Add option to keep converted HTML files

README.md

@@ -1,14 +1,11 @@
-##EML to PDF Converter
-
-### Homepage
-<a href="https://eml-to-pdf.com">eml-to-pdf.com</a>
+##EML to PDF/HTML Converter
 
 ### Screenshot
-<img src="https://www.whitebyte.info/wp-content/uploads/2015/02/scr1.png" />
+![Screenshot](screenshot.png?raw=true)
 
 ### Commandline Interface
 ```
-Usage: EMLtoPDFConverter [options] 
+Usage: emailconverter [options] <EML-File>
   Options:
     -d, --debug
        Debug mode
@@ -24,17 +21,20 @@ Usage: EMLtoPDFConverter [options]
        Default: false
     -ad, --extract-attachments-directory
        Extract Attachments to this Directory, if this option is not present the
-       directory is besides the pdf as "-attachments".
-    -?, --help
+       directory is besides the output file as "<output-filename>-attachments".
+    -h, --help
        Print this help.
        Default: false
     -hh, --hide-headers
        Do not add email headers (subject, from, etc.) at the beginning of the
-       PDF document.
+       PDF/HTML document.
+       Default: false
+    --html
+       Produce HTML document instead of PDF.
        Default: false
     -o, --output-filepath
-       Filepath of the produced PDF document. If this option is ommited the PDF
-       will be placed alongside the EML File.
+       Filepath of the produced PDF/HTML document. If this option is ommited the
+       PDF/HTML will be placed alongside the EML File.
     -p, --proxy
        Proxy (e.g. "http://10.64.1.74:81"). If "auto" is supplied the default
        system proxy will be used.
@@ -65,3 +65,10 @@ Executes the unit tests and generates various reports (jacoco, checkstyle, findb
 
 ### License
 The code available under the terms of the GNU Affero General Public License (AGPL). This means you have to release the source code of applications that use this software. If you can't do so you can <a target="_blank" href="https://eml-to-pdf.com">buy a commercial license</a>.
+
+### Download
+A Java installation is required. If you haven't installed Java yet get it [here](https://www.java.com/download) completely free.
+
+Win32 binaries and compiled jar for non-windows Systems (MacOs, Linux, etc) can be found in [Releases](../../releases) section.
+
+*Note: If you have another system than Windows you need to install the free [wkhtmltopdf](http://wkhtmltopdf.org/downloads.html) and add it's binary to your PATH variable.*

src/main/java/cli/CommandLineParameters.java

@@ -31,7 +31,7 @@ public class CommandLineParameters {
 	@Parameter(description = "<EML-File>", arity = 1)
 	private List<String> files = new ArrayList<String>();
 
-	@Parameter(names = {"-o", "--output-filepath"}, description = "Filepath of the produced PDF document. If this option is ommited the PDF will be placed alongside the EML File.")
+	@Parameter(names = {"-o", "--output-filepath"}, description = "Filepath of the produced PDF/HTML document. If this option is ommited the PDF/HTML will be placed alongside the EML File.")
 	private String output;
 
 	@Parameter(names = {"-p", "--proxy"}, description = "Proxy (e.g. \"http://10.64.1.74:81\"). If \"auto\" is supplied the default system proxy will be used.")
@@ -46,13 +46,16 @@ public class CommandLineParameters {
 	@Parameter(names = {"-q", "--quiet"}, description = "Do not display any messages at all.")
 	private boolean quiet = false;
 
-	@Parameter(names = {"-?", "--help"}, description = "Print this help.", help = true)
+	@Parameter(names = {"-h", "--help"}, description = "Print this help.", help = true)
 	private boolean help;
 
 	@Parameter(names = {"-v", "--version"}, description = "Print the version number.")
 	private boolean version;
 
-	@Parameter(names = {"-hh", "--hide-headers"}, description = "Do not add email headers (subject, from, etc.) at the beginning of the PDF document.")
+	@Parameter(names = {"--html"}, description = "Produce HTML document instead of PDF.")
+	private boolean outputHTML = false;
+
+	@Parameter(names = {"-hh", "--hide-headers"}, description = "Do not add email headers (subject, from, etc.) at the beginning of the PDF/HTML document.")
 	private boolean hideHeaders = false;
 
 	@Parameter(names = {"-a", "--extract-attachments"}, description = "Extract Attachments.")
