Add self-contained Mermaid diagram support via Goldmark

go.mod

@@ -1,17 +1,13 @@
 module github.com/mapitman/mdview
 
-go 1.21.1
+go 1.24
+
+toolchain go1.24.11
 
 require (
 	github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c
-	gitlab.com/golang-commonmark/markdown v0.0.0-20211110145824-bf3e522c626a
+	github.com/yuin/goldmark v1.7.13
+	go.abhg.dev/goldmark/mermaid v0.6.0
 )
 
-require (
-	gitlab.com/golang-commonmark/html v0.0.0-20191124015941-a22733972181 // indirect
-	gitlab.com/golang-commonmark/linkify v0.0.0-20191026162114-a0c2df6c8f82 // indirect
-	gitlab.com/golang-commonmark/mdurl v0.0.0-20191124015652-932350d1cb84 // indirect
-	gitlab.com/golang-commonmark/puny v0.0.0-20191124015043-9f83538fa04f // indirect
-	golang.org/x/sys v0.1.0 // indirect
-	golang.org/x/text v0.3.8 // indirect
-)
+require golang.org/x/sys v0.34.0 // indirect

go.sum

@@ -1,22 +1,31 @@
+github.com/chromedp/cdproto v0.0.0-20250803210736-d308e07a266d h1:ZtA1sedVbEW7EW80Iz2GR3Ye6PwbJAJXjv7D74xG6HU=
+github.com/chromedp/cdproto v0.0.0-20250803210736-d308e07a266d/go.mod h1:NItd7aLkcfOA/dcMXvl8p1u+lQqioRMq/SqDp71Pb/k=
+github.com/chromedp/chromedp v0.14.0 h1:/xE5m6wEBwivhalHwlCOyYfBcAJNwg4nLw96QiCfYr0=
+github.com/chromedp/chromedp v0.14.0/go.mod h1:rHzAv60xDE7VNy/MYtTUrYreSc0ujt2O1/C3bzctYBo=
+github.com/chromedp/sysutil v1.1.0 h1:PUFNv5EcprjqXZD9nJb9b/c9ibAbxiYo4exNWZyipwM=
+github.com/chromedp/sysutil v1.1.0/go.mod h1:WiThHUdltqCNKGc4gaU50XgYjwjYIhKWoHGPTUfWTJ8=
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/go-json-experiment/json v0.0.0-20250725192818-e39067aee2d2 h1:iizUGZ9pEquQS5jTGkh4AqeeHCMbfbjeb0zMt0aEFzs=
+github.com/go-json-experiment/json v0.0.0-20250725192818-e39067aee2d2/go.mod h1:TiCD2a1pcmjd7YnhGH0f/zKNcCD06B029pHhzV23c2M=
+github.com/gobwas/httphead v0.1.0 h1:exrUm0f4YX0L7EBwZHuCF4GDp8aJfVeBrlLQrs6NqWU=
+github.com/gobwas/httphead v0.1.0/go.mod h1:O/RXo79gxV8G+RqlR/otEwx4Q36zl9rqC5u12GKvMCM=
+github.com/gobwas/pool v0.2.1 h1:xfeeEhW7pwmX8nuLVlqbzVc7udMDrwetjEv+TZIz1og=
+github.com/gobwas/pool v0.2.1/go.mod h1:q8bcK0KcYlCgd9e7WYLm9LpyS+YeLd8JVDW6WezmKEw=
+github.com/gobwas/ws v1.4.0 h1:CTaoG1tojrh4ucGPcoJFiAQUAsEWekEWvLy7GsVNqGs=
+github.com/gobwas/ws v1.4.0/go.mod h1:G3gNqMNtPppf5XUz7O4shetPpcZ1VJ7zt18dlUeakrc=
 github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c h1:+mdjkGKdHQG3305AYmdv1U2eRNDiU2ErMBj1gwrq8eQ=
 github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c/go.mod h1:7rwL4CYBLnjLxUqIJNnCWiEdr3bn6IUYi15bNlnbCCU=
-github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
-github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
-gitlab.com/golang-commonmark/html v0.0.0-20191124015941-a22733972181 h1:K+bMSIx9A7mLES1rtG+qKduLIXq40DAzYHtb0XuCukA=
-gitlab.com/golang-commonmark/html v0.0.0-20191124015941-a22733972181/go.mod h1:dzYhVIwWCtzPAa4QP98wfB9+mzt33MSmM8wsKiMi2ow=
