feat(ui): Support Pandoc style code blocks

modules/markup/markdown/markdown_test.go

@@ -1489,14 +1489,14 @@ func TestCallout(t *testing.T) {
 </blockquote>`)
 }
 
-func TestCodeblockLanguageStripping(t *testing.T) {
+func TestCodeblockLanguageTransformation(t *testing.T) {
 	test := func(input, expected string) {
 		buffer, err := markdown.RenderString(&markup.RenderContext{Ctx: git.DefaultContext}, input)
 		require.NoError(t, err)
 		assert.Equal(t, strings.TrimSpace(expected), strings.TrimSpace(string(buffer)))
 	}
 
-	// Unstripped
+	// No transformation
 	test(
 		"```rust\n"+
 			"fn main() {}\n"+
@@ -1504,11 +1504,37 @@ func TestCodeblockLanguageStripping(t *testing.T) {
 		`<pre class="code-block"><code class="chroma language-rust display"><span class="k">fn</span> <span class="nf">main</span><span class="p">()</span><span class="w"> </span><span class="p">{}</span><span class="w">
 </span></code></pre>`)
 
-	// Stripped
+	// Comma stripped
 	test(
 		"```rust,ignore\n"+
 			"fn main() {}\n"+
 			"```",
 		`<pre class="code-block"><code class="chroma language-rust display"><span class="k">fn</span> <span class="nf">main</span><span class="p">()</span><span class="w"> </span><span class="p">{}</span><span class="w">
 </span></code></pre>`)
+
+	// Pandoc stripping
+	// https://pandoc.org/MANUAL.html#extension-fenced_code_attributes
+	test(
+		"```haskell {.numberLines}\n"+
+			"qsort []     = []\n"+
+			"qsort (x:xs) = qsort (filter (< x) xs) ++ [x] ++\n"+
+			"               qsort (filter (>= x) xs)\n"+
+			"```",
+		`<pre class="code-block"><code class="chroma language-haskell display"><span class="nf">qsort</span> <span class="kt">[]</span>     <span class="ow">=</span> <span class="kt">[]</span>
+<span class="nf">qsort</span> <span class="p">(</span><span class="n">x</span><span class="kt">:</span><span class="n">xs</span><span class="p">)</span> <span class="ow">=</span> <span class="n">qsort</span> <span class="p">(</span><span class="n">filter</span> <span class="p">(</span><span class="o">&lt;</span> <span class="n">x</span><span class="p">)</span> <span class="n">xs</span><span class="p">)</span> <span class="o">++</span> <span class="p">[</span><span class="n">x</span><span class="p">]</span> <span class="o">++</span>
+               <span class="n">qsort</span> <span class="p">(</span><span class="n">filter</span> <span class="p">(</span><span class="o">&gt;=</span> <span class="n">x</span><span class="p">)</span> <span class="n">xs</span><span class="p">)</span>
+</code></pre>`)
+
+	// Pandoc language extracting
+	// https://pandoc.org/MANUAL.html#extension-fenced_code_attributes
+	test(
+		"```{#mycode .numberLines .haskell startFrom=\"100\"}\n"+
+			"qsort []     = []\n"+
+			"qsort (x:xs) = qsort (filter (< x) xs) ++ [x] ++\n"+
+			"               qsort (filter (>= x) xs)\n"+
+			"```",
+		`<pre class="code-block"><code class="chroma language-haskell display"><span class="nf">qsort</span> <span class="kt">[]</span>     <span class="ow">=</span> <span class="kt">[]</span>
+<span class="nf">qsort</span> <span class="p">(</span><span class="n">x</span><span class="kt">:</span><span class="n">xs</span><span class="p">)</span> <span class="ow">=</span> <span class="n">qsort</span> <span class="p">(</span><span class="n">filter</span> <span class="p">(</span><span class="o">&lt;</span> <span class="n">x</span><span class="p">)</span> <span class="n">xs</span><span class="p">)</span> <span class="o">++</span> <span class="p">[</span><span class="n">x</span><span class="p">]</span> <span class="o">++</span>
+               <span class="n">qsort</span> <span class="p">(</span><span class="n">filter</span> <span class="p">(</span><span class="o">&gt;=</span> <span class="n">x</span><span class="p">)</span> <span class="n">xs</span><span class="p">)</span>
+</code></pre>`)
 }

modules/markup/markdown/transform_codeblock_lang.go

@@ -6,6 +6,7 @@ package markdown
 import (
 	"bytes"
 
+	"github.com/alecthomas/chroma/v2/lexers"
 	"github.com/yuin/goldmark/ast"
 	"github.com/yuin/goldmark/text"
 )
@@ -13,6 +14,47 @@ import (
 func (g *ASTTransformer) transformCodeblockLanguage(v *ast.FencedCodeBlock, reader text.Reader) {
 	src := reader.Source()
 	info := v.Info.Segment.Value(src)
+
+	// Parse Pandoc style attributes
+	// https://pandoc.org/MANUAL.html#extension-fenced_code_attributes
+	//
+	// For example,
+	// ```{.haskell .numberLines}
+	// ...
+	// ```
+	// Should have a language of "haskell", not "{.haskell .numberLines}"
+	if trimmed := bytes.TrimSpace(info); len(trimmed) != 0 && trimmed[0] == '{' && trimmed[len(trimmed)-1] == '}' {
+		attributes := trimmed[1 : len(trimmed)-1]
+		for attribute := range bytes.SplitSeq(attributes, []byte{' '}) {
+			if len(attribute) != 0 && attribute[0] == '.' {
+				class := attribute[1:]
+				if lexer := lexers.Get(string(class)); lexer != nil {
+					lang := class
+					langInx := bytes.Index(info, lang)
+					start := v.Info.Segment.Start + langInx
+					end := start + len(lang)
+					v.Info = ast.NewTextSegment(text.NewSegment(start, end))
+					return
+				}
+			}
+		}
+		return
+	}
+
+	// Strip trailing Pandoc style attributes
+	// https://pandoc.org/MANUAL.html#extension-fenced_code_attributes
+	//
+	// For example,
+	// ```haskell {.numberLines}
+	// ...
+	// ```
+	// Should have a language of "haskell ", not "haskell {.numberLines}"
+	if i := bytes.IndexByte(info, '{'); i != -1 {
+		start := v.Info.Segment.Start
+		v.Info = ast.NewTextSegment(text.NewSegment(start, start+i))
+		return
+	}
+
 	// Strip language after commas
 	//
 	// For example,
@@ -23,5 +65,6 @@ func (g *ASTTransformer) transformCodeblockLanguage(v *ast.FencedCodeBlock, read
 	if i := bytes.IndexByte(info, ','); i != -1 {
 		start := v.Info.Segment.Start
 		v.Info = ast.NewTextSegment(text.NewSegment(start, start+i))
+		return
 	}
 }