@@ -61,7 +64,7 @@ public class CommandLineParameters {
 	@Parameter(names = {"-dc", "--disable-crashreports"}, description = "Do not send crash reports to the developer.")
 	private boolean disableCrashreports = false;
 
-	@Parameter(names = {"-ad", "--extract-attachments-directory"}, description = "Extract Attachments to this Directory, if this option is not present the directory is besides the pdf as \"<pdf-name>-attachments\".")
+	@Parameter(names = {"-ad", "--extract-attachments-directory"}, description = "Extract Attachments to this Directory, if this option is not present the directory is besides the output file as \"<output-filename>-attachments\".")
 	private String extractAttachmentsDir;
 
 	@Parameter(names = {"-gui", "--show-graphical-user-interface"}, description = "Show graphical user interface (other parameters are ignored when using this switch).")
@@ -123,6 +126,10 @@ public void setProxy(String proxy) {
 		this.proxy = proxy;
 	}
 
+	public boolean isOutputHTML() {
+		return outputHTML;
+	}
+
 	public boolean isHideHeaders() {
 		return hideHeaders;
 	}

src/main/java/cli/Main.java

@@ -49,7 +49,7 @@ public class Main {
 	public static void main(String[] args) throws IOException {
 		CommandLineParameters cli = new CommandLineParameters();
 		JCommander jCmd = new JCommander(cli, args);
-		jCmd.setProgramName("EMLtoPDFConverter");
+		jCmd.setProgramName("emailconverter");
 
 		if (cli.isGui()) {
 			MainWindow.main(new String[0]);
@@ -120,7 +120,7 @@ public static void main(String[] args) throws IOException {
 		}
 
 		try {
-			MimeMessageConverter.convertToPdf(in, out, cli.isHideHeaders(), cli.isExtractAttachments(), cli.getExtractAttachmentsDir(), extParams);
+			MimeMessageConverter.convertToPdf(in, out, cli.isOutputHTML(), cli.isHideHeaders(), cli.isExtractAttachments(), cli.getExtractAttachmentsDir(), extParams);
 		} catch (Exception e) {
 			Logger.error("The eml could not be converted. Error: %s", Throwables.getStackTraceAsString(e));
 

src/main/java/gui/MainWindow.java

@@ -110,7 +110,7 @@ private void initialize() {
 		frmEmlToPdf = new JFrame();
 		frmEmlToPdf.setIconImage(Toolkit.getDefaultToolkit().getImage(MainWindow.class.getResource("/icons/logo_emlconverter-482_16x16.png")));
 		frmEmlToPdf.setResizable(false);
-		frmEmlToPdf.setTitle("EML to PDF Converter");
+		frmEmlToPdf.setTitle("EML to PDF/HTML Converter");
 		frmEmlToPdf.getContentPane().setBackground(Color.WHITE);
 		frmEmlToPdf.setBackground(Color.WHITE);
 		frmEmlToPdf.setBounds(100, 100, 700, 703);
@@ -218,12 +218,25 @@ public void actionPerformed(ActionEvent e) {
 		frmEmlToPdf.getContentPane().add(panel);
 		panel.setLayout(null);
 
-		final JCheckBox chckbxAddEmailHeaders = new JCheckBox("Add Email headers to the PDF document");
+		final JCheckBox chckbxAddEmailHeaders = new JCheckBox("Add Email headers to the PDF/HTML document");
 		chckbxAddEmailHeaders.setSelected(true);
 		chckbxAddEmailHeaders.setBackground(Color.WHITE);
-		chckbxAddEmailHeaders.setBounds(10, 17, 632, 23);
+		chckbxAddEmailHeaders.setBounds(10, 17, 270, 23);
 		panel.add(chckbxAddEmailHeaders);
 
+		final JRadioButton rdbtnOutputPDF = new JRadioButton("Output PDF");
+		rdbtnOutputPDF.setSelected(true);
+		rdbtnOutputPDF.setBackground(Color.WHITE);
+		rdbtnOutputPDF.setBounds(280, 17, 100, 23);
+		panel.add(rdbtnOutputPDF);
+		final JRadioButton rdbtnOutputHTML = new JRadioButton("Output HTML");
+		rdbtnOutputHTML.setBackground(Color.WHITE);
+		rdbtnOutputHTML.setBounds(380, 17, 100, 23);
