feat(email-to-pdf): add inline images, clickable links, and embedded attachments

- Add CID inline image support via base64 data URI replacement
- Implement clickable link extraction from HTML anchors using regex
- Embed email attachments into PDF using pymupdf embfile_add
- Reduce font sizes for more compact PDF output (18px subject, 12px body)
- Format date with timezone (UTC+HH:MM) while preserving original time
- Clean email address formatting (Name (email) instead of <brackets>)
- Add UI options: page size selector, CC/BCC toggle, attachments toggle
This commit is contained in:
abdullahalam123
2026-01-08 21:36:21 +05:30
parent 4a4a47158f
commit 280348763d
30 changed files with 3978 additions and 9416 deletions

View File

@@ -0,0 +1,268 @@
import { showLoader, hideLoader, showAlert } from '../ui.js';
import { downloadFile, formatBytes } from '../utils/helpers.js';
import { state } from '../state.js';
import { createIcons, icons } from 'lucide';
import { parseEmailFile, renderEmailToHtml } from './email-to-pdf.js';
import { PyMuPDF } from '@bentopdf/pymupdf-wasm';
import { getWasmBaseUrl } from '../config/wasm-cdn-config.js';
const EXTENSIONS = ['.eml', '.msg'];
const TOOL_NAME = 'Email';
document.addEventListener('DOMContentLoaded', () => {
const fileInput = document.getElementById('file-input') as HTMLInputElement;
const dropZone = document.getElementById('drop-zone');
const processBtn = document.getElementById('process-btn');
const fileDisplayArea = document.getElementById('file-display-area');
const fileControls = document.getElementById('file-controls');
const addMoreBtn = document.getElementById('add-more-btn');
const clearFilesBtn = document.getElementById('clear-files-btn');
const backBtn = document.getElementById('back-to-tools');
if (backBtn) {
backBtn.addEventListener('click', () => {
window.location.href = import.meta.env.BASE_URL;
});
}
const convertOptions = document.getElementById('convert-options');
const updateUI = async () => {
if (!fileDisplayArea || !processBtn || !fileControls) return;
if (state.files.length > 0) {
fileDisplayArea.innerHTML = '';
for (let index = 0; index < state.files.length; index++) {
const file = state.files[index];
const fileDiv = document.createElement('div');
fileDiv.className =
'flex items-center justify-between bg-gray-700 p-3 rounded-lg text-sm';
const infoContainer = document.createElement('div');
infoContainer.className = 'flex flex-col overflow-hidden';
const nameSpan = document.createElement('div');
nameSpan.className = 'truncate font-medium text-gray-200 text-sm mb-1';
nameSpan.textContent = file.name;
const metaSpan = document.createElement('div');
metaSpan.className = 'text-xs text-gray-400';
metaSpan.textContent = formatBytes(file.size);
infoContainer.append(nameSpan, metaSpan);
const removeBtn = document.createElement('button');
removeBtn.className =
'ml-4 text-red-400 hover:text-red-300 flex-shrink-0';
removeBtn.innerHTML = '<i data-lucide="trash-2" class="w-4 h-4"></i>';
removeBtn.onclick = () => {
state.files = state.files.filter((_, i) => i !== index);
updateUI();
};
fileDiv.append(infoContainer, removeBtn);
fileDisplayArea.appendChild(fileDiv);
}
createIcons({ icons });
fileControls.classList.remove('hidden');
if (convertOptions) convertOptions.classList.remove('hidden');
(processBtn as HTMLButtonElement).disabled = false;
} else {
fileDisplayArea.innerHTML = '';
fileControls.classList.add('hidden');
if (convertOptions) convertOptions.classList.add('hidden');
(processBtn as HTMLButtonElement).disabled = true;
}
};
const resetState = () => {
state.files = [];
state.pdfDoc = null;
updateUI();
};
const convertToPdf = async () => {
try {
if (state.files.length === 0) {
showAlert(
'No Files',
`Please select at least one ${TOOL_NAME} file (.eml or .msg).`
);
return;
}
const pageSizeSelect = document.getElementById(
'page-size'
) as HTMLSelectElement;
const includeCcBccCheckbox = document.getElementById(
'include-cc-bcc'
) as HTMLInputElement;
const includeAttachmentsCheckbox = document.getElementById(
'include-attachments'
) as HTMLInputElement;
const pageSize =
(pageSizeSelect?.value as 'a4' | 'letter' | 'legal') || 'a4';
const includeCcBcc = includeCcBccCheckbox?.checked ?? true;
const includeAttachments = includeAttachmentsCheckbox?.checked ?? true;
showLoader('Loading PDF engine...');
const pymupdf = new PyMuPDF(getWasmBaseUrl('pymupdf'));
await pymupdf.load();
if (state.files.length === 1) {
const originalFile = state.files[0];
showLoader(`Parsing ${originalFile.name}...`);
const email = await parseEmailFile(originalFile);
showLoader('Generating PDF...');
const htmlContent = renderEmailToHtml(email, {
includeCcBcc,
includeAttachments,
pageSize,
});
const pdfBlob = await (pymupdf as any).htmlToPdf(htmlContent, {
pageSize,
margins: { top: 50, right: 50, bottom: 50, left: 50 },
attachments: email.attachments
.filter((a) => a.content)
.map((a) => ({
filename: a.filename,
content: a.content!,
})),
});
const fileName = originalFile.name.replace(/\.[^.]+$/, '') + '.pdf';
downloadFile(pdfBlob, fileName);
hideLoader();
showAlert(
'Conversion Complete',
`Successfully converted ${originalFile.name} to PDF.`,
'success',
() => resetState()
);
} else {
showLoader('Converting emails...');
const JSZip = (await import('jszip')).default;
const zip = new JSZip();
for (let i = 0; i < state.files.length; i++) {
const file = state.files[i];
showLoader(
`Converting ${i + 1}/${state.files.length}: ${file.name}...`
);
try {
const email = await parseEmailFile(file);
const htmlContent = renderEmailToHtml(email, {
includeCcBcc,
includeAttachments,
pageSize,
});
const pdfBlob = await (pymupdf as any).htmlToPdf(htmlContent, {
pageSize,
margins: { top: 50, right: 50, bottom: 50, left: 50 },
attachments: email.attachments
.filter((a) => a.content)
.map((a) => ({
filename: a.filename,
content: a.content!,
})),
});
const baseName = file.name.replace(/\.[^.]+$/, '');
const pdfBuffer = await pdfBlob.arrayBuffer();
zip.file(`${baseName}.pdf`, pdfBuffer);
} catch (e: any) {
console.error(`Failed to convert ${file.name}:`, e);
}
}
const zipBlob = await zip.generateAsync({ type: 'blob' });
downloadFile(zipBlob, 'emails-converted.zip');
hideLoader();
showAlert(
'Conversion Complete',
`Successfully converted ${state.files.length} ${TOOL_NAME} file(s) to PDF.`,
'success',
() => resetState()
);
}
} catch (e: any) {
console.error(`[${TOOL_NAME}2PDF] ERROR:`, e);
hideLoader();
showAlert(
'Error',
`An error occurred during conversion. Error: ${e.message}`
);
}
};
const handleFileSelect = (files: FileList | null) => {
if (files && files.length > 0) {
state.files = [...state.files, ...Array.from(files)];
updateUI();
}
};
if (fileInput && dropZone) {
fileInput.addEventListener('change', (e) => {
handleFileSelect((e.target as HTMLInputElement).files);
});
dropZone.addEventListener('dragover', (e) => {
e.preventDefault();
dropZone.classList.add('bg-gray-700');
});
dropZone.addEventListener('dragleave', (e) => {
e.preventDefault();
dropZone.classList.remove('bg-gray-700');
});
dropZone.addEventListener('drop', (e) => {
e.preventDefault();
dropZone.classList.remove('bg-gray-700');
const files = e.dataTransfer?.files;
if (files && files.length > 0) {
const validFiles = Array.from(files).filter((f) => {
const name = f.name.toLowerCase();
return EXTENSIONS.some((ext) => name.endsWith(ext));
});
if (validFiles.length > 0) {
const dataTransfer = new DataTransfer();
validFiles.forEach((f) => dataTransfer.items.add(f));
handleFileSelect(dataTransfer.files);
}
}
});
fileInput.addEventListener('click', () => {
fileInput.value = '';
});
}
if (addMoreBtn) {
addMoreBtn.addEventListener('click', () => {
fileInput.click();
});
}
if (clearFilesBtn) {
clearFilesBtn.addEventListener('click', () => {
resetState();
});
}
if (processBtn) {
processBtn.addEventListener('click', convertToPdf);
}
});

