diff --git a/common/build.gradle b/common/build.gradle index b4c51c2f8..871ba43f9 100644 --- a/common/build.gradle +++ b/common/build.gradle @@ -43,7 +43,7 @@ dependencies { api 'jakarta.servlet:jakarta.servlet-api:6.1.0' api 'org.snakeyaml:snakeyaml-engine:2.9' api "org.springdoc:springdoc-openapi-starter-webmvc-ui:2.8.8" - + api 'jakarta.mail:jakarta.mail-api:2.1.3' compileOnly "org.projectlombok:lombok:$lombokVersion" annotationProcessor "org.projectlombok:lombok:$lombokVersion" diff --git a/common/src/main/java/stirling/software/common/model/api/converters/EmlToPdfRequest.java b/common/src/main/java/stirling/software/common/model/api/converters/EmlToPdfRequest.java new file mode 100644 index 000000000..97ea125ad --- /dev/null +++ b/common/src/main/java/stirling/software/common/model/api/converters/EmlToPdfRequest.java @@ -0,0 +1,39 @@ +package stirling.software.common.model.api.converters; + +import io.swagger.v3.oas.annotations.media.Schema; +import lombok.Data; +import lombok.EqualsAndHashCode; +import stirling.software.common.model.api.PDFFile; + +@Data +@EqualsAndHashCode(callSuper = true) +public class EmlToPdfRequest extends PDFFile { + + // fileInput is inherited from PDFFile + + @Schema( + description = "Include email attachments in the PDF output", + requiredMode = Schema.RequiredMode.NOT_REQUIRED, + example = "false") + private boolean includeAttachments = false; + + @Schema( + description = "Maximum attachment size in MB to include (default 10MB, range: 1-100)", + requiredMode = Schema.RequiredMode.NOT_REQUIRED, + example = "10", + minimum = "1", + maximum = "100") + private int maxAttachmentSizeMB = 10; + + @Schema( + description = "Download HTML intermediate file instead of PDF", + requiredMode = Schema.RequiredMode.NOT_REQUIRED, + example = "false") + private boolean downloadHtml = false; + + @Schema( + description = "Include CC and BCC recipients in header (if available)", + requiredMode = Schema.RequiredMode.NOT_REQUIRED, + example = "true") + private boolean includeAllRecipients = true; +} diff --git a/common/src/main/java/stirling/software/common/util/EmlToPdf.java b/common/src/main/java/stirling/software/common/util/EmlToPdf.java new file mode 100644 index 000000000..9de5e206c --- /dev/null +++ b/common/src/main/java/stirling/software/common/util/EmlToPdf.java @@ -0,0 +1,1522 @@ +package stirling.software.common.util; + +import java.io.ByteArrayInputStream; +import java.io.ByteArrayOutputStream; +import java.io.IOException; +import java.io.InputStream; +import java.lang.reflect.Constructor; +import java.lang.reflect.Method; +import java.nio.charset.Charset; +import java.nio.charset.StandardCharsets; +import java.util.ArrayList; +import java.util.Base64; +import java.util.Date; +import java.util.GregorianCalendar; +import java.util.HashMap; +import java.util.List; +import java.util.Locale; +import java.util.Map; +import java.util.Properties; +import java.util.regex.Matcher; +import java.util.regex.Pattern; + +import org.apache.pdfbox.Loader; +import org.apache.pdfbox.cos.COSDictionary; +import org.apache.pdfbox.cos.COSName; +import org.apache.pdfbox.pdmodel.PDDocument; +import org.apache.pdfbox.pdmodel.PDDocumentCatalog; +import org.apache.pdfbox.pdmodel.PDDocumentNameDictionary; +import org.apache.pdfbox.pdmodel.PDEmbeddedFilesNameTreeNode; +import org.apache.pdfbox.pdmodel.PDPage; +import org.apache.pdfbox.pdmodel.common.PDRectangle; +import org.apache.pdfbox.pdmodel.common.filespecification.PDComplexFileSpecification; +import org.apache.pdfbox.pdmodel.common.filespecification.PDEmbeddedFile; +import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationFileAttachment; +import org.apache.pdfbox.pdmodel.interactive.annotation.PDAppearanceDictionary; +import org.apache.pdfbox.pdmodel.interactive.annotation.PDAppearanceStream; +import org.jetbrains.annotations.NotNull; +import org.jetbrains.annotations.Nullable; + +import lombok.Data; +import lombok.Getter; +import lombok.experimental.UtilityClass; +import lombok.extern.slf4j.Slf4j; +import stirling.software.common.model.api.converters.EmlToPdfRequest; + +@Slf4j +@UtilityClass +public class EmlToPdf { + + private static Boolean jakartaMailAvailable = null; + @Getter + private static EmlToPdfRequest request; + @Getter + private static String fileName; + + private static boolean isJakartaMailAvailable() { + if (jakartaMailAvailable == null) { + try { + Class.forName("jakarta.mail.internet.MimeMessage"); + Class.forName("jakarta.mail.Session"); + jakartaMailAvailable = true; + } catch (ClassNotFoundException e) { + jakartaMailAvailable = false; + } + } + return jakartaMailAvailable; + } + + public static String convertEmlToHtml(byte[] emlBytes, EmlToPdfRequest request) throws IOException { + + if (emlBytes == null || emlBytes.length == 0) { + throw new IllegalArgumentException("EML file is empty or null"); + } + + if (isInvalidEmlFormat(emlBytes)) { + throw new IllegalArgumentException("Invalid EML file format"); + } + + if (isJakartaMailAvailable()) { + return convertEmlToHtmlAdvanced(emlBytes, request); + } else { + return convertEmlToHtmlBasic(emlBytes, request); + } + } + + public static byte[] convertEmlToPdf( + String weasyprintPath, + EmlToPdfRequest request, + byte[] emlBytes, + String fileName, + boolean disableSanitize) + throws IOException, InterruptedException { + EmlToPdf.fileName = fileName; + + if (emlBytes == null || emlBytes.length == 0) { + throw new IllegalArgumentException("EML file is empty or null"); + } + + if (isInvalidEmlFormat(emlBytes)) { + throw new IllegalArgumentException("Invalid EML file format"); + } + + // Generate HTML representation + String htmlContent; + EmailContent emailContent = null; + if (isJakartaMailAvailable()) { + emailContent = extractEmailContentAdvanced(emlBytes, request); + htmlContent = generateEnhancedEmailHtml(emailContent, request); + } else { + htmlContent = convertEmlToHtmlBasic(emlBytes, request); + } + + // Create enhanced HTML to PDF request + stirling.software.common.model.api.converters.HTMLToPdfRequest htmlRequest = + createHtmlRequest(request); + + // Convert HTML to PDF first (without attachments in the HTML) + byte[] pdfBytes; + try { + pdfBytes = + FileToPdf.convertHtmlToPdf( + weasyprintPath, + htmlRequest, + htmlContent.getBytes(StandardCharsets.UTF_8), + "email.html", + disableSanitize); + } catch (IOException | InterruptedException e) { + // Try with simplified HTML + String simplifiedHtml = htmlContent.replaceAll("(?i)]*>.*?", ""); + simplifiedHtml = simplifiedHtml.replaceAll("(?i)]*>.*?", ""); + + pdfBytes = + FileToPdf.convertHtmlToPdf( + weasyprintPath, + htmlRequest, + simplifiedHtml.getBytes(StandardCharsets.UTF_8), + "email.html", + disableSanitize); + } + + // Apply attachments to the PDF if available and requested + if (emailContent != null + && request != null + && request.isIncludeAttachments() + && !emailContent.getAttachments().isEmpty()) { + + try { + pdfBytes = attachFilesToPdf(pdfBytes, emailContent.getAttachments()); + } catch (IOException e) { + // Continue with PDF without attachments rather than failing completely + log.warn("Failed to attach files to PDF: {}", e.getMessage()); + } + } + + return pdfBytes; + } + + private static String convertEmlToHtmlBasic( + byte[] emlBytes, EmlToPdfRequest request) { + if (emlBytes == null || emlBytes.length == 0) { + throw new IllegalArgumentException("EML file is empty or null"); + } + + String emlContent = new String(emlBytes, StandardCharsets.UTF_8); + + // Basic email parsing + String subject = extractBasicHeader(emlContent, "Subject:"); + String from = extractBasicHeader(emlContent, "From:"); + String to = extractBasicHeader(emlContent, "To:"); + String cc = extractBasicHeader(emlContent, "Cc:"); + String bcc = extractBasicHeader(emlContent, "Bcc:"); + String date = extractBasicHeader(emlContent, "Date:"); + + // Try to extract HTML content + String htmlBody = extractHtmlBody(emlContent); + if (htmlBody == null) { + String textBody = extractTextBody(emlContent); + htmlBody = + convertTextToHtml( + textBody != null ? textBody : "Email content could not be parsed"); + } + + // Generate HTML with custom styling based on request + StringBuilder html = new StringBuilder(); + html.append("\n"); + html.append("\n"); + html.append("").append(escapeHtml(subject)).append("\n"); + html.append("\n"); + html.append("\n"); + + html.append("
\n"); + html.append("
\n"); + html.append("

