Add DOCX conversion support using Pandoc and update README.md with new requirements

Author: sametcn99

README.md

@@ -62,7 +62,8 @@ Terminal-based file converter built with Go. It provides a modern, user-friendly
 
 | Input                                     | Output                                                                    |
 |-------------------------------------------|---------------------------------------------------------------------------|
-| `.pdf`, `.md`, `.html`                    | `.pdf`, `.md`, `.html`, `.epub`, `.mobi`, `.azw`, `.azw3`, `.fb2`         |
+| `.pdf`, `.md`, `.html`                    | `.pdf`, `.md`, `.html`, `.docx`, `.epub`, `.mobi`, `.azw`, `.azw3`, `.fb2` |
+| `.docx`                                   | `.md`, `.html`, `.txt`                                                    |
 | `.epub`, `.mobi`, `.azw`, `.azw3`, `.fb2` | `.epub`, `.mobi`, `.azw`, `.azw3`, `.fb2`, `.pdf`, `.html`, `.txt`, `.md` |
 | `.csv`                                    | `.xlsx`                                                                   |
 | `.xlsx`, `.xls`                           | `.csv`                                                                    |
@@ -73,24 +74,31 @@ Terminal-based file converter built with Go. It provides a modern, user-friendly
 - Markdown to styled HTML with responsive design
 - Markdown/HTML to EPUB conversion
 - EPUB/MOBI/AZW/AZW3/FB2 conversions via Calibre (if installed)
+- DOCX conversions via Pandoc (if installed)
 - PDF compression/optimization
 - CSV to Excel conversion with styled headers and auto-fit columns
 - Excel to CSV export (exports first sheet)
 
-> **Note:** Video and audio conversion requires `ffmpeg`. Ebook conversions beyond EPUB require Calibre's `ebook-convert`.
+> **Note:** Video and audio conversion requires `ffmpeg`. Ebook conversions beyond EPUB require Calibre's `ebook-convert`. DOCX conversions require Pandoc.
 
 **PATH Note (ebook-convert):**
 - **Linux:** Typically available at `/usr/bin/ebook-convert` (or `/snap/bin/ebook-convert`). Ensure the directory is on `PATH`.
 - **macOS (Homebrew):** `/opt/homebrew/bin/ebook-convert` (Apple Silicon) or `/usr/local/bin/ebook-convert` (Intel).
 - **Windows:** `C:\Program Files\Calibre2\ebook-convert.exe` (or `C:\Program Files (x86)\Calibre2\ebook-convert.exe`). Add the folder to `PATH` if not detected.
 
+**PATH Note (pandoc):**
+- **Linux:** Typically available at `/usr/bin/pandoc` or `/usr/local/bin/pandoc`.
+- **macOS (Homebrew):** `/opt/homebrew/bin/pandoc` (Apple Silicon) or `/usr/local/bin/pandoc` (Intel).
+- **Windows:** `C:\Program Files\Pandoc\pandoc.exe` (or `C:\Program Files (x86)\Pandoc\pandoc.exe`). Add the folder to `PATH` if not detected.
+
 ## Installation
 
 ### Prerequisites
 
 - **Go 1.21+**
 - **ffmpeg** (required for video/audio conversion)
 - **Calibre (ebook-convert)** (required for ebook conversions beyond EPUB)
+- **Pandoc** (required for DOCX conversions)
 
