Clean mailbox preview rendering

2026-07-13 07:46:07 +02:00 · 2026-07-13 07:46:07 +02:00 · 8823b431f4
commit 8823b431f4
parent 647ce4bc90
2 changed files with 132 additions and 4 deletions
--- a/backend/06-mbox.go
+++ b/backend/06-mbox.go
@ -4,6 +4,7 @@ import (
 	"bytes"
 	"encoding/base64"
 	"fmt"
+	"html"
 	"io"
 	"mime"
 	"mime/multipart"
@ -205,9 +206,127 @@ func extractTextBody(h headerGetter, body []byte) string {
 		}
 		return ""
 	}
+	if strings.HasPrefix(mediaType, "text/html") || looksLikeHTML(decoded) {
+		return htmlToText(string(decoded))
+	}
 	return string(decoded)
 }

+func looksLikeHTML(body []byte) bool {
+	s := strings.ToLower(strings.TrimSpace(string(body)))
+	return strings.HasPrefix(s, "<!doctype html") || strings.HasPrefix(s, "<html") || strings.Contains(s, "<body")
+}
+
+func htmlToText(s string) string {
+	s = stripHTMLBlock(s, "script")
+	s = stripHTMLBlock(s, "style")
+	s = markHTMLBreaks(s)
+	var b strings.Builder
+	inTag := false
+	lastSpace := false
+	for _, r := range s {
+		switch r {
+		case '<':
+			inTag = true
+			if !lastSpace {
+				b.WriteByte(' ')
+				lastSpace = true
+			}
+		case '>':
+			inTag = false
+		default:
+			if inTag {
+				continue
+			}
+			if r == '\n' {
+				b.WriteByte('\n')
+				lastSpace = true
+				continue
+			}
+			if r == '\r' || r == '\t' || r == ' ' {
+				if !lastSpace {
+					b.WriteByte(' ')
+					lastSpace = true
+				}
+				continue
+			}
+			b.WriteRune(r)
+			lastSpace = false
+		}
+	}
+	text := html.UnescapeString(b.String())
+	lines := strings.Split(text, "\n")
+	out := make([]string, 0, len(lines))
+	for _, line := range lines {
+		line = strings.TrimSpace(line)
+		if line != "" {
+			out = append(out, line)
+		}
+	}
+	if len(out) == 0 {
+		return strings.TrimSpace(text)
+	}
+	return strings.Join(out, "\n")
+}
+
+func markHTMLBreaks(s string) string {
+	repls := []struct {
+		Needle string
+		With   string
+	}{
+		{"<br>", "\n"},
+		{"<br/>", "\n"},
+		{"<br />", "\n"},
+		{"</p>", "\n"},
+		{"</div>", "\n"},
+		{"</tr>", "\n"},
+		{"</td>", " "},
+		{"</th>", " "},
+		{"</li>", "\n"},
+	}
+	for _, repl := range repls {
+		s = replaceCaseInsensitive(s, repl.Needle, repl.With)
+	}
+	return s
+}
+
+func replaceCaseInsensitive(s, old, new string) string {
+	var b strings.Builder
+	lower := strings.ToLower(s)
+	needle := strings.ToLower(old)
+	for {
+		i := strings.Index(lower, needle)
+		if i < 0 {
+			b.WriteString(s)
+			return b.String()
+		}
+		b.WriteString(s[:i])
+		b.WriteString(new)
+		cut := i + len(old)
+		s = s[cut:]
+		lower = lower[cut:]
+	}
+}
+
+func stripHTMLBlock(s, tag string) string {
+	lower := strings.ToLower(s)
+	open := "<" + tag
+	close := "</" + tag + ">"
+	for {
+		start := strings.Index(lower, open)
+		if start < 0 {
+			return s
+		}
+		end := strings.Index(lower[start:], close)
+		if end < 0 {
+			return s[:start]
+		}
+		end += start + len(close)
+		s = s[:start] + " " + s[end:]
+		lower = strings.ToLower(s)
+	}
+}
+
 func decodeTransfer(body []byte, enc string) []byte {
 	switch strings.ToLower(strings.TrimSpace(enc)) {
 	case "quoted-printable":