").append(escapeHtml(subject)).append("

\n"); + html.append("
\n"); + html.append("
From: ").append(escapeHtml(from)).append("
\n"); + html.append("
To: ").append(escapeHtml(to)).append("
\n"); + + // Include CC and BCC if present and requested + if (request != null && request.isIncludeAllRecipients()) { + if (!cc.trim().isEmpty()) { + html.append("
CC: ").append(escapeHtml(cc)).append("
\n"); + } + if (!bcc.trim().isEmpty()) { + html.append("
BCC: ") + .append(escapeHtml(bcc)) + .append("
\n"); + } + } + + if (!date.trim().isEmpty()) { + html.append("
Date: ").append(escapeHtml(date)).append("
\n"); + } + html.append("
\n"); + + html.append("
\n"); + html.append(processEmailHtmlBody(htmlBody)); + html.append("
\n"); + + // Add attachment information - always check for and display attachments + String attachmentInfo = extractAttachmentInfo(emlContent); + if (!attachmentInfo.isEmpty()) { + html.append("
\n"); + html.append("

Attachments

\n"); + html.append(attachmentInfo); + + // Add status message about attachment inclusion + if (request != null && request.isIncludeAttachments()) { + html.append("
\n"); + html.append( + "

Note: Attachments are saved as external files and linked in this PDF. Click the links to open files externally.

\n"); + html.append("
\n"); + } else { + html.append("
\n"); + html.append( + "

Attachment information displayed - files not included in PDF. Enable 'Include attachments' to embed files.

\n"); + html.append("
\n"); + } + + html.append("
\n"); + } + + // Show advanced features status if requested + assert request != null; + if (request != null && request.getFileInput().isEmpty()) { + html.append("
\n"); + html.append( + "

Note: Some advanced features require Jakarta Mail dependencies.