-gitlab.com/golang-commonmark/linkify v0.0.0-20191026162114-a0c2df6c8f82 h1:oYrL81N608MLZhma3ruL8qTM4xcpYECGut8KSxRY59g=
-gitlab.com/golang-commonmark/linkify v0.0.0-20191026162114-a0c2df6c8f82/go.mod h1:Gn+LZmCrhPECMD3SOKlE+BOHwhOYD9j7WT9NUtkCrC8=
-gitlab.com/golang-commonmark/markdown v0.0.0-20211110145824-bf3e522c626a h1:O85GKETcmnCNAfv4Aym9tepU8OE0NmcZNqPlXcsBKBs=
-gitlab.com/golang-commonmark/markdown v0.0.0-20211110145824-bf3e522c626a/go.mod h1:LaSIs30YPGs1H5jwGgPhLzc8vkNc/k0rDX/fEZqiU/M=
-gitlab.com/golang-commonmark/mdurl v0.0.0-20191124015652-932350d1cb84 h1:qqjvoVXdWIcZCLPMlzgA7P9FZWdPGPvP/l3ef8GzV6o=
-gitlab.com/golang-commonmark/mdurl v0.0.0-20191124015652-932350d1cb84/go.mod h1:IJZ+fdMvbW2qW6htJx7sLJ04FEs4Ldl/MDsJtMKywfw=
-gitlab.com/golang-commonmark/puny v0.0.0-20191124015043-9f83538fa04f h1:Wku8eEdeJqIOFHtrfkYUByc4bCaTeA6fL0UJgfEiFMI=
-gitlab.com/golang-commonmark/puny v0.0.0-20191124015043-9f83538fa04f/go.mod h1:Tiuhl+njh/JIg0uS/sOJVYi0x2HEa5rc1OAaVsb5tAs=
-gitlab.com/opennota/wd v0.0.0-20180912061657-c5d65f63c638 h1:uPZaMiz6Sz0PZs3IZJWpU5qHKGNy///1pacZC9txiUI=
-gitlab.com/opennota/wd v0.0.0-20180912061657-c5d65f63c638/go.mod h1:EGRJaqe2eO9XGmFtQCvV3Lm9NLico3UhFwUpCG/+mVU=
-golang.org/x/sys v0.1.0 h1:kunALQeHf1/185U1i0GOB/fy1IPRDDpuoOOqRReG57U=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
+github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
+github.com/yuin/goldmark v1.7.13 h1:GPddIs617DnBLFFVJFgpo1aBfe/4xcvMc3SB5t/D0pA=
+github.com/yuin/goldmark v1.7.13/go.mod h1:ip/1k0VRfGynBgxOz0yCqHrbZXhcjxyuS66Brc7iBKg=
+go.abhg.dev/goldmark/mermaid v0.6.0 h1:VvkYFWuOjD6cmSBVJpLAtzpVCGM1h0B7/DQ9IzERwzY=
+go.abhg.dev/goldmark/mermaid v0.6.0/go.mod h1:uMc+PcnIH2NVL7zjH10Q1wr7hL3+4n4jUMifhyBYB9I=
 golang.org/x/sys v0.1.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
-golang.org/x/text v0.3.8 h1:nAL+RVCQ9uMn3vJZbV+MRnydTJFPf8qqY42YiA6MrqY=
-golang.org/x/text v0.3.8/go.mod h1:E6s5w1FMmriuDzIBO73fBruAKo1PCIq6d2Q6DHfQ8WQ=
-golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/sys v0.34.0 h1:H5Y5sJ2L2JRdyv7ROF1he/lPdvFsd0mJHFw2ThKHxLA=
+golang.org/x/sys v0.34.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

main.go

@@ -1,6 +1,7 @@
 package main
 
 import (
+	"bytes"
 	"crypto/rand"
 	"encoding/base64"
 	_ "embed"
@@ -16,7 +17,13 @@ import (
 	"strings"
 
 	"github.com/pkg/browser"
-	"gitlab.com/golang-commonmark/markdown"
+	"github.com/yuin/goldmark"
+	"github.com/yuin/goldmark/ast"
+	"github.com/yuin/goldmark/extension"
+	"github.com/yuin/goldmark/parser"
+	"github.com/yuin/goldmark/renderer/html"
+	"github.com/yuin/goldmark/text"
+	"go.abhg.dev/goldmark/mermaid"
 )
 
 var appVersion string
@@ -25,12 +32,20 @@ var appVersion string
 // Captures: 1=prefix, 2=opening quote, 3=src path, 4=closing quote
 var imgSrcRegex = regexp.MustCompile(`(<img[^>]*\ssrc=)(["']?)([^"'\s>]+)(["']?)`)
 
