Merge pull request #1605 from fsprojects/repo-assist/fix-html-pre-whitespace-1509-e19da38c877032c0

[Repo Assist] Fix HtmlNode.ToString: preserve whitespace in elements nested inside <pre>

Author: dsyme

src/FSharp.Data.Html.Core/HtmlNode.fs

@@ -114,7 +114,7 @@ type HtmlNode =
 
             fun name -> Set.contains name set
 
-        let rec serialize (sb: StringBuilder) indentation canAddNewLine html =
+        let rec serialize (sb: StringBuilder) indentation canAddNewLine insidePre html =
             let append (str: string) = sb.Append str |> ignore
 
             let appendEndTag name =
@@ -135,8 +135,9 @@ type HtmlNode =
                         | _ -> false)
 
                 let isPreTag = name = "pre"
+                let nowInsidePre = insidePre || isPreTag
 
-                if canAddNewLine && not (onlyText || isPreTag) then
+                if canAddNewLine && not insidePre && not (onlyText || isPreTag) then
                     newLine 0
 
                 append "<"
@@ -157,16 +158,16 @@ type HtmlNode =
                 else
                     append ">"
 
-                    if not (onlyText || isPreTag) then
+                    if not insidePre && not (onlyText || isPreTag) then
                         newLine 2
 
                     let mutable canAddNewLine = false
 
                     for element in elements do
-                        serialize sb (indentation + 2) canAddNewLine element
+                        serialize sb (indentation + 2) canAddNewLine nowInsidePre element
                         canAddNewLine <- true
 
-                    if not (onlyText || isPreTag) then
+                    if not insidePre && not (onlyText || isPreTag) then
                         newLine 0
 
                     appendEndTag name
@@ -181,7 +182,7 @@ type HtmlNode =
                 append "]]>"
 
         let sb = StringBuilder()
-        serialize sb 0 false x |> ignore
+        serialize sb 0 false false x |> ignore
         sb.ToString()
 
     /// <exclude />

tests/FSharp.Data.Core.Tests/HtmlParser.fs

@@ -869,6 +869,18 @@ let ``Maintain whitespace inside pre tag through round-trip``() =
     let expected = html
     result |> should equal expected
 
+[<Test>]
+let ``Maintain whitespace in deeply nested elements inside pre through round-trip``() =
+    // Regression test for https://github.com/fsprojects/FSharp.Data/issues/1509
+    // Syntax highlighters (e.g. shiki) emit <pre><code><span class="line"><span>...</span></span></code></pre>
+    // Without the insidePre fix, the nested multi-element spans would have newlines inserted between them.
+    let html = """<pre><code><span class="line"><span style="color:red">let</span> <span style="color:blue">x</span> <span style="color:green">=</span> <span style="color:black">1</span></span></code></pre>"""
+
+    let result = HtmlDocument.Parse(html).ToString()
+
+    let expected = html
+    result |> should equal expected
+
 [<Test>]
 let ``Can parse national rail mobile site correctly``() =
     HtmlDocument.Load "UKDepartures.html"