\n"); + html.append("
\n"); + } + + html.append("
\n"); + html.append(""); + + return html.toString(); + } + + private static EmailContent extractEmailContentAdvanced( + byte[] emlBytes, EmlToPdfRequest request) { + try { + // Use Jakarta Mail for processing + Class sessionClass = Class.forName("jakarta.mail.Session"); + Class mimeMessageClass = Class.forName("jakarta.mail.internet.MimeMessage"); + + Method getDefaultInstance = + sessionClass.getMethod("getDefaultInstance", Properties.class); + Object session = getDefaultInstance.invoke(null, new Properties()); + + Constructor mimeMessageConstructor = + mimeMessageClass.getConstructor(sessionClass, InputStream.class); + Object message = + mimeMessageConstructor.newInstance(session, new ByteArrayInputStream(emlBytes)); + + + return extractEmailContentAdvanced(message, request); + + } catch (ReflectiveOperationException e) { + // Create basic EmailContent from basic processing + EmailContent content = new EmailContent(); + content.setHtmlBody(convertEmlToHtmlBasic(emlBytes, request)); + return content; + } + } + + private static String convertEmlToHtmlAdvanced( + byte[] emlBytes, EmlToPdfRequest request) { + EmailContent content = extractEmailContentAdvanced(emlBytes, request); + return generateEnhancedEmailHtml(content, request); + } + + private static String extractAttachmentInfo(String emlContent) { + StringBuilder attachmentInfo = new StringBuilder(); + try { + String[] lines = emlContent.split("\r?\n"); + boolean inHeaders = true; + String currentContentType = ""; + String currentDisposition = ""; + String currentFilename = ""; + String currentEncoding = ""; + boolean inMultipart = false; + String boundary = ""; + + // First pass: find boundary for multipart messages + for (String line : lines) { + String lowerLine = line.toLowerCase().trim(); + if (lowerLine.startsWith("content-type:") && lowerLine.contains("multipart")) { + if (lowerLine.contains("boundary=")) { + int boundaryStart = lowerLine.indexOf("boundary=") + 9; + String boundaryPart = line.substring(boundaryStart).trim(); + if (boundaryPart.startsWith("\"")) { + boundary = boundaryPart.substring(1, boundaryPart.indexOf("\"", 1)); + } else { + int spaceIndex = boundaryPart.indexOf(" "); + boundary = + spaceIndex > 0 + ? boundaryPart.substring(0, spaceIndex) + : boundaryPart; + } + inMultipart = true; + break; + } + } + if (line.trim().isEmpty()) break; + } + + // Second pass: extract attachment information + for (String line : lines) { + String lowerLine = line.toLowerCase().trim(); + + // Check for boundary markers in multipart messages + if (inMultipart && line.trim().startsWith("--" + boundary)) { + // Reset for new part + currentContentType = ""; + currentDisposition = ""; + currentFilename = ""; + currentEncoding = ""; + inHeaders = true; + continue; + } + + if (inHeaders && line.trim().isEmpty()) { + inHeaders = false; + + // Process accumulated attachment info + if (isAttachment(currentDisposition, currentFilename, currentContentType)) { + addAttachmentToInfo( + attachmentInfo, + currentFilename, + currentContentType, + currentEncoding); + + // Reset for next attachment + currentContentType = ""; + currentDisposition = ""; + currentFilename = ""; + currentEncoding = ""; + } + continue; + } + + if (!inHeaders) continue; // Skip body content + + // Parse headers + if (lowerLine.startsWith("content-type:")) { + currentContentType = line.substring(13).trim(); + } else if (lowerLine.startsWith("content-disposition:")) { + currentDisposition = line.substring(20).trim(); + // Extract filename if present + currentFilename = extractFilenameFromDisposition(currentDisposition); + } else if (lowerLine.startsWith("content-transfer-encoding:")) { + currentEncoding = line.substring(26).trim(); + } else if (line.startsWith(" ") || line.startsWith("\t")) { + // Continuation of previous header + if (currentDisposition.contains("filename=")) { + currentDisposition += " " + line.trim(); + currentFilename = extractFilenameFromDisposition(currentDisposition); + } else if (!currentContentType.isEmpty()) { + currentContentType += " " + line.trim(); + } + } + } + + if (isAttachment(currentDisposition, currentFilename, currentContentType)) { + addAttachmentToInfo( + attachmentInfo, currentFilename, currentContentType, currentEncoding); + } + + } catch (RuntimeException e) { + log.warn("Error extracting attachment info: {}", e.getMessage()); + } + return attachmentInfo.toString(); + } + + private static boolean isAttachment(String disposition, String filename, String contentType) { + return (disposition.toLowerCase().contains("attachment") && !filename.isEmpty()) + || (!filename.isEmpty() && !contentType.toLowerCase().startsWith("text/")) + || (contentType.toLowerCase().contains("application/") && !filename.isEmpty()); + } + + private static String extractFilenameFromDisposition(String disposition) { + if (disposition.contains("filename=")) { + int filenameStart = disposition.toLowerCase().indexOf("filename=") + 9; + int filenameEnd = disposition.indexOf(";", filenameStart); + if (filenameEnd == -1) filenameEnd = disposition.length(); + String filename = disposition.substring(filenameStart, filenameEnd).trim(); + filename = filename.replaceAll("^\"|\"$", ""); + // Apply MIME decoding to handle encoded filenames + return safeMimeDecode(filename); + } + return ""; + } + + private static void addAttachmentToInfo( + StringBuilder attachmentInfo, String filename, String contentType, String encoding) { + // Create attachment info with paperclip emoji before filename + attachmentInfo + .append("
") + .append("icon ") + .append("").append(escapeHtml(filename)).append(""); + + // Add content type and encoding info + if (!contentType.isEmpty() || !encoding.isEmpty()) { + attachmentInfo.append(" ("); + if (!contentType.isEmpty()) { + attachmentInfo.append(escapeHtml(contentType)); + } + if (!encoding.isEmpty()) { + if (!contentType.isEmpty()) attachmentInfo.append(", "); + attachmentInfo.append("encoding: ").append(escapeHtml(encoding)); + } + attachmentInfo.append(")"); + } + attachmentInfo.append("
\n"); + } + + private static boolean isInvalidEmlFormat(byte[] emlBytes) { + try { + int checkLength = Math.min(emlBytes.length, 8192); + String content = new String(emlBytes, 0, checkLength, StandardCharsets.UTF_8); + String lowerContent = content.toLowerCase(); + + boolean hasFrom = + lowerContent.contains("from:") || lowerContent.contains("return-path:"); + boolean hasSubject = lowerContent.contains("subject:"); + boolean hasMessageId = lowerContent.contains("message-id:"); + boolean hasDate = lowerContent.contains("date:"); + boolean hasTo = + lowerContent.contains("to:") + || lowerContent.contains("cc:") + || lowerContent.contains("bcc:"); + boolean hasMimeStructure = + lowerContent.contains("multipart/") + || lowerContent.contains("text/plain") + || lowerContent.contains("text/html") + || lowerContent.contains("boundary="); + + int headerCount = 0; + if (hasFrom) headerCount++; + if (hasSubject) headerCount++; + if (hasMessageId) headerCount++; + if (hasDate) headerCount++; + if (hasTo) headerCount++; + + return headerCount < 2 && !hasMimeStructure; + + } catch (RuntimeException e) { + return false; + } + } + + private static String extractBasicHeader(String emlContent, String headerName) { + try { + String[] lines = emlContent.split("\r?\n"); + for (int i = 0; i < lines.length; i++) { + String line = lines[i]; + if (line.toLowerCase().startsWith(headerName.toLowerCase())) { + StringBuilder value = + new StringBuilder(line.substring(headerName.length()).trim()); + // Handle multi-line headers + for (int j = i + 1; j < lines.length; j++) { + if (lines[j].startsWith(" ") || lines[j].startsWith("\t")) { + value.append(" ").append(lines[j].trim()); + } else { + break; + } + } + // Apply MIME header decoding + return safeMimeDecode(value.toString()); + } + if (line.trim().isEmpty()) break; + } + } catch (RuntimeException e) { + log.warn("Error extracting header '{}': {}", headerName, e.getMessage()); + } + return ""; + } + + private static String extractHtmlBody(String emlContent) { + try { + String lowerContent = emlContent.toLowerCase(); + int htmlStart = lowerContent.indexOf("content-type: text/html"); + if (htmlStart == -1) return null; + + return getString(emlContent, htmlStart); + + } catch (Exception e) { + return null; + } + } + + @Nullable + private static String getString(String emlContent, int htmlStart) { + int bodyStart = emlContent.indexOf("\r\n\r\n", htmlStart); + if (bodyStart == -1) bodyStart = emlContent.indexOf("\n\n", htmlStart); + if (bodyStart == -1) return null; + + bodyStart += (emlContent.charAt(bodyStart + 1) == '\r') ? 4 : 2; + int bodyEnd = findPartEnd(emlContent, bodyStart); + + return emlContent.substring(bodyStart, bodyEnd).trim(); + } + + private static String extractTextBody(String emlContent) { + try { + String lowerContent = emlContent.toLowerCase(); + int textStart = lowerContent.indexOf("content-type: text/plain"); + if (textStart == -1) { + int bodyStart = emlContent.indexOf("\r\n\r\n"); + if (bodyStart == -1) bodyStart = emlContent.indexOf("\n\n"); + if (bodyStart != -1) { + bodyStart += (emlContent.charAt(bodyStart + 1) == '\r') ? 4 : 2; + int bodyEnd = findPartEnd(emlContent, bodyStart); + return emlContent.substring(bodyStart, bodyEnd).trim(); + } + return null; + } + + return getString(emlContent, textStart); + + } catch (RuntimeException e) { + return null; + } + } + + private static int findPartEnd(String content, int start) { + String[] lines = content.substring(start).split("\r?\n"); + StringBuilder result = new StringBuilder(); + + for (String line : lines) { + if (line.startsWith("--") && line.length() > 10) break; + result.append(line).append("\n"); + } + + return start + result.length(); + } + + private static String convertTextToHtml(String textBody) { + if (textBody == null) return ""; + + String html = escapeHtml(textBody); + html = html.replace("\r\n", "\n").replace("\r", "\n"); + html = html.replace("\n", "
