pkg/md: Add a Codec for smart punctuations.

Author: xiaq

pkg/md/smart_puncts.go

@@ -0,0 +1,77 @@
+package md
+
+import (
+	"strings"
+	"unicode"
+)
+
+// SmartPunctsCodec wraps another codec, converting certain ASCII punctuations to
+// nicer Unicode counterparts:
+//
+//   - A straight double quote (") is converted to a left double quote (“) when
+//     it follows a whitespace, or a right double quote (”) when it follows a
+//     non-whitespace.
+//
+//   - A straight single quote (') is converted to a left single quote (‘) when
+//     it follows a whitespace, or a right single quote or apostrophe (’) when
+//     it follows a non-whitespace.
+//
+//   - A run of two dashes (--) is converted to an en-dash (–).
+//
+//   - A run of three dashes (---) is converted to an em-dash (—).
+//
+//   - A run of three dot (...) is converted to an ellipsis (…).
+//
+// Start of lines are considered to be whitespaces.
+type SmartPunctsCodec struct{ Inner Codec }
+
+func (c SmartPunctsCodec) Do(op Op) { c.Inner.Do(applySmartPunctsToOp(op)) }
+
+func applySmartPunctsToOp(op Op) Op {
+	for i := range op.Content {
+		inlineOp := &op.Content[i]
+		switch inlineOp.Type {
+		case OpText, OpLinkStart, OpLinkEnd, OpImage:
+			inlineOp.Text = applySmartPuncts(inlineOp.Text)
+			if inlineOp.Type == OpImage {
+				inlineOp.Alt = applySmartPuncts(inlineOp.Alt)
+			}
+		}
+	}
+	return op
+}
+
+var applySimpleSmartPuncts = strings.NewReplacer(
+	"--", "–", "---", "—", "...", "…").Replace
+
+func applySmartPuncts(s string) string {
+	return applySimpleSmartPuncts(applySmartQuotes(s))
+}
+
+func applySmartQuotes(s string) string {
+	if !strings.ContainsAny(s, `'"`) {
+		return s
+	}
+	var sb strings.Builder
+	// Start of line is considered to be whitespace
+	prev := ' '
+	for _, r := range s {
+		if r == '"' {
+			if unicode.IsSpace(prev) {
+				sb.WriteRune('“')
+			} else {
+				sb.WriteRune('”')
+			}
+		} else if r == '\'' {
+			if unicode.IsSpace(prev) {
+				sb.WriteRune('‘')
+			} else {
+				sb.WriteRune('’')
+			}
+		} else {
+			sb.WriteRune(r)
+		}
+		prev = r
+	}
+	return sb.String()
+}

pkg/md/smart_puncts_test.go

@@ -0,0 +1,76 @@
+package md_test
+
+import (
+	"testing"
+
+	"github.com/google/go-cmp/cmp"
+	. "src.elv.sh/pkg/md"
+)
+
+var smartPunctsTestCases = []testCase{
+	{
+		Name:     "Simple smart punctuations",
+		Markdown: `a -- b --- c...`,
+		HTML: dedent(`
+			<p>a – b –- c…</p>
+			`),
+	},
+	{
+		Name:     "Smart quotes",
+		Markdown: `It's "foo" and 'bar'.`,
+		HTML: dedent(`
+			<p>It’s “foo” and ‘bar’.</p>
+			`),
+	},
+	{
+		Name: "Link and image title",
+		Markdown: dedent(`
+			[link text](a.html "--")
+			![img alt](a.png "--")
+			`),
+		HTML: dedent(`
+			<p><a href="a.html" title="–">link text</a>
+			<img src="a.png" alt="img alt" title="–" /></p>
+			`),
+	},
+	{
+		Name:     "Link alt",
+		Markdown: `![img -- alt](a.png)`,
+		HTML: dedent(`
+			<p><img src="a.png" alt="img – alt" /></p>
+			`),
+	},
+	{
+		Name:     "Code span is unchanged",
+		Markdown: "`a -- b`",
+		HTML: dedent(`
+			<p><code>a -- b</code></p>
+			`),
+	},
+	{
+		Name: "Non-inline content is unchanged",
+		Markdown: dedent(`
+			~~~
+			a -- b
+			~~~
+			`),
+		HTML: dedent(`
+			<pre><code>a -- b
+			</code></pre>
+			`),
+	},
+}
+
+func TestSmartPuncts(t *testing.T) {
+	for _, tc := range smartPunctsTestCases {
+		t.Run(tc.Name, func(t *testing.T) {
+			var htmlCodec HTMLCodec
+			Render(tc.Markdown, SmartPunctsCodec{&htmlCodec})
+			got := htmlCodec.String()
+			if diff := cmp.Diff(tc.HTML, got); diff != "" {
+				t.Errorf("input:\n%s\ndiff (-want +got):\n%s",
+					hr+"\n"+tc.Markdown+hr, diff)
+			}
+		})
+	}
+}