+		panel.add(rdbtnOutputHTML);
+		{ButtonGroup bg = new ButtonGroup();
+		bg.add(rdbtnOutputPDF);
+		bg.add(rdbtnOutputHTML);}
+
 		final JRadioButton rdbtnAutomaticProxySelection = new JRadioButton("Automatic Proxy Selection");
 		rdbtnAutomaticProxySelection.setSelected(true);
 		rdbtnAutomaticProxySelection.setEnabled(false);
@@ -303,7 +316,7 @@ public void actionPerformed(ActionEvent e) {
 				new Thread(new Runnable() {
 					@Override
 					public void run() {
-						startConversion(Collections.list(listModel.elements()), chckbxAddEmailHeaders.isSelected(), proxy, chckbxExtractAttachments.isSelected());
+						startConversion(Collections.list(listModel.elements()), rdbtnOutputHTML.isSelected(), chckbxAddEmailHeaders.isSelected(), proxy, chckbxExtractAttachments.isSelected());
 					}
 				}).start();
 			}
@@ -362,10 +375,14 @@ public void actionPerformed(ActionEvent e) {
 	 *
 	 * @param enumeration
 	 */
-	private void startConversion(List<String> l, boolean showHeaders, String proxy, boolean extractAttachments) {
+	private void startConversion(List<String> l, boolean outputHTML, boolean showHeaders, String proxy, boolean extractAttachments) {
 		try {
 			ArrayList<String> argsOptions = new ArrayList<String>();
 
+			if (outputHTML) {
+				argsOptions.add("--html");
+			}
+
 			if (!showHeaders) {
 				argsOptions.add("--hide-headers");
 			}

src/main/java/mimeparser/MimeMessageConverter.java

@@ -79,6 +79,7 @@ public class MimeMessageConverter {
 
 	// html wrapper template for text/plain messages
 	private static final String HTML_WRAPPER_TEMPLATE = "<!DOCTYPE html><html><head><style>body{font-size: 0.5cm;}</style><meta charset=\"%s\"><title>title</title></head><body>%s</body></html>";
+	private static final String HTML_CHARSET_TEMPLATE = "<!DOCTYPE html><html><head><meta charset=\"%s\"><title>title</title></head><body>%s</body></html>";
 	private static final String ADD_HEADER_IFRAME_JS_TAG_TEMPLATE = "<script id=\"header-v6a8oxpf48xfzy0rhjra\" data-file=\"%s\" type=\"text/javascript\">%s</script>";
 	private static final String HEADER_FIELD_TEMPLATE = "<tr><td class=\"header-name\">%s</td><td class=\"header-value\">%s</td></tr>";
 
@@ -108,7 +109,7 @@ private static void execCommand(List<String> command) {
 	 * Convert an EML file to PDF.
 	 * @throws Exception
 	 */
-	public static void convertToPdf(String emlPath, String pdfOutputPath, boolean hideHeaders, boolean extractAttachments, String attachmentsdir, List<String> extParams) throws Exception {
+	public static void convertToPdf(String emlPath, String pdfOutputPath, boolean outputHTML, boolean hideHeaders, boolean extractAttachments, String attachmentsdir, List<String> extParams) throws Exception {
 		Logger.info("Start converting %s to %s", emlPath, pdfOutputPath);
 
 		Logger.debug("Read eml file from %s", emlPath);
@@ -158,6 +159,8 @@ public static void convertToPdf(String emlPath, String pdfOutputPath, boolean hi
 		/* ######### Embed images in the html ######### */
 		String htmlBody = bodyEntry.getEntry();
 		if (bodyEntry.getContentType().match("text/html")) {
+			htmlBody = String.format(HTML_CHARSET_TEMPLATE, charsetName, htmlBody.replaceAll("(?i)</?(html|body)>", ""));
+
 			if (inlineImageMap.size() > 0) {
 				Logger.debug("Embed the referenced images (cid) using <img src=\"data:image ...> syntax");
 
@@ -222,12 +225,11 @@ public String replace(Matcher m) throws Exception {
 		Logger.debug("Body (excerpt): %s", bodyExcerpt);
 		Logger.debug("----------------------------------");
 