\n"); + + html = + html.replaceAll( + "(https?://[\\w\\-._~:/?#\\[\\]@!$&'()*+,;=%]+)", + "$1"); + + html = + html.replaceAll( + "([a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,63})", + "$1"); + + return html; + } + + private static String processEmailHtmlBody(String htmlBody) { + if (htmlBody == null) return ""; + + String processed = htmlBody; + + // Remove problematic CSS + processed = processed.replaceAll("(?i)\\s*position\\s*:\\s*fixed[^;]*;?", ""); + processed = processed.replaceAll("(?i)\\s*position\\s*:\\s*absolute[^;]*;?", ""); + + return processed; + } + + private static void appendEnhancedStyles(StringBuilder html, EmlToPdfRequest request) { + EmlToPdf.request = request; + int fontSize = 12; // Default font size + + String textColor = "#202124"; + String backgroundColor = "#ffffff"; + String borderColor = "#e8eaed"; + + html.append("body {\n"); + html.append(" font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', Arial, sans-serif;\n"); + html.append(" font-size: ").append(fontSize).append("px;\n"); + html.append(" line-height: 1.4;\n"); + html.append(" color: ").append(textColor).append(";\n"); + html.append(" margin: 0;\n"); + html.append(" padding: 16px;\n"); + html.append(" background-color: ").append(backgroundColor).append(";\n"); + html.append("}\n\n"); + + html.append(".email-container {\n"); + html.append(" width: 100%;\n"); + html.append(" max-width: 100%;\n"); + html.append(" margin: 0 auto;\n"); + html.append("}\n\n"); + + html.append(".email-header {\n"); + html.append(" padding-bottom: 10px;\n"); + html.append(" border-bottom: 1px solid ").append(borderColor).append(";\n"); + html.append(" margin-bottom: 10px;\n"); + html.append("}\n\n"); + html.append(".email-header h1 {\n"); + html.append(" margin: 0 0 10px 0;\n"); + html.append(" font-size: ").append(fontSize + 4).append("px;\n"); + html.append(" font-weight: bold;\n"); + html.append("}\n\n"); + html.append(".email-meta div {\n"); + html.append(" margin-bottom: 2px;\n"); + html.append(" font-size: ").append(fontSize - 1).append("px;\n"); + html.append("}\n\n"); + + + html.append(".email-body {\n"); + html.append(" word-wrap: break-word;\n"); + html.append("}\n\n"); + + + html.append(".attachment-section {\n"); + html.append(" margin-top: 15px;\n"); + html.append(" padding: 10px;\n"); + html.append(" background-color: #f9f9f9;\n"); + html.append(" border: 1px solid #eeeeee;\n"); + html.append(" border-radius: 3px;\n"); + html.append("}\n\n"); + html.append(".attachment-section h3 {\n"); + html.append(" margin: 0 0 8px 0;\n"); + html.append(" font-size: ").append(fontSize + 1).append("px;\n"); + html.append("}\n\n"); + html.append(".attachment-item {\n"); + html.append(" padding: 5px 0;\n"); + html.append("}\n\n"); + html.append(".attachment-icon {\n"); + html.append(" margin-right: 5px;\n"); + html.append("}\n\n"); + html.append(".attachment-details, .attachment-type {\n"); + html.append(" font-size: ").append(fontSize - 2).append("px;\n"); + html.append(" color: #555555;\n"); + html.append("}\n\n"); + html.append(".attachment-inclusion-note, .attachment-info-note {\n"); + html.append(" margin-top: 8px;\n"); + html.append(" padding: 6px;\n"); + html.append(" font-size: ").append(fontSize - 2).append("px;\n"); + html.append(" border-radius: 3px;\n"); + html.append("}\n\n"); + html.append(".attachment-inclusion-note {\n"); + html.append(" background-color: #e6ffed;\n"); + html.append(" border: 1px solid #d4f7dc;\n"); + html.append(" color: #006420;\n"); + html.append("}\n\n"); + html.append(".attachment-info-note {\n"); + html.append(" background-color: #fff9e6;\n"); + html.append(" border: 1px solid #fff0c2;\n"); + html.append(" color: #664d00;\n"); + html.append("}\n\n"); + html.append(".attachment-link-container {\n"); + html.append(" display: flex;\n"); + html.append(" align-items: center;\n"); + html.append(" padding: 8px;\n"); + html.append(" background-color: #f8f9fa;\n"); + html.append(" border: 1px solid #dee2e6;\n"); + html.append(" border-radius: 4px;\n"); + html.append(" margin: 4px 0;\n"); + html.append("}\n\n"); + html.append(".attachment-link-container:hover {\n"); + html.append(" background-color: #e9ecef;\n"); + html.append("}\n\n"); + html.append(".attachment-note {\n"); + html.append(" font-size: ").append(fontSize - 3).append("px;\n"); + html.append(" color: #6c757d;\n"); + html.append(" font-style: italic;\n"); + html.append(" margin-left: 8px;\n"); + html.append("}\n\n"); + + + // Basic image styling: ensure images are responsive but not overly constrained. + html.append("img {\n"); + html.append(" max-width: 100%;\n"); // Make images responsive to container width + html.append(" height: auto;\n"); // Maintain aspect ratio + html.append(" display: block;\n"); // Avoid extra space below images + html.append("}\n\n"); + } + + private static String escapeHtml(String text) { + if (text == null) return ""; + return text.replace("&", "&") + .replace("<", "<") + .replace(">", ">") + .replace("\"", """) + .replace("'", "'"); + } + + private static stirling.software.common.model.api.converters.HTMLToPdfRequest createHtmlRequest( + EmlToPdfRequest request) { + stirling.software.common.model.api.converters.HTMLToPdfRequest htmlRequest = + new stirling.software.common.model.api.converters.HTMLToPdfRequest(); + if (request != null) { + htmlRequest.setFileInput(request.getFileInput()); + + // Calculate zoom based on font size if adaptive font sizing is enabled + float zoom = 1.0f; + htmlRequest.setZoom(zoom); + } else { + htmlRequest.setZoom(1.0f); + } + return htmlRequest; + } + + private static EmailContent extractEmailContentAdvanced( + Object message, EmlToPdfRequest request) { + EmailContent content = new EmailContent(); + + try { + Class messageClass = message.getClass(); + + // Extract headers via reflection + java.lang.reflect.Method getSubject = messageClass.getMethod("getSubject"); + String subject = (String) getSubject.invoke(message); + content.setSubject(subject != null ? safeMimeDecode(subject) : "No Subject"); + + java.lang.reflect.Method getFrom = messageClass.getMethod("getFrom"); + Object[] fromAddresses = (Object[]) getFrom.invoke(message); + content.setFrom( + fromAddresses != null && fromAddresses.length > 0 + ? safeMimeDecode(fromAddresses[0].toString()) + : ""); + + java.lang.reflect.Method getAllRecipients = messageClass.getMethod("getAllRecipients"); + Object[] recipients = (Object[]) getAllRecipients.invoke(message); + content.setTo( + recipients != null && recipients.length > 0 ? safeMimeDecode(recipients[0].toString()) : ""); + + java.lang.reflect.Method getSentDate = messageClass.getMethod("getSentDate"); + content.setDate((Date) getSentDate.invoke(message)); + + // Extract content + java.lang.reflect.Method getContent = messageClass.getMethod("getContent"); + Object messageContent = getContent.invoke(message); + + if (messageContent instanceof String stringContent) { + java.lang.reflect.Method getContentType = messageClass.getMethod("getContentType"); + String contentType = (String) getContentType.invoke(message); + if (contentType != null && contentType.toLowerCase().contains("text/html")) { + content.setHtmlBody(stringContent); + } else { + content.setTextBody(stringContent); + } + } else { + // Handle multipart content + try { + Class multipartClass = Class.forName("jakarta.mail.Multipart"); + if (multipartClass.isInstance(messageContent)) { + processMultipartAdvanced(messageContent, content, request); + } + } catch (Exception e) { + log.warn("Error processing multipart content: {}", e.getMessage()); + } + } + + } catch (Exception e) { + content.setSubject("Email Conversion"); + content.setFrom("Unknown"); + content.setTo("Unknown"); + content.setTextBody("Email content could not be parsed with advanced processing"); + } + + return content; + } + + private static void processMultipartAdvanced( + Object multipart, EmailContent content, EmlToPdfRequest request) { + try { + Class multipartClass = multipart.getClass(); + java.lang.reflect.Method getCount = multipartClass.getMethod("getCount"); + int count = (Integer) getCount.invoke(multipart); + + java.lang.reflect.Method getBodyPart = + multipartClass.getMethod("getBodyPart", int.class); + + for (int i = 0; i < count; i++) { + Object part = getBodyPart.invoke(multipart, i); + processPartAdvanced(part, content, request); + } + + } catch (Exception e) { + content.setTextBody("Email content could not be parsed with advanced processing"); + } + } + + private static void processPartAdvanced( + Object part, EmailContent content, EmlToPdfRequest request) { + try { + Class partClass = part.getClass(); + java.lang.reflect.Method isMimeType = partClass.getMethod("isMimeType", String.class); + java.lang.reflect.Method getContent = partClass.getMethod("getContent"); + java.lang.reflect.Method getDisposition = partClass.getMethod("getDisposition"); + java.lang.reflect.Method getFileName = partClass.getMethod("getFileName"); + java.lang.reflect.Method getContentType = partClass.getMethod("getContentType"); + java.lang.reflect.Method getHeader = partClass.getMethod("getHeader", String.class); + + Object disposition = getDisposition.invoke(part); + String filename = (String) getFileName.invoke(part); + String contentType = (String) getContentType.invoke(part); + + if ((Boolean) isMimeType.invoke(part, "text/plain") && disposition == null) { + content.setTextBody((String) getContent.invoke(part)); + } else if ((Boolean) isMimeType.invoke(part, "text/html") && disposition == null) { + content.setHtmlBody((String) getContent.invoke(part)); + } else if ("attachment".equalsIgnoreCase((String) disposition) + || (filename != null && !filename.trim().isEmpty())) { + + content.setAttachmentCount(content.getAttachmentCount() + 1); + + // Always extract basic attachment metadata for display + if (filename != null && !filename.trim().isEmpty()) { + // Create attachment with metadata only + EmailAttachment attachment = new EmailAttachment(); + // Apply MIME decoding to filename to handle encoded attachment names + attachment.setFilename(safeMimeDecode(filename)); + attachment.setContentType(contentType); + + // Check if it's an embedded image + String[] contentIdHeaders = (String[]) getHeader.invoke(part, "Content-ID"); + if (contentIdHeaders != null && contentIdHeaders.length > 0) { + attachment.setEmbedded(true); + } + + // Extract attachment data only if attachments should be included + if (request != null && request.isIncludeAttachments()) { + try { + Object attachmentContent = getContent.invoke(part); + byte[] attachmentData = null; + + if (attachmentContent instanceof java.io.InputStream inputStream) { + try { + attachmentData = inputStream.readAllBytes(); + } catch (IOException e) { + log.warn("Failed to read InputStream attachment: {}", e.getMessage()); + } + } else if (attachmentContent instanceof byte[] byteArray) { + attachmentData = byteArray; + } else if (attachmentContent instanceof String stringContent) { + attachmentData = + stringContent.getBytes(StandardCharsets.UTF_8); + } + + if (attachmentData != null) { + // Check size limit (use default 10MB if request is null) + long maxSizeMB = request.getMaxAttachmentSizeMB(); + long maxSizeBytes = maxSizeMB * 1024 * 1024; + + if (attachmentData.length <= maxSizeBytes) { + attachment.setData(attachmentData); + attachment.setSizeBytes(attachmentData.length); + } else { + // Still show attachment info even if too large + attachment.setSizeBytes(attachmentData.length); + } + } + } catch (Exception e) { + log.warn("Error extracting attachment data: {}", e.getMessage()); + } + } + + // Add attachment to the list for display (with or without data) + content.getAttachments().add(attachment); + } + } else if ((Boolean) isMimeType.invoke(part, "multipart/*")) { + // Handle nested multipart content + try { + Object multipartContent = getContent.invoke(part); + Class multipartClass = Class.forName("jakarta.mail.Multipart"); + if (multipartClass.isInstance(multipartContent)) { + processMultipartAdvanced(multipartContent, content, request); + } + } catch (Exception e) { + log.warn("Error processing multipart content: {}", e.getMessage()); + } + } + + } catch (Exception e) { + log.warn("Error processing multipart part: {}", e.getMessage()); + } + } + + private static String generateEnhancedEmailHtml(EmailContent content, EmlToPdfRequest request) { + StringBuilder html = new StringBuilder(); + + html.append("\n"); + html.append("\n"); + html.append("").append(escapeHtml(content.getSubject())).append("\n"); + html.append("\n"); + html.append("\n"); + + html.append("
\n"); + html.append("
\n"); + html.append("

