Preserve underscores in emphasis.

RELEASE_NOTES.md

@@ -1,3 +1,6 @@
+## 15.0.3
+* Fixes Markdown parser gets multiple-underscores-inside-italics wrong [#389](https://github.com/fsprojects/FSharp.Formatting/issues/389)
+
 ## 15.0.2
 * Trim the `--fscoptions` before passing them as `otherflags`. ([comment #616](https://github.com/fsprojects/FSharp.Formatting/issues/616#issuecomment-1200877765))
 

src/FSharp.Formatting.Markdown/MarkdownParser.fs

@@ -69,6 +69,18 @@ let inline (|EscapedLatexInlineMathChar|_|) input =
     | '\\' :: (('$') as c) :: rest -> Some(c, rest)
     | _ -> None
 
+/// Succeeds when the specified character list starts with a letter or number
+let inline (|AlphaNum|_|) input =
+    let re = """^[a-zA-Z0-9]"""
+    let match' = Regex.Match(Array.ofList input |> String, re)
+
+    if match'.Success then
+        let entity = match'.Value
+        let _, rest = List.splitAt entity.Length input
+        Some(char entity, rest)
+    else
+        None
+
 /// Matches a list if it starts with a sub-list that is delimited
 /// using the specified delimiters. Returns a wrapped list and the rest.
 ///
@@ -79,7 +91,12 @@ let (|DelimitedMarkdown|_|) bracket input =
     let rec loop acc =
         function
         | EscapedChar (x, xs) -> loop (x :: '\\' :: acc) xs
-        | input when List.startsWith endl input -> Some(List.rev acc, input)
+        | input when List.startsWith endl input ->
+            let rest = List.skip bracket.Length input
+
+            match rest with
+            | AlphaNum (x, xs) -> loop (x :: endl @ acc) xs
+            | _ -> Some(List.rev acc, input)
         | x :: xs -> loop (x :: acc) xs
         | [] -> None
     // If it starts with 'startl', let's search for 'endl'
@@ -90,7 +107,6 @@ let (|DelimitedMarkdown|_|) bracket input =
     else
         None
 
-
 /// This is similar to `List.Delimited`, but it skips over Latex inline math characters.
 let (|DelimitedLatexDisplayMath|_|) bracket input =
     let _startl, endl = bracket, bracket

tests/FSharp.Markdown.Tests/Markdown.fs

@@ -790,3 +790,90 @@ let ``Parse blockquote with three leading spaces`` () =
           ) ]
 
     (Markdown.Parse doc).Paragraphs |> shouldEqual expected
+
+[<Test>]
+let ``Underscore inside italic is preserved`` () =
+    let doc = "_fsharp_space_after_comma_"
+
+    let expected =
+        [ Paragraph(
+              [ Emphasis(
+                    [ Literal(
+                          "fsharp_space_after_comma",
+                          Some(
+                              { StartLine = 1
+                                StartColumn = 0
+                                EndLine = 1
+                                EndColumn = 24 }
+                          )
+                      ) ],
+                    Some(
+                        { StartLine = 1
+                          StartColumn = 0
+                          EndLine = 1
+                          EndColumn = 26 }
+                    )
+                ) ],
+              Some(
+                  { StartLine = 1
+                    StartColumn = 0
+                    EndLine = 1
+                    EndColumn = 26 }
+              )
+          ) ]
+
+    (Markdown.Parse doc).Paragraphs |> shouldEqual expected
+
+[<Test>]
+let ``Underscores inside word in heading`` () =
+    let doc =
+        """
+### fsharp_bar_before_discriminated_union_declaration
+
+Always use a bar before every case in the declaration of a discriminated union.
+"""
+
+    let expected =
+        [ Heading(
+              3,
+              [ Literal(
+                    "fsharp_bar_before_discriminated_union_declaration",
+                    Some
+                        { StartLine = 2
+                          StartColumn = 4
+                          EndLine = 2
+                          EndColumn = 53 }
+                ) ],
+              Some
+                  { StartLine = 2
+                    StartColumn = 0
+                    EndLine = 2
+                    EndColumn = 53 }
+          )
+          Paragraph(
+              [ Literal(
+                    "Always use a bar before every case in the declaration of a discriminated union.",
+                    Some
+                        { StartLine = 4
+                          StartColumn = 0
+                          EndLine = 4
+                          EndColumn = 79 }
+                ) ],
+              Some
+                  { StartLine = 4
+                    StartColumn = 0
+                    EndLine = 4
+                    EndColumn = 79 }
+          ) ]
+
+    (Markdown.Parse doc).Paragraphs |> shouldEqual expected
+
+[<Test>]
+let ``Underscore inside italic and bold near punctuation is preserved`` () =
+    let doc = "This is **bold_bold**, and this _italic_; and _this_too_: again."
+
+    let expected =
+        "<p>This is <strong>bold_bold</strong>, and this <em>italic</em>; and <em>this_too</em>: again.</p>\r\n"
+        |> properNewLines
+
+    Markdown.ToHtml doc |> shouldEqual expected