-		Logger.info("Start conversion to pdf");
+		Logger.info("Start conversion to " + (outputHTML ? "html" : "pdf"));
+		File pdf = new File(pdfOutputPath);
 
 		File tmpHtmlHeader = null;
 		if (!hideHeaders) {
-			tmpHtmlHeader = File.createTempFile("emailtopdf", ".html");
-			String tmpHtmlHeaderStr = Resources.toString(Resources.getResource("header.html"), StandardCharsets.UTF_8);
 			String headers = "";
 
 			if (!Strings.isNullOrEmpty(from)) {
@@ -246,38 +248,46 @@ public String replace(Matcher m) throws Exception {
 				headers += String.format(HEADER_FIELD_TEMPLATE, "Date", HtmlEscapers.htmlEscaper().escape(sentDateStr));
 			}
 
-			Files.write(String.format(tmpHtmlHeaderStr, headers), tmpHtmlHeader, StandardCharsets.UTF_8);
+			if (outputHTML)
+				htmlBody = htmlBody.replace("</head><body>", "<style>.header-name {color:#9E9E9E; text-align:right;}</style></head><body><table style='border:1px solid #DDD; margin: 8px'>" + headers + "</table>");
+			else {
+				tmpHtmlHeader = new File(pdf.getParentFile(), Files.getNameWithoutExtension(pdfOutputPath) + "_h.html");
+				String tmpHtmlHeaderStr = Resources.toString(Resources.getResource("header.html"), StandardCharsets.UTF_8);
+
+				Files.write(String.format(tmpHtmlHeaderStr, headers), tmpHtmlHeader, StandardCharsets.UTF_8);
 
-			// Append this script tag dirty to the bottom
-			htmlBody += String.format(ADD_HEADER_IFRAME_JS_TAG_TEMPLATE, tmpHtmlHeader.toURI(), Resources.toString(Resources.getResource("contentScript.js"), StandardCharsets.UTF_8));
+				// Append this script tag dirty to the bottom
+				htmlBody += String.format(ADD_HEADER_IFRAME_JS_TAG_TEMPLATE, tmpHtmlHeader.toURI(), Resources.toString(Resources.getResource("contentScript.js"), StandardCharsets.UTF_8));
+			}
 		}
 
-		File tmpHtml = File.createTempFile("emailtopdf", ".html");
-		Logger.debug("Write html to temporary file %s", tmpHtml.getAbsolutePath());
+		File tmpHtml = new File(pdf.getParentFile(), Files.getNameWithoutExtension(pdfOutputPath) + ".html");
+		Logger.debug("Write html to file %s", tmpHtml.getAbsolutePath());
 		Files.write(htmlBody, tmpHtml, Charset.forName(charsetName));
 
-		File pdf = new File(pdfOutputPath);
-		Logger.debug("Write pdf to %s", pdf.getAbsolutePath());
-
-		List<String> cmd = new ArrayList<String>(Arrays.asList("wkhtmltopdf",
-				"--viewport-size", "2480x3508",
-				// "--disable-smart-shrinking",
-				"--image-quality", "100",
-				"--encoding", charsetName));
-		cmd.addAll(extParams);
-		cmd.add(tmpHtml.getAbsolutePath());
-		cmd.add(pdf.getAbsolutePath());
-
-		Logger.debug("Execute: %s", Joiner.on(' ').join(cmd));
-		execCommand(cmd);
-
-		if (!tmpHtml.delete()) {
-			tmpHtml.deleteOnExit();
-		}
+		if (!outputHTML) {
+			Logger.debug("Write pdf to %s", pdf.getAbsolutePath());
 
-		if (tmpHtmlHeader != null) {
-			if (!tmpHtmlHeader.delete()) {
-				tmpHtmlHeader.deleteOnExit();
+			List<String> cmd = new ArrayList<String>(Arrays.asList("wkhtmltopdf",
+					"--viewport-size", "2480x3508",
+					// "--disable-smart-shrinking",
+					"--image-quality", "100",
+					"--encoding", charsetName));
+			cmd.addAll(extParams);
+			cmd.add(tmpHtml.getAbsolutePath());
+			cmd.add(pdf.getAbsolutePath());
+
+			Logger.debug("Execute: %s", Joiner.on(' ').join(cmd));
+			execCommand(cmd);
+
+			if (!tmpHtml.delete()) {
+				tmpHtml.deleteOnExit();
+			}
+
+			if (tmpHtmlHeader != null) {
+				if (!tmpHtmlHeader.delete()) {
+					tmpHtmlHeader.deleteOnExit();
+				}
 			}
 		}