRocket
+
+[<Test>]
+let ``Emoji in bold spans in FSX doc comment are preserved in HTML`` () =
+    let fsx = sprintf "(**\n**Bold %s text**\n*)\nlet x = 42" emojiParty
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiParty
+
+[<Test>]
+let ``Emoji in italic spans in FSX doc comment are preserved in HTML`` () =
+    let fsx = sprintf "(**\n_Italic %s text_\n*)\nlet x = 42" emojiStar
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiStar
+
+[<Test>]
+let ``Emoji in list items in FSX doc comment are preserved in HTML`` () =
+    let fsx = sprintf "(**\n- Item %s\n- Item %s\n*)\nlet x = 42" emojiParty emojiCheck
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiParty
+    html |> shouldContainText emojiCheck
+
+[<Test>]
+let ``Emoji in inline code in FSX doc comment are preserved in HTML`` () =
+    let fsx = sprintf "(**\nCode `%s emoji` here\n*)\nlet x = 42" emojiParty
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiParty
+
+[<Test>]
+let ``All emoji types together in FSX doc comment are all preserved in HTML`` () =
+    let fsx =
+        sprintf
+            "(**\nAll: %s %s %s %s %s\n*)\nlet x = 42"
+            emojiParty
+            emojiConstruction
+            emojiStar
+            emojiWarning
+            emojiCheck
+
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiParty
+    html |> shouldContainText emojiConstruction
+    html |> shouldContainText emojiStar
+    html |> shouldContainText emojiWarning
+    html |> shouldContainText emojiCheck
+
+[<Test>]
+let ``Emoji across multiple FSX doc comment blocks are all preserved in HTML`` () =
+    let fsx = sprintf "(**\nFirst block %s\n*)\nlet x = 42\n(**\nSecond block %s\n*)\nlet y = 99" emojiParty emojiRocket
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiParty
+    html |> shouldContainText emojiRocket
+
+[<Test>]
+let ``Emoji in multi-line FSX doc comment are preserved in HTML`` () =
+    let fsx = sprintf "(**\nLine one %s\nLine two %s\nLine three %s\n*)\nlet x = 42" emojiParty emojiStar emojiCheck
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiParty
+    html |> shouldContainText emojiStar
+    html |> shouldContainText emojiCheck
+
+[<Test>]
+let ``Emoji do not break HTML escaping in FSX doc comments`` () =
+    let fsx = sprintf "(**\nA &amp; %s and &lt;tag&gt;\n*)\nlet x = 42" emojiParty
+    let doc = Literate.ParseScriptString(fsx)
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiParty
+    html |> shouldContainText "&amp;"
+
+[<Test>]
+let ``Emoji in FSX file on disk are preserved in HTML output`` () =
+    let fsx = File.ReadAllText(__SOURCE_DIRECTORY__ </> "files" </> "emoji.fsx")
+    let doc = Literate.ParseScriptString(fsx, __SOURCE_DIRECTORY__ </> "files" </> "emoji.fsx")
+    let html = Literate.ToHtml(doc)
+    html |> shouldContainText emojiParty
+    html |> shouldContainText emojiRocket
+    html |> shouldContainText emojiStar
+    html |> shouldContainText emojiWarning
+    html |> shouldContainText emojiCheck
+    html |> shouldContainText emojiConstruction
+    html |> shouldContainText emojiFamily
+
+[<Test>]
+let ``Emoji in ConvertScriptFile HTML output file are preserved`` () =
+    let outputFile = __SOURCE_DIRECTORY__ </> "output" </> "emoji.html"
+
+    Literate.ConvertScriptFile(
+        __SOURCE_DIRECTORY__ </> "files" </> "emoji.fsx",
+        outputKind = OutputKind.Html,
+        output = outputFile
+    )
+
+    let html = File.ReadAllText outputFile
+    html |> shouldContainText emojiParty
+    html |> shouldContainText emojiRocket
+    html |> shouldContainText emojiStar
+    html |> shouldContainText emojiWarning
+    html |> shouldContainText emojiCheck
+    html |> shouldContainText emojiConstruction
+
+[<Test>]
+let ``Emoji in ConvertScriptFile Markdown output file are preserved`` () =
+    let outputFile = __SOURCE_DIRECTORY__ </> "output2" </> "emoji.md"
+
+    Literate.ConvertScriptFile(
+        __SOURCE_DIRECTORY__ </> "files" </> "emoji.fsx",
+        outputKind = OutputKind.Markdown,
+        output = outputFile
+    )
+
+    let md = File.ReadAllText outputFile
+    md |> shouldContainText emojiParty
+    md |> shouldContainText emojiRocket
+    md |> shouldContainText emojiStar
+
+// End emoji tests
diff --git a/tests/FSharp.Literate.Tests/files/emoji.fsx b/tests/FSharp.Literate.Tests/files/emoji.fsx
@@ -0,0 +1,19 @@
+(**
+# Title with 🎉 Emoji
+
+This paragraph contains **bold 🚀 text** and *italic ⭐ text*.
+
+Here are some emoji categories:
+- Party 🎉 (supplementary plane, surrogate pair)
+- Rocket 🚀 (supplementary plane, surrogate pair)
+- Star ⭐ (basic multilingual plane)
+- Warning ⚠️ (BMP + variation selector)
+- Check ✅ (BMP)
+- Construction 🚧 (supplementary plane)
+
+A family ZWJ sequence: 👨‍👩‍👧‍👦
+
+Inline `code with 🎉 emoji` here.