").append(escapeHtml(content.getSubject())).append("

\n"); + html.append("
\n"); + html.append("
From: ") + .append(escapeHtml(content.getFrom())) + .append("
\n"); + html.append("
To: ").append(escapeHtml(content.getTo())).append("
\n"); + + if (content.getDate() != null) { + html.append("
Date: ") + .append(formatEmailDate(content.getDate())) + .append("
\n"); + } + html.append("
\n"); + + html.append("
\n"); + if (content.getHtmlBody() != null && !content.getHtmlBody().trim().isEmpty()) { + html.append(processEmailHtmlBody(content.getHtmlBody())); + } else if (content.getTextBody() != null && !content.getTextBody().trim().isEmpty()) { + html.append("
"); + html.append(convertTextToHtml(content.getTextBody())); + html.append("
"); + } else { + html.append("
"); + html.append("

No content available

"); + html.append("
"); + } + html.append("
\n"); + + if (content.getAttachmentCount() > 0 || !content.getAttachments().isEmpty()) { + html.append("
\n"); + int displayedAttachmentCount = + content.getAttachmentCount() > 0 + ? content.getAttachmentCount() + : content.getAttachments().size(); + html.append("

Attachments (").append(displayedAttachmentCount).append(")

\n"); + + if (!content.getAttachments().isEmpty()) { + for (EmailAttachment attachment : content.getAttachments()) { + // Create attachment info with paperclip emoji before filename + String uniqueId = + "attachment_" + + attachment.getFilename().hashCode() + + "_" + + System.nanoTime(); + attachment.setEmbeddedFilename( + attachment.getEmbeddedFilename() != null + ? attachment.getEmbeddedFilename() + : attachment.getFilename()); + + html.append("
") + .append("").append("\uD83D\uDCCE").append(" ") + .append("") + .append(escapeHtml(safeMimeDecode(attachment.getFilename()))) + .append(""); + + String sizeStr = formatFileSize(attachment.getSizeBytes()); + html.append(" (").append(sizeStr); + if (attachment.getContentType() != null && !attachment.getContentType().isEmpty()) { + html.append(", ").append(escapeHtml(attachment.getContentType())); + } + html.append(")
\n"); + } + } + + if (request.isIncludeAttachments()) { + html.append("
\n"); + html.append( + "

Attachments are embedded in the file.

\n"); + html.append("
\n"); + } else { + html.append("
\n"); + html.append( + "

Attachment information displayed - files not included in PDF.

