package converter
import (
"archive/zip"
"fmt"
"io"
"os"
"path/filepath"
"regexp"
"sort"
"strings"
"time"
"github.com/russross/blackfriday/v2"
)
// convertEbook handles epub ↔ txt/html/md/pdf conversions.
func convertEbook(inputPath, outputPath, sourceExt, targetFormat string) error {
if sourceExt == "epub" {
return convertFromEpub(inputPath, outputPath, targetFormat)
}
// txt/html/md → epub
return convertToEpub(inputPath, outputPath, sourceExt)
}
// ─── EPUB → other formats ────────────────────────────────────
func convertFromEpub(inputPath, outputPath, targetFormat string) error {
title, htmlChapters, err := extractEpubContent(inputPath)
if err != nil {
return fmt.Errorf("reading epub: %w", err)
}
fullHTML := strings.Join(htmlChapters, "\n
\n")
switch targetFormat {
case "txt":
text := stripHTMLTags(fullHTML)
return os.WriteFile(outputPath, []byte(text), 0o644)
case "html":
styled := fmt.Sprintf(`
%s
%s
%s`, escapeHTML(title), escapeHTML(title), fullHTML)
return os.WriteFile(outputPath, []byte(styled), 0o644)
case "md":
md := "# " + title + "\n\n" + ebookHTMLToMarkdown(fullHTML)
return os.WriteFile(outputPath, []byte(md), 0o644)
case "pdf":
text := stripHTMLTags(fullHTML)
return textToPDF(text, outputPath)
default:
return fmt.Errorf("unsupported target for epub: %s", targetFormat)
}
}
// ─── Other formats → EPUB ────────────────────────────────────
func convertToEpub(inputPath, outputPath, sourceExt string) error {
raw, err := os.ReadFile(inputPath)
if err != nil {
return fmt.Errorf("reading input: %w", err)
}
content := string(raw)
title := strings.TrimSuffix(filepath.Base(inputPath), filepath.Ext(inputPath))
var htmlContent string
switch sourceExt {
case "txt":
// Split into paragraphs on double newlines
paragraphs := strings.Split(content, "\n\n")
var sb strings.Builder
for _, p := range paragraphs {
p = strings.TrimSpace(p)
if p != "" {
sb.WriteString("" + escapeHTML(p) + "
\n")
}
}
htmlContent = sb.String()
case "html", "htm":
// Extract body if full document
bodyRe := regexp.MustCompile(`(?is)]*>(.*) `)
if m := bodyRe.FindStringSubmatch(content); m != nil {
htmlContent = m[1]
} else {
htmlContent = content
}
case "md":
htmlBytes := blackfriday.Run([]byte(content))
htmlContent = string(htmlBytes)
default:
return fmt.Errorf("unsupported source for epub creation: %s", sourceExt)
}
return writeEpubFile(outputPath, title, htmlContent)
}
// ─── EPUB reader ─────────────────────────────────────────────
func extractEpubContent(path string) (string, []string, error) {
r, err := zip.OpenReader(path)
if err != nil {
return "", nil, err
}
defer r.Close()
title := "Untitled"
var htmlChapters []string
// Find OPF file via container.xml
var opfPath string
for _, f := range r.File {
if f.Name == "META-INF/container.xml" {
data, err := readZipFile(f)
if err != nil {
break
}
re := regexp.MustCompile(`full-path="([^"]+)"`)
if m := re.FindStringSubmatch(string(data)); m != nil {
opfPath = m[1]
}
break
}
}
if opfPath != "" {
// Read OPF
opfContent := ""
for _, f := range r.File {
if f.Name == opfPath {
data, err := readZipFile(f)
if err == nil {
opfContent = string(data)
}
break
}
}
if opfContent != "" {
// Extract title
titleRe := regexp.MustCompile(`