 ### Quick Install
 
@@ -129,13 +137,13 @@ task build
 
 ```bash
 # Ubuntu/Debian
-sudo apt update && sudo apt install ffmpeg calibre
+sudo apt update && sudo apt install ffmpeg calibre pandoc
 
 # Fedora
-sudo dnf install ffmpeg calibre
+sudo dnf install ffmpeg calibre pandoc
 
 # Arch Linux
-sudo pacman -S ffmpeg calibre
+sudo pacman -S ffmpeg calibre pandoc
 
 # Build
 go build -o golter main.go
@@ -156,6 +164,9 @@ brew install ffmpeg
 # Install Calibre (ebook-convert)
 brew install --cask calibre
 
+# Install Pandoc
+brew install pandoc
+
 # Build
 go build -o golter main.go
 
@@ -175,12 +186,18 @@ winget install ffmpeg
 # Calibre (ebook-convert)
 winget install calibre.calibre
 
+# Pandoc
+winget install --id JohnMacFarlane.Pandoc
+
 # Or using chocolatey
 choco install ffmpeg
 
 # Calibre (ebook-convert)
 choco install calibre
 
+# Pandoc
+choco install pandoc
+
 # Build
 go build -o golter.exe main.go
 

internal/converter/document.go

@@ -71,9 +71,11 @@ func (c *DocumentConverter) CanConvert(srcExt, targetExt string) bool {
 	case ".pdf":
 		return targetExt == ".md" || targetExt == ".pdf"
 	case ".md":
-		return targetExt == ".pdf" || targetExt == ".html" || isEbookExt(targetExt)
+		return targetExt == ".pdf" || targetExt == ".html" || targetExt == ".docx" || isEbookExt(targetExt)
 	case ".html":
-		return targetExt == ".md" || isEbookExt(targetExt)
+		return targetExt == ".md" || targetExt == ".docx" || isEbookExt(targetExt)
+	case ".docx":
+		return targetExt == ".md" || targetExt == ".html" || targetExt == ".txt"
 	case ".csv":
 		return targetExt == ".xlsx" || targetExt == ".xls"
 	case ".xlsx", ".xls":
@@ -88,7 +90,7 @@ func (c *DocumentConverter) CanConvert(srcExt, targetExt string) bool {
 }
 
 func (c *DocumentConverter) SupportedSourceExtensions() []string {
-	return []string{".pdf", ".md", ".html", ".epub", ".mobi", ".azw", ".azw3", ".fb2", ".csv", ".xlsx", ".xls"}
+	return []string{".pdf", ".md", ".html", ".docx", ".epub", ".mobi", ".azw", ".azw3", ".fb2", ".csv", ".xlsx", ".xls"}
 }
 
 func (c *DocumentConverter) SupportedTargetFormats(srcExt string) []string {
@@ -101,9 +103,11 @@ func (c *DocumentConverter) SupportedTargetFormats(srcExt string) []string {
 	case ".pdf":
 		return []string{".md", ".pdf"} // .pdf -> .pdf implies compression
 	case ".md":
-		return []string{".html", ".pdf", ".epub", ".mobi", ".azw", ".azw3", ".fb2"}
+		return []string{".html", ".pdf", ".docx", ".epub", ".mobi", ".azw", ".azw3", ".fb2"}
 	case ".html":
-		return []string{".md", ".epub", ".mobi", ".azw", ".azw3", ".fb2"}
+		return []string{".md", ".docx", ".epub", ".mobi", ".azw", ".azw3", ".fb2"}
+	case ".docx":
+		return []string{".md", ".html", ".txt"}
 	case ".csv":
 		return []string{".xlsx"}
 	case ".xlsx", ".xls":
@@ -145,6 +149,8 @@ func (c *DocumentConverter) Convert(src, target string, opts Options) error {
 			return c.convertMarkdownToHTML(src, target)
 		} else if targetExt == ".pdf" {
 			return c.convertMarkdownToPDF(src, target)
+		} else if targetExt == ".docx" {
+			return c.convertWithPandoc(src, target, opts)