\n"); + html.append("
\n"); + } + + html.append("
\n"); + } + + html.append("
\n"); + html.append(""); + + return html.toString(); + } + + private static byte[] attachFilesToPdf(byte[] pdfBytes, List attachments) + throws IOException { + try (PDDocument document = Loader.loadPDF(pdfBytes); + ByteArrayOutputStream outputStream = new ByteArrayOutputStream()) { + + if (attachments == null || attachments.isEmpty()) { + document.save(outputStream); + return outputStream.toByteArray(); + } + + List embeddedFiles = new ArrayList<>(); + + // Set up the embedded files name tree once + if (document.getDocumentCatalog().getNames() == null) { + document.getDocumentCatalog() + .setNames(new PDDocumentNameDictionary(document.getDocumentCatalog())); + } + + PDDocumentNameDictionary names = document.getDocumentCatalog().getNames(); + if (names.getEmbeddedFiles() == null) { + names.setEmbeddedFiles(new PDEmbeddedFilesNameTreeNode()); + } + + PDEmbeddedFilesNameTreeNode efTree = names.getEmbeddedFiles(); + Map efMap = efTree.getNames(); + if (efMap == null) { + efMap = new HashMap<>(); + } + + // Embed each attachment directly into the PDF + for (EmailAttachment attachment : attachments) { + if (attachment.getData() == null || attachment.getData().length == 0) { + continue; + } + + try { + // Generate unique filename + String filename = attachment.getFilename(); + if (filename == null || filename.trim().isEmpty()) { + filename = "attachment_" + System.currentTimeMillis(); + if (attachment.getContentType() != null + && attachment.getContentType().contains("/")) { + String[] parts = attachment.getContentType().split("/"); + if (parts.length > 1) { + filename += "." + parts[1]; + } + } + } + + // Ensure unique filename + String uniqueFilename = getUniqueFilename(filename, embeddedFiles, efMap); + + // Create embedded file + PDEmbeddedFile embeddedFile = + new PDEmbeddedFile(document, new ByteArrayInputStream(attachment.getData())); + embeddedFile.setSize(attachment.getData().length); + embeddedFile.setCreationDate(new GregorianCalendar()); + if (attachment.getContentType() != null) { + embeddedFile.setSubtype(attachment.getContentType()); + } + + // Create file specification + PDComplexFileSpecification fileSpec = new PDComplexFileSpecification(); + fileSpec.setFile(uniqueFilename); + fileSpec.setEmbeddedFile(embeddedFile); + if (attachment.getContentType() != null) { + fileSpec.setFileDescription("Email attachment: " + uniqueFilename); + } + + // Add to the map (but don't set it yet) + efMap.put(uniqueFilename, fileSpec); + embeddedFiles.add(uniqueFilename); + + // Store the filename for annotation creation + attachment.setEmbeddedFilename(uniqueFilename); + + } catch (Exception e) { + // Log error but continue with other attachments + log.warn( + "Failed to embed attachment: {} - {}", + attachment.getFilename(), + e.getMessage()); + } + } + + // Set the complete map once at the end + if (!efMap.isEmpty()) { + efTree.setNames(efMap); + + // Set catalog viewer preferences to automatically show attachments pane + setCatalogViewerPreferences(document); + } + + // Add attachment annotations to the first page for each embedded file + if (!embeddedFiles.isEmpty()) { + addAttachmentAnnotationsToDocument(document, attachments); + } + + document.save(outputStream); + return outputStream.toByteArray(); + } + } + + private static String getUniqueFilename(String filename, List embeddedFiles, Map efMap) { + String uniqueFilename = filename; + int counter = 1; + while (embeddedFiles.contains(uniqueFilename) + || efMap.containsKey(uniqueFilename)) { + String extension = ""; + String baseName = filename; + int lastDot = filename.lastIndexOf('.'); + if (lastDot > 0) { + extension = filename.substring(lastDot); + baseName = filename.substring(0, lastDot); + } + uniqueFilename = baseName + "_" + counter + extension; + counter++; + } + return uniqueFilename; + } + + private static void addAttachmentAnnotationsToDocument( + PDDocument document, List attachments) throws IOException { + if (document.getNumberOfPages() == 0 || attachments == null || attachments.isEmpty()) { + return; + } + + // 1. Find the screen position of all emoji anchors + EmojiPositionFinder finder = new EmojiPositionFinder(); + finder.setSortByPosition(true); // Process pages in order + finder.getText(document); + List emojiPositions = finder.getPositions(); + + // 2. Warn if the number of anchors and attachments don't match + if (emojiPositions.size() != attachments.size()) { + log.warn( + "Found {} emoji anchors, but there are {} attachments. Annotation count may be incorrect.", + emojiPositions.size(), + attachments.size()); + } + + // 3. Create an invisible annotation over each found emoji + int annotationsToAdd = Math.min(emojiPositions.size(), attachments.size()); + for (int i = 0; i < annotationsToAdd; i++) { + EmojiPosition position = emojiPositions.get(i); + EmailAttachment attachment = attachments.get(i); + + if (attachment.getEmbeddedFilename() != null) { + PDPage page = document.getPage(position.getPageIndex()); + addAttachmentAnnotationToPage( + document, page, attachment, position.getX(), position.getY()); + } + } + } + + private static void addAttachmentAnnotationToPage( + PDDocument document, PDPage page, EmailAttachment attachment, float x, float y) + throws IOException { + + PDAnnotationFileAttachment fileAnnotation = new PDAnnotationFileAttachment(); + + PDRectangle rect = getPdRectangle(page, x, y); + fileAnnotation.setRectangle(rect); + + // Remove visual appearance while keeping clickable functionality + try { + PDAppearanceDictionary appearance = new PDAppearanceDictionary(); + PDAppearanceStream normalAppearance = new PDAppearanceStream(document); + normalAppearance.setBBox(new PDRectangle(0, 0, 0, 0)); // Zero-size bounding box + + appearance.setNormalAppearance(normalAppearance); + fileAnnotation.setAppearance(appearance); + } catch (Exception e) { + // If appearance manipulation fails, just set it to null + fileAnnotation.setAppearance(null); + } + + // Set invisibility flags but keep it functional + fileAnnotation.setInvisible(true); + fileAnnotation.setHidden(false); // Must be false to remain clickable + fileAnnotation.setNoView(false); // Must be false to remain clickable + fileAnnotation.setPrinted(false); + + PDEmbeddedFilesNameTreeNode efTree = document.getDocumentCatalog().getNames().getEmbeddedFiles(); + if (efTree != null) { + Map efMap = efTree.getNames(); + if (efMap != null) { + PDComplexFileSpecification fileSpec = efMap.get(attachment.getEmbeddedFilename()); + if (fileSpec != null) { + fileAnnotation.setFile(fileSpec); + } + } + } + + fileAnnotation.setContents("Click to open: " + attachment.getFilename()); + fileAnnotation.setAnnotationName("EmbeddedFile_" + attachment.getEmbeddedFilename()); + + page.getAnnotations().add(fileAnnotation); + + log.info("Added attachment annotation for '{}' on page {}", + attachment.getFilename(), document.getPages().indexOf(page) + 1); + } + + private static @NotNull PDRectangle getPdRectangle(PDPage page, float x, float y) { + float xOffset = 2f; + float yOffset = 10f; + PDRectangle mediaBox = page.getMediaBox(); + float pdfY = mediaBox.getHeight() - y; + + float iconWidth = 12f; // Keep original size for clickability + float iconHeight = 14f; // Keep original size for clickability + + // Keep the full-size rectangle so it remains clickable + return new PDRectangle( + x + xOffset, + pdfY - iconHeight + yOffset, + iconWidth, + iconHeight + ); + } + + private static String formatEmailDate(Date date) { + if (date == null) return ""; + java.text.SimpleDateFormat formatter = + new java.text.SimpleDateFormat("EEE, MMM d, yyyy 'at' h:mm a", Locale.ENGLISH); + return formatter.format(date); + } + + private static String formatFileSize(long bytes) { + if (bytes < 1024) return bytes + " B"; + int exp = (int) (Math.log(bytes) / Math.log(1024)); + String pre = "KMGTPE".charAt(exp - 1) + ""; + return String.format("%.1f %sB", bytes / Math.pow(1024, exp), pre); + } + + private static void setCatalogViewerPreferences(PDDocument document) { + try { + PDDocumentCatalog catalog = document.getDocumentCatalog(); + if (catalog != null) { + // Get the catalog's COS dictionary to work with low-level PDF objects + COSDictionary catalogDict = catalog.getCOSObject(); + + // Set PageMode to UseAttachments - this is the standard PDF specification approach + // PageMode values: UseNone, UseOutlines, UseThumbs, FullScreen, UseOC, UseAttachments + catalogDict.setName(COSName.PAGE_MODE, "UseAttachments"); + + // Also set viewer preferences for better attachment viewing experience + COSDictionary viewerPrefs = (COSDictionary) catalogDict.getDictionaryObject(COSName.VIEWER_PREFERENCES); + if (viewerPrefs == null) { + viewerPrefs = new COSDictionary(); + catalogDict.setItem(COSName.VIEWER_PREFERENCES, viewerPrefs); + } + + // Set NonFullScreenPageMode to UseAttachments as fallback for viewers that support it + viewerPrefs.setName(COSName.getPDFName("NonFullScreenPageMode"), "UseAttachments"); + + // Additional viewer preferences that may help with attachment display + viewerPrefs.setBoolean(COSName.getPDFName("DisplayDocTitle"), true); + + log.info("Set PDF PageMode to UseAttachments to automatically show attachments pane"); + } + } catch (Exception e) { + // Log warning but don't fail the entire operation for viewer preferences + log.warn("Failed to set catalog viewer preferences for attachments: {}", e.getMessage()); + } + } + + // MIME header decoding functionality for RFC 2047 encoded headers + private static final Pattern MIME_ENCODED_PATTERN = + Pattern.compile("=\\?