+// cdnScriptRegex matches Mermaid CDN script tags followed by initialization script
+// Goldmark's mermaid extension inserts these tags that need to be replaced with embedded version
+// Pattern allows for flexible whitespace between elements
+var cdnScriptRegex = regexp.MustCompile(`<script\s+src\s*=\s*"https://cdn\.jsdelivr\.net/npm/mermaid[^"]*"\s*>\s*</script>\s*<script[^>]*>\s*mermaid\.initialize\s*\([^)]*\)\s*;\s*</script>`)
+
 //go:embed github-markdown.css
 var style string
 
 //go:embed template.html
 var template string
 
+//go:embed mermaid.min.js
+var mermaidJS string
+
 func main() {
 	var outfilePtr = flag.String("o", "", "Output filename. (Optional)")
 	var versionPtr = flag.Bool("version", false, "Prints mdview version.")
@@ -57,20 +72,43 @@ func main() {
 	dat, err := os.ReadFile(inputFilename)
 	check(err)
 
-	md := markdown.New(
-		markdown.HTML(true),
-		markdown.Nofollow(true),
-		markdown.Tables(true),
-		markdown.Typographer(true))
-
-	markdownTokens := md.Parse(dat)
-
-	// Convert relative image links to data URIs
+	// Convert relative image links to data URIs in the markdown source
 	baseDir := filepath.Dir(inputFilename)
-	processImageTokens(markdownTokens, baseDir)
+	processedMarkdown := processMarkdownImages(string(dat), baseDir)
+	processedBytes := []byte(processedMarkdown)
+
+	// Create Goldmark markdown processor with extensions
+	md := goldmark.New(
+		goldmark.WithExtensions(
+			extension.GFM,        // GitHub Flavored Markdown (includes tables)
+			extension.Typographer, // Smart quotes, dashes, etc.
+			&mermaid.Extender{
+				NoScript: true,   // Don't add CDN script tags - we'll add our own embedded version
+			},
+		),
+		goldmark.WithParserOptions(
+			parser.WithAutoHeadingID(), // Auto-generate heading IDs
+		),
+		goldmark.WithRendererOptions(
+			html.WithUnsafe(), // Allow raw HTML (equivalent to markdown.HTML(true))
+		),
+	)
+
+	// Parse markdown to AST
+	doc := md.Parser().Parse(text.NewReader(processedBytes))
 
-	html := md.RenderTokensToString(markdownTokens)
-	title := getTitle(markdownTokens)
+	// Extract title from AST
+	title := getTitleFromAST(doc, processedBytes)
+
+	// Render to HTML
+	var buf bytes.Buffer
+	if err := md.Renderer().Render(&buf, processedBytes, doc); err != nil {
+		log.Fatal(err)
+	}
+	htmlContent := buf.String()
+
+	// Replace CDN-based Mermaid scripts with inline script
+	htmlContent = embedMermaidScript(htmlContent)
 
 	outfilePath := *outfilePtr
 	if outfilePath == "" {
@@ -87,7 +125,7 @@ func main() {
 		actualStyle = style
 	}
 
-	_, err = fmt.Fprintf(f, template, actualStyle, title, html)
+	_, err = fmt.Fprintf(f, template, actualStyle, title, htmlContent)
 	check(err)
 	f.Sync()
 	browser.Stderr = nil
@@ -145,68 +183,67 @@ func check(e error) {
 	}
 }
 
-func getTitle(tokens []markdown.Token) string {
-	var result string
-	if len(tokens) > 0 {
-		for i := 0; i < len(tokens); i++ {
-			if topLevelHeading, ok := tokens[i].(*markdown.HeadingOpen); ok {
-				for j := i + 1; j < len(tokens); j++ {
-					if token, ok := tokens[j].(*markdown.HeadingClose); ok && token.Lvl == topLevelHeading.Lvl {
-						break
-					}
-					result += getText(tokens[j])
-				}
-				result = strings.TrimSpace(result)
-				break
-			}
+func getTitleFromAST(doc ast.Node, source []byte) string {
+	var title string
+	ast.Walk(doc, func(n ast.Node, entering bool) (ast.WalkStatus, error) {
+		if !entering {
+			return ast.WalkContinue, nil
 		}
-	}
-
-	return result
+		if heading, ok := n.(*ast.Heading); ok && heading.Level == 1 {
+			// Extract all text from heading and its children recursively
+			var buf bytes.Buffer
+			extractText(heading, source, &buf)
+			title = strings.TrimSpace(buf.String())
+			return ast.WalkStop, nil
+		}
+		return ast.WalkContinue, nil
+	})
+	return title
 }
 