 		} else if targetExt == ".epub" {
 			return c.convertMarkdownToEPUB(src, target)
 		} else if isEbookExt(targetExt) {
@@ -153,11 +159,17 @@ func (c *DocumentConverter) Convert(src, target string, opts Options) error {
 	case ".html":
 		if targetExt == ".md" {
 			return c.convertHTMLToMarkdown(src, target)
+		} else if targetExt == ".docx" {
+			return c.convertWithPandoc(src, target, opts)
 		} else if targetExt == ".epub" {
 			return c.convertHTMLToEPUB(src, target)
 		} else if isEbookExt(targetExt) {
 			return c.convertHTMLToEbook(src, target, opts)
 		}
+	case ".docx":
+		if targetExt == ".md" || targetExt == ".html" || targetExt == ".txt" {
+			return c.convertWithPandoc(src, target, opts)
+		}
 	case ".csv":
 		if targetExt == ".xlsx" || targetExt == ".xls" {
 			return c.convertCSVToExcel(src, target)
@@ -471,6 +483,28 @@ func (c *DocumentConverter) convertEbookWithCalibre(src, target string, opts Opt
 	return nil
 }
 
+func (c *DocumentConverter) convertWithPandoc(src, target string, opts Options) error {
+	_, err := exec.LookPath("pandoc")
+	if err != nil {
+		return fmt.Errorf("pandoc not found: please install Pandoc to convert DOCX formats (https://pandoc.org)")
+	}
+
+	args := []string{src, "-o", target}
+	if extra, ok := opts["pandocArgs"].([]string); ok && len(extra) > 0 {
+		args = append(args, extra...)
+	} else if extraStr, ok := opts["pandocArgs"].(string); ok && strings.TrimSpace(extraStr) != "" {
+		args = append(args, strings.Fields(extraStr)...)
+	}
+
+	cmd := exec.Command("pandoc", args...)
+	output, err := cmd.CombinedOutput()
+	if err != nil {
+		return fmt.Errorf("pandoc failed: %w\nOutput: %s", err, string(output))
+	}
+
+	return nil
+}
+
 // convertCSVToExcel converts a CSV file to Excel format
 func (c *DocumentConverter) convertCSVToExcel(src, target string) error {
 	// Open CSV file

internal/converter/document_test.go

@@ -20,7 +20,7 @@ func TestDocumentConverter_SupportedExtensions(t *testing.T) {
 	if len(srcExts) == 0 {
 		t.Error("SupportedSourceExtensions returned empty list")
 	}
-	expectedSrc := []string{".pdf", ".md", ".html", ".epub", ".mobi", ".azw", ".azw3", ".fb2", ".csv", ".xlsx", ".xls"}
+	expectedSrc := []string{".pdf", ".md", ".html", ".docx", ".epub", ".mobi", ".azw", ".azw3", ".fb2", ".csv", ".xlsx", ".xls"}
 	for _, exp := range expectedSrc {
 		found := false
 		for _, got := range srcExts {
@@ -295,6 +295,43 @@ func TestDocumentConverter_Convert_EbookFromMarkdownAndHTML(t *testing.T) {
 	}
 }
 
+func TestDocumentConverter_Convert_DocxPandoc(t *testing.T) {
+	if !ensurePandocInPath(t) {
+		t.Skip("pandoc not found, skipping DOCX conversion tests")
+	}
+
+	tmpDir, err := os.MkdirTemp("", "golter_docx_test")
+	if err != nil {
+		t.Fatalf("failed to create temp dir: %v", err)
+	}
+	defer os.RemoveAll(tmpDir)
+
+	c := &DocumentConverter{}
+
+	mdPath := filepath.Join(tmpDir, "src.md")
+	if err := os.WriteFile(mdPath, []byte("# Title\n\nHello docx"), 0644); err != nil {
+		t.Fatalf("failed to write md: %v", err)
+	}
+
+	// MD -> DOCX