([^?]+)\\?([BbQq])\\?([^?]*)\\?="); + + private static String decodeMimeHeader(String encodedText) { + if (encodedText == null || encodedText.trim().isEmpty()) { + return encodedText; + } + + try { + StringBuilder result = new StringBuilder(); + Matcher matcher = MIME_ENCODED_PATTERN.matcher(encodedText); + int lastEnd = 0; + + while (matcher.find()) { + // Add any text before the encoded part + result.append(encodedText, lastEnd, matcher.start()); + + String charset = matcher.group(1); + String encoding = matcher.group(2).toUpperCase(); + String encodedValue = matcher.group(3); + + try { + String decodedValue; + if ("B".equals(encoding)) { + // Base64 decoding + byte[] decodedBytes = Base64.getDecoder().decode(encodedValue); + decodedValue = new String(decodedBytes, Charset.forName(charset)); + } else if ("Q".equals(encoding)) { + // Quoted-printable decoding + decodedValue = decodeQuotedPrintable(encodedValue, charset); + } else { + // Unknown encoding, keep original + decodedValue = matcher.group(0); + } + result.append(decodedValue); + } catch (Exception e) { + log.warn("Failed to decode MIME header part: {} - {}", matcher.group(0), e.getMessage()); + // If decoding fails, keep the original encoded text + result.append(matcher.group(0)); + } + + lastEnd = matcher.end(); + } + + // Add any remaining text after the last encoded part + result.append(encodedText.substring(lastEnd)); + + return result.toString(); + } catch (Exception e) { + log.warn("Error decoding MIME header: {} - {}", encodedText, e.getMessage()); + return encodedText; // Return original if decoding fails + } + } + + private static String decodeQuotedPrintable(String encodedText, String charset) { + StringBuilder result = new StringBuilder(); + for (int i = 0; i < encodedText.length(); i++) { + char c = encodedText.charAt(i); + switch (c) { + case '=' -> { + if (i + 2 < encodedText.length()) { + String hex = encodedText.substring(i + 1, i + 3); + try { + int value = Integer.parseInt(hex, 16); + result.append((char) value); + i += 2; // Skip the hex digits + } catch (NumberFormatException e) { + // If hex parsing fails, keep the original character + result.append(c); + } + } else { + result.append(c); + } + } + case '_' -> // In RFC 2047, underscore represents space + result.append(' '); + default -> result.append(c); + } + } + + // Convert bytes to proper charset + byte[] bytes = result.toString().getBytes(StandardCharsets.ISO_8859_1); + return new String(bytes, Charset.forName(charset)); + } + + private static String safeMimeDecode(String headerValue) { + if (headerValue == null) { + return ""; + } + + try { + return decodeMimeHeader(headerValue.trim()); + } catch (Exception e) { + log.warn("Failed to decode MIME header, using original: {} - {}", headerValue, e.getMessage()); + return headerValue; + } + } + + public static void setRequest(EmlToPdfRequest request) { + EmlToPdf.request = request; + } + + public static void setFileName(String fileName) { + EmlToPdf.fileName = fileName; + } + + @Data + public static class EmailContent { + private String subject; + private String from; + private String to; + private Date date; + private String htmlBody; + private String textBody; + private int attachmentCount; + private List attachments = new ArrayList<>(); + + public void setHtmlBody(String htmlBody) { + this.htmlBody = htmlBody != null ? htmlBody.replaceAll("\r", "") : null; + } + + public void setTextBody(String textBody) { + this.textBody = textBody != null ? textBody.replaceAll("\r", "") : null; + } + } + + @Data + public static class EmailAttachment { + private String filename; + private String contentType; + private byte[] data; + private boolean embedded; + private String embeddedFilename; + private long sizeBytes; + + // New fields for advanced processing + private String contentId; + private String disposition; + private String transferEncoding; + + // Custom setter to maintain size calculation logic + public void setData(byte[] data) { + this.data = data; + if (data != null) { + this.sizeBytes = data.length; + } + } + } + + @Data + public static class EmojiPosition { + private int pageIndex; + private float x; + private float y; + private String character; + + public EmojiPosition() { + } + + public EmojiPosition(int pageIndex, float x, float y, String character) { + this.pageIndex = pageIndex; + this.x = x; + this.y = y; + this.character = character; + } + } + + public static class EmojiPositionFinder extends org.apache.pdfbox.text.PDFTextStripper { + @Getter + private final List positions = new ArrayList<>(); + private int currentPageIndex; + private boolean sortByPosition; + private boolean isInAttachmentSection; + private boolean attachmentSectionFound; + + public EmojiPositionFinder() throws IOException { + super(); + this.currentPageIndex = 0; + this.sortByPosition = false; + this.isInAttachmentSection = false; + this.attachmentSectionFound = false; + } + + @Override + protected void startPage(org.apache.pdfbox.pdmodel.PDPage page) throws IOException { + super.startPage(page); + } + + @Override + protected void endPage(org.apache.pdfbox.pdmodel.PDPage page) throws IOException { + currentPageIndex++; + super.endPage(page); + } + + @Override + protected void writeString(String string, List textPositions) throws IOException { + // Check if we are entering or exiting the attachment section + String lowerString = string.toLowerCase(); + + // Look for attachment section start marker + if (lowerString.contains("attachments (")) { + isInAttachmentSection = true; + attachmentSectionFound = true; + } + + // Look for attachment section end markers (common patterns that indicate end of attachments) + if (isInAttachmentSection && (lowerString.contains("") || + lowerString.contains("") || + (attachmentSectionFound && lowerString.trim().isEmpty() && string.length() > 50))) { + isInAttachmentSection = false; + } + + // Only look for emojis if we are in the attachment section + if (isInAttachmentSection) { + // Look for paperclip emoji characters (U+1F4CE) + String paperclipEmoji = "\uD83D\uDCCE"; // 📎 Unicode representation + + for (int i = 0; i < string.length(); i++) { + // Check if we have a complete paperclip emoji at this position + if (i < string.length() - 1 && + string.substring(i, i + 2).equals(paperclipEmoji) && + i < textPositions.size()) { + + org.apache.pdfbox.text.TextPosition textPosition = textPositions.get(i); + EmojiPosition position = new EmojiPosition( + currentPageIndex, + textPosition.getXDirAdj(), + textPosition.getYDirAdj(), + paperclipEmoji + ); + positions.add(position); + } + } + } + super.writeString(string, textPositions); + } + + @Override + public void setSortByPosition(boolean sortByPosition) { + this.sortByPosition = sortByPosition; + } + + public boolean isSortByPosition() { + return sortByPosition; + } + + + public void reset() { + positions.clear(); + currentPageIndex = 0; + isInAttachmentSection = false; + attachmentSectionFound = false; + } + } +} diff --git a/src/main/java/stirling/software/SPDF/controller/api/converters/ConvertEmlToPDF.java b/src/main/java/stirling/software/SPDF/controller/api/converters/ConvertEmlToPDF.java new file mode 100644 index 000000000..0303ccda5 --- /dev/null +++ b/src/main/java/stirling/software/SPDF/controller/api/converters/ConvertEmlToPDF.java @@ -0,0 +1,148 @@ +package stirling.software.SPDF.controller.api.converters; + +import java.io.IOException; +import java.nio.charset.StandardCharsets; + +import org.jetbrains.annotations.NotNull; +import org.springframework.beans.factory.annotation.Value; +import