+
+*)
+let x = 42
diff --git a/tests/FSharp.Markdown.Tests/Markdown.fs b/tests/FSharp.Markdown.Tests/Markdown.fs
@@ -54,6 +54,113 @@ let ``Inline HTML tag containing 'at' is not turned into hyperlink`` () =
               )
           ) ]
 
+// --------------------------------------------------------------------------------------
+// Emoji in Markdown → HTML (Issue #964)
+// These tests verify the full FSX → HTML path for emoji characters.
+// Emoji should be preserved as-is in HTML output (raw UTF-8).
+// --------------------------------------------------------------------------------------
+
+// Supplementary plane emoji (U+1F389, stored as surrogate pair in UTF-16)
+let emojiParty = "\U0001F389" // 🎉 PARTY POPPER
+let emojiRocket = "\U0001F680" // 🚀 ROCKET
+let emojiConstruction = "\U0001F6A7" // 🚧 CONSTRUCTION SIGN
+// Basic multilingual plane emoji (single UTF-16 code unit)
+let emojiStar = "\u2B50" // ⭐ WHITE MEDIUM STAR
+let emojiCheck = "\u2705" // ✅ WHITE HEAVY CHECK MARK
+// Emoji with variation selector (two code points)
+let emojiWarning = "\u26A0\uFE0F" // ⚠️ WARNING SIGN + VS-16
+// ZWJ sequence (multiple code points joined)
+let emojiFamily = "\U0001F468\u200D\U0001F469\u200D\U0001F467\u200D\U0001F466" // 👨‍👩‍👧‍👦
+
+[<Test>]
+let ``Supplementary plane emoji (surrogate pair) are preserved in paragraph`` () =
+    let html = sprintf "Like this %s and %s" emojiParty emojiRocket |> Markdown.ToHtml
+    html |> should contain emojiParty
+    html |> should contain emojiRocket
+
+[<Test>]
+let ``BMP emoji (single code unit) are preserved in paragraph`` () =
+    let html = sprintf "Stars %s and checks %s" emojiStar emojiCheck |> Markdown.ToHtml
+    html |> should contain emojiStar
+    html |> should contain emojiCheck
+
+[<Test>]
+let ``Emoji with variation selector are preserved`` () =
+    let html = sprintf "Warning %s sign" emojiWarning |> Markdown.ToHtml
+    html |> should contain emojiWarning
+
+[<Test>]
+let ``ZWJ emoji sequences are preserved`` () =
+    let html = sprintf "Family %s emoji" emojiFamily |> Markdown.ToHtml
+    html |> should contain emojiFamily
+
+[<Test>]
+let ``Emoji are preserved in headings`` () =
+    let html =
+        sprintf "# Heading %s\n\n## Subheading %s" emojiParty emojiRocket
+        |> Markdown.ToHtml
+
+    html |> should contain emojiParty
+    html |> should contain emojiRocket
+
+[<Test>]
+let ``Emoji are preserved in bold and italic spans`` () =
+    let html = sprintf "**Bold %s** and _italic %s_" emojiParty emojiStar |> Markdown.ToHtml
+    html |> should contain emojiParty
+    html |> should contain emojiStar
+
+[<Test>]
+let ``Emoji are preserved in list items`` () =
+    let html =
+        sprintf "- Item %s\n- Item %s\n- Item %s" emojiParty emojiStar emojiCheck
+        |> Markdown.ToHtml
+
+    html |> should contain emojiParty
+    html |> should contain emojiStar
+    html |> should contain emojiCheck
+
+[<Test>]
+let ``Emoji are preserved in link text`` () =
+    let html = sprintf "[Link %s](http://example.com)" emojiParty |> Markdown.ToHtml
+    html |> should contain emojiParty
+
+[<Test>]
+let ``Emoji are preserved in inline code`` () =
+    let html = sprintf "Code `%s emoji`" emojiParty |> Markdown.ToHtml
+    html |> should contain emojiParty
+
+[<Test>]
+let ``Emoji do not break HTML escaping of & < > characters`` () =
+    let html = sprintf "A &amp; %s and &lt;tag&gt;" emojiParty |> Markdown.ToHtml
+    html |> should contain "&amp;"
+    html |> should contain "&lt;"
+    html |> should contain "&gt;"
+    html |> should contain emojiParty
+
+[<Test>]
+let ``Multiple emoji types together are all preserved`` () =
+    let text = sprintf "%s%s%s%s%s" emojiParty emojiConstruction emojiStar emojiWarning emojiCheck
+    let html = text |> Markdown.ToHtml
+    html |> should contain emojiParty
+    html |> should contain emojiConstruction
+    html |> should contain emojiStar
+    html |> should contain emojiWarning
+    html |> should contain emojiCheck
+
+[<Test>]
+let ``Emoji at start and end of paragraph are preserved`` () =
+    let html = sprintf "%s Start and End %s" emojiParty emojiRocket |> Markdown.ToHtml
+    html |> should contain emojiParty
+    html |> should contain emojiRocket
+
+[<Test>]
+let ``Emoji are preserved in fenced code block`` () =
+    let md = sprintf "```\nlet emoji = \"%s\"\n```" emojiParty
+    let html = md |> Markdown.ToHtml
+    html |> should contain emojiParty
+
+// End emoji tests
+
 [<Test>]
 let ``Encode '<' and '>' characters as HTML entities`` () =
     let doc = "foo\n\n - a --> b" |> Markdown.ToHtml