-func getText(token markdown.Token) string {
-	switch token := token.(type) {
-	case *markdown.Text:
-		return token.Content
-	case *markdown.Inline:
-		result := ""
-		for _, token := range token.Children {
-			result += getText(token)
+// extractText recursively extracts text from a node and its children
+func extractText(node ast.Node, source []byte, buf *bytes.Buffer) {
+	for child := node.FirstChild(); child != nil; child = child.NextSibling() {
+		switch n := child.(type) {
+		case *ast.Text:
+			buf.Write(n.Segment.Value(source))
+		case *ast.String:
+			buf.Write(n.Value)
+		default:
+			// Recursively extract text from other node types (emphasis, strong, links, etc.)
+			extractText(child, source, buf)
 		}
-		return result
 	}
-	return ""
-
 }
 
 func isSnap() bool {
 	return os.Getenv("SNAP_USER_COMMON") != ""
 }
 
-// processImageTokens walks through markdown tokens and converts relative image paths to data URIs
-func processImageTokens(tokens []markdown.Token, baseDir string) {
-	for _, token := range tokens {
-		switch t := token.(type) {
-		case *markdown.Image:
-			if isRelativePath(t.Src) {
-				if dataURI := imageToDataURI(t.Src, baseDir); dataURI != "" {
-					t.Src = dataURI
-				}
-			}
-		case *markdown.HTMLInline:
-			// Process inline HTML that may contain <img> tags
-			t.Content = processHTMLImages(t.Content, baseDir)
-		case *markdown.HTMLBlock:
-			// Process block HTML that may contain <img> tags
-			t.Content = processHTMLImages(t.Content, baseDir)
-		case *markdown.Inline:
-			// Recursively process child tokens
-			if t.Children != nil {
-				processImageTokens(t.Children, baseDir)
+// processMarkdownImages processes markdown source and converts relative image paths to data URIs
+func processMarkdownImages(markdown string, baseDir string) string {
+	// Process markdown image syntax: ![alt](path)
+	imgMarkdownRegex := regexp.MustCompile(`!\[([^\]]*)\]\(([^)]+)\)`)
+	markdown = imgMarkdownRegex.ReplaceAllStringFunc(markdown, func(match string) string {
+		parts := imgMarkdownRegex.FindStringSubmatch(match)
+		if len(parts) < 3 {
+			return match
+		}
+		alt := parts[1]
+		imgPath := parts[2]
+
+		if isRelativePath(imgPath) {
+			if dataURI := imageToDataURI(imgPath, baseDir); dataURI != "" {
+				return fmt.Sprintf("![%s](%s)", alt, dataURI)
 			}
 		}
-	}
+		return match
+	})
+
+	// Process HTML img tags in markdown
+	markdown = processHTMLImages(markdown, baseDir)
+
+	return markdown
 }
 
 // processHTMLImages processes HTML content and converts relative image src attributes to data URIs
@@ -359,3 +396,22 @@ func getMimeType(path string) string {
 		return "image/*"
 	}
 }
+
+// embedMermaidScript adds the embedded Mermaid.js library to the HTML content
+// Since we set NoScript: true on the Mermaid extender, we need to manually add the script
+func embedMermaidScript(htmlContent string) string {
+	// Check if there are any mermaid diagrams in the content
+	// The Goldmark mermaid extension uses class="mermaid" for diagram blocks
+	if !strings.Contains(htmlContent, `class="mermaid"`) {
+		return htmlContent // No mermaid diagrams, don't add the script
+	}
+
+	// Escape any </script> tags (with closing >) inside the mermaid.js code 
+	// to prevent premature script closure. The standard way is to escape the forward slash.
+	escapedMermaidJS := strings.ReplaceAll(mermaidJS, "</script>", "<\\/script>")
+
+	// Add the embedded Mermaid.js and initialization at the end of the content
+	inlineScript := fmt.Sprintf("<script>%s</script><script>mermaid.initialize({startOnLoad: true});</script>", escapedMermaidJS)
+
+	return htmlContent + inlineScript
+}