org.springframework.http.HttpStatus; +import org.springframework.http.MediaType; +import org.springframework.http.ResponseEntity; +import org.springframework.web.bind.annotation.ModelAttribute; +import org.springframework.web.bind.annotation.PostMapping; +import org.springframework.web.bind.annotation.RequestMapping; +import org.springframework.web.bind.annotation.RestController; +import org.springframework.web.multipart.MultipartFile; + +import io.github.pixee.security.Filenames; +import io.swagger.v3.oas.annotations.Operation; +import io.swagger.v3.oas.annotations.tags.Tag; +import lombok.extern.slf4j.Slf4j; +import stirling.software.common.model.api.converters.EmlToPdfRequest; +import stirling.software.common.util.EmlToPdf; +import stirling.software.common.util.WebResponseUtils; + +@RestController +@RequestMapping("/api/v1/convert") +@Tag(name = "Convert", description = "Convert APIs") +@Slf4j +public class ConvertEmlToPDF { + + @Value("${WEASYPRINT_PATH:weasyprint}") + private String weasyprintPath; + + @PostMapping(consumes = "multipart/form-data", value = "/eml/pdf") + @Operation( + summary = "Convert EML to PDF", + description = + "This endpoint converts EML (email) files to PDF format with extensive" + + " customization options. Features include font settings, image constraints, display modes, attachment handling," + + " and HTML debug output. Input: EML file, Output: PDF" + + " or HTML file. Type: SISO") + public ResponseEntity convertEmlToPdf(@ModelAttribute EmlToPdfRequest request) { + + MultipartFile inputFile = request.getFileInput(); + String originalFilename = inputFile.getOriginalFilename(); + + // Validate input + if (inputFile == null || inputFile.isEmpty()) { + log.error("No file provided for EML to PDF conversion."); + return ResponseEntity.badRequest() + .body("No file provided".getBytes(StandardCharsets.UTF_8)); + } + + if (originalFilename == null || originalFilename.trim().isEmpty()) { + log.error("Filename is null or empty."); + return ResponseEntity.badRequest() + .body("Please provide a valid filename".getBytes(StandardCharsets.UTF_8)); + } + + // Validate file type - support EML + String lowerFilename = originalFilename.toLowerCase(); + if (!lowerFilename.endsWith(".eml")) { + log.error("Invalid file type for EML to PDF: {}", originalFilename); + return ResponseEntity.badRequest() + .body("Please upload a valid EML file".getBytes(StandardCharsets.UTF_8)); + } + + String baseFilename = Filenames.toSimpleFileName(originalFilename); // Use Filenames utility + + try { + byte[] fileBytes = inputFile.getBytes(); + + if (request.isDownloadHtml()) { + try { + String htmlContent = EmlToPdf.convertEmlToHtml(fileBytes, request); + log.info("Successfully converted EML to HTML: {}", originalFilename); + return WebResponseUtils.bytesToWebResponse( + htmlContent.getBytes(StandardCharsets.UTF_8), + baseFilename + ".html", + MediaType.TEXT_HTML); + } catch (Exception e) { + log.error("HTML conversion failed for {}", originalFilename, e); + return ResponseEntity.status(HttpStatus.INTERNAL_SERVER_ERROR) + .body( + ("HTML conversion failed: " + e.getMessage()) + .getBytes(StandardCharsets.UTF_8)); + } + } + + // Convert EML to PDF with enhanced options + try { + byte[] pdfBytes = + EmlToPdf.convertEmlToPdf( + weasyprintPath, // Use configured WeasyPrint path + request, + fileBytes, + originalFilename, + false); + + if (pdfBytes == null || pdfBytes.length == 0) { + log.error("PDF conversion failed - empty output for {}", originalFilename); + return ResponseEntity.status(HttpStatus.INTERNAL_SERVER_ERROR) + .body( + "PDF conversion failed - empty output" + .getBytes(StandardCharsets.UTF_8)); + } + log.info("Successfully converted EML to PDF: {}", originalFilename); + return WebResponseUtils.bytesToWebResponse( + pdfBytes, baseFilename + ".pdf", MediaType.APPLICATION_PDF); + + } catch (InterruptedException e) { + Thread.currentThread().interrupt(); + log.error("EML to PDF conversion was interrupted for {}", originalFilename, e); + return ResponseEntity.status(HttpStatus.INTERNAL_SERVER_ERROR) + .body("Conversion was interrupted".getBytes(StandardCharsets.UTF_8)); + } catch (Exception e) { + String errorMessage = buildErrorMessage(e, originalFilename); + log.error("EML to PDF conversion failed for {}: {}", originalFilename, errorMessage, e); + return ResponseEntity.status(HttpStatus.INTERNAL_SERVER_ERROR) + .body(errorMessage.getBytes(StandardCharsets.UTF_8)); + } + + } catch (IOException e) { + log.error("File processing error for EML to PDF: {}", originalFilename, e); + return ResponseEntity.status(HttpStatus.INTERNAL_SERVER_ERROR) + .body("File processing error".getBytes(StandardCharsets.UTF_8)); + } + } + + private static @NotNull String buildErrorMessage(Exception e, String originalFilename) { + String errorMessage; + if (e.getMessage() != null && e.getMessage().contains("Invalid EML")) { + errorMessage = + "Invalid EML file format. Please ensure you've uploaded a valid email" + + " file (" + + originalFilename + + ")."; + } else if (e.getMessage() != null && e.getMessage().contains("WeasyPrint")) { + errorMessage = + "PDF generation failed for " + + originalFilename + + ". This may be due to complex email formatting."; + } else { + errorMessage = "Conversion failed for " + originalFilename + ": " + e.getMessage(); + } + return errorMessage; + } +} diff --git a/src/main/java/stirling/software/SPDF/controller/web/ConverterWebController.java b/src/main/java/stirling/software/SPDF/controller/web/ConverterWebController.java index 10794693e..efde59066 100644 --- a/src/main/java/stirling/software/SPDF/controller/web/ConverterWebController.java +++ b/src/main/java/stirling/software/SPDF/controller/web/ConverterWebController.java @@ -7,7 +7,6 @@ import org.springframework.web.servlet.ModelAndView; import io.swagger.v3.oas.annotations.Hidden; import io.swagger.v3.oas.annotations.tags.Tag; - import stirling.software.common.util.CheckProgramInstall; @Controller @@ -121,4 +120,11 @@ public class ConverterWebController { model.addAttribute("currentPage", "pdf-to-pdfa"); return "convert/pdf-to-pdfa"; } + + @GetMapping("/eml-to-pdf") + @Hidden + public String convertEmlToPdfForm(Model model) { + model.addAttribute("currentPage", "eml-to-pdf"); + return "convert/eml-to-pdf"; + } } diff --git a/src/main/resources/messages_en_GB.properties b/src/main/resources/messages_en_GB.properties index b875859b6..e1d7fda17 100644 --- a/src/main/resources/messages_en_GB.properties +++ b/src/main/resources/messages_en_GB.properties @@ -621,6 +621,22 @@ home.HTMLToPDF.title=HTML to PDF home.HTMLToPDF.desc=Converts any HTML file or zip to PDF HTMLToPDF.tags=markup,web-content,transformation,convert +#eml-to-pdf +home.EMLToPDF.title=EML to PDF +home.EMLToPDF.desc=Converts email (EML) files to PDF format including headers, body, and inline images +EMLToPDF.tags=email,conversion,eml,message,transformation,convert,mail + +EMLToPDF.title=EML To PDF +EMLToPDF.header=EML To PDF +EMLToPDF.submit=Convert +EMLToPDF.downloadHtml=Download HTML intermediate file instead of PDF +EMLToPDF.downloadHtmlHelp=This allows you to see the HTML version before PDF conversion and can help debug formatting issues +EMLToPDF.includeAttachments=Include attachments in PDF +EMLToPDF.maxAttachmentSize=Maximum attachment size (MB) +EMLToPDF.help=Converts email (EML) files to PDF format including headers, body, and inline images +EMLToPDF.troubleshootingTip1=EML to HTML is a more reliable process, so with batch-processing it is recommended to save both +EMLToPDF.troubleshootingTip2=With a small number of EMLs, if the PDF is malformed, you can download HTML and override some of the problematic HTML code. +EMLToPDF.troubleshootingTip3=Embeddings, however, do not work with HTMLs home.MarkdownToPDF.title=Markdown to PDF home.MarkdownToPDF.desc=Converts any Markdown file to PDF diff --git a/src/main/resources/templates/convert/eml-to-pdf.html b/src/main/resources/templates/convert/eml-to-pdf.html new file mode 100644 index 000000000..0be880362 --- /dev/null +++ b/src/main/resources/templates/convert/eml-to-pdf.html @@ -0,0 +1,93 @@ + + + + + + + + +
+
+ +
+
+
+
+
+
+ email + +
+
+
+
+ +
+ + +
+
+ +
+
+ + +
+ +
+ + +
+ + +
+ +
+ +
+
+

+
    +
  • +
  • +
  • +
+
+
+
+ + +
+
+
+
+
+
+
+ +
+ + + + diff --git a/src/main/resources/templates/fragments/navElements.html b/src/main/resources/templates/fragments/navElements.html index 1c7d329dd..3ced01be8 100644 --- a/src/main/resources/templates/fragments/navElements.html +++ b/src/main/resources/templates/fragments/navElements.html @@ -59,6 +59,9 @@
+
+