+	docxPath := filepath.Join(tmpDir, "out.docx")
+	if err := c.Convert(mdPath, docxPath, Options{}); err != nil {
+		t.Fatalf("Convert(MD->DOCX) failed: %v", err)
+	}
+	if _, err := os.Stat(docxPath); os.IsNotExist(err) {
+		t.Fatalf("Target DOCX not created: %s", docxPath)
+	}
+
+	// DOCX -> MD
+	backToMD := filepath.Join(tmpDir, "back.md")
+	if err := c.Convert(docxPath, backToMD, Options{}); err != nil {
+		t.Fatalf("Convert(DOCX->MD) failed: %v", err)
+	}
+	if _, err := os.Stat(backToMD); os.IsNotExist(err) {
+		t.Fatalf("Target MD not created: %s", backToMD)
+	}
+}
+
 func TestDocumentConverter_Name(t *testing.T) {
 	c := &DocumentConverter{}
 	if !strings.Contains(c.Name(), "Document Converter") {
@@ -317,14 +354,22 @@ func TestDocumentConverter_CanConvert(t *testing.T) {
 		// Markdown
 		{".md", ".pdf", true},
 		{".md", ".html", true},
+		{".md", ".docx", true},
 		{".md", ".epub", true},
 		{".md", ".txt", false},
 
 		// HTML
 		{".html", ".md", true},
+		{".html", ".docx", true},
 		{".html", ".epub", true},
 		{".html", ".pdf", false},
 
+		// DOCX
+		{".docx", ".md", true},
+		{".docx", ".html", true},
+		{".docx", ".txt", true},
+		{".docx", ".pdf", false},
+
 		// CSV/Excel
 		{".csv", ".xlsx", true},
 		{".csv", ".xls", true},
@@ -364,8 +409,9 @@ func TestDocumentConverter_SupportedTargetFormats(t *testing.T) {
 		want []string
 	}{
 		{".pdf", []string{".md", ".pdf"}},
-		{".md", []string{".html", ".pdf", ".epub", ".mobi", ".azw", ".azw3", ".fb2"}},
+		{".md", []string{".html", ".pdf", ".docx", ".epub", ".mobi", ".azw", ".azw3", ".fb2"}},
 		{".csv", []string{".xlsx"}},
+		{".docx", []string{".md", ".html", ".txt"}},
 		{".epub", []string{".pdf", ".md", ".html", ".mobi", ".azw", ".azw3", ".fb2", ".txt"}},
 		{".mobi", []string{".epub", ".azw", ".azw3", ".fb2", ".pdf", ".html", ".txt", ".md"}},
 	}
@@ -434,3 +480,44 @@ func ensureEbookConvertInPath(t *testing.T) bool {
 
 	return false
 }
+
+func ensurePandocInPath(t *testing.T) bool {
+	binName := "pandoc"
+	if runtime.GOOS == "windows" {
+		binName = "pandoc.exe"
+	}
+
+	if _, err := exec.LookPath(binName); err == nil {
+		return true
+	}
+
+	var candidates []string
+	if runtime.GOOS == "windows" {
+		candidates = []string{
+			`C:\\Program Files\\Pandoc\\pandoc.exe`,
+			`C:\\Program Files (x86)\\Pandoc\\pandoc.exe`,
+		}
+	} else {
+		candidates = []string{
+			"/usr/bin/pandoc",
+			"/usr/local/bin/pandoc",
+			"/opt/homebrew/bin/pandoc",
+		}
+	}
+
+	for _, p := range candidates {
+		if _, err := os.Stat(p); err == nil {
+			dir := filepath.Dir(p)
+			current := os.Getenv("PATH")
+			if !strings.Contains(current, dir) {
+				if err := os.Setenv("PATH", dir+string(os.PathListSeparator)+current); err != nil {
+					t.Logf("failed to update PATH for pandoc: %v", err)
+					return false
+				}
+			}
+			return true
+		}
+	}
+
+	return false
+}

internal/version/version.go

@@ -11,7 +11,7 @@ import (
 
 // Current represents the current version of the application
 const (
-	Current = "0.1.1"
+	Current = "0.1.2"
 	Repo    = "sametcn99/golter"
 )