View File

@@ -0,0 +1,393 @@
import PostalMime from 'postal-mime';
import MsgReader from '@kenjiuno/msgreader';
import { formatBytes, escapeHtml } from '../utils/helpers.js';
import type { EmailAttachment, ParsedEmail, EmailRenderOptions } from '@/types';
// Re-export types for convenience
export type { EmailAttachment, ParsedEmail, EmailRenderOptions };
/**
* Format email address without angle brackets for cleaner display
*/
function formatAddress(
name: string | undefined,
email: string | undefined
): string {
if (name && email) {
return `${name} (${email})`;
}
return email || name || '';
}
export async function parseEmlFile(file: File): Promise<ParsedEmail> {
const arrayBuffer = await file.arrayBuffer();
const parser = new PostalMime();
const email = await parser.parse(arrayBuffer);
const from =
formatAddress(email.from?.name, email.from?.address) || 'Unknown Sender';
const to = (email.to || [])
.map((addr) => formatAddress(addr.name, addr.address))
.filter(Boolean);
const cc = (email.cc || [])
.map((addr) => formatAddress(addr.name, addr.address))
.filter(Boolean);
const bcc = (email.bcc || [])
.map((addr) => formatAddress(addr.name, addr.address))
.filter(Boolean);
// Helper to map parsing result to EmailAttachment
const mapAttachment = (att: any): EmailAttachment => {
let content: Uint8Array | undefined;
let size = 0;
if (att.content) {
if (att.content instanceof ArrayBuffer) {
content = new Uint8Array(att.content);
size = content.byteLength;
} else if (att.content instanceof Uint8Array) {
content = att.content;
size = content.byteLength;
}
}
return {
filename: att.filename || 'unnamed',
size,
contentType: att.mimeType || 'application/octet-stream',
content,
contentId: att.contentId
? att.contentId.replace(/^<|>$/g, '')
: undefined,
};
};
const attachments: EmailAttachment[] = [
...(email.attachments || []).map(mapAttachment),
...((email as any).inline || []).map(mapAttachment),
];
// Preserve original date string from headers
let rawDateString = '';
if (email.headers) {
const dateHeader = email.headers.find(
(h) => h.key.toLowerCase() === 'date'
);
if (dateHeader) {
rawDateString = dateHeader.value as string;
}
}
if (!rawDateString && email.date) {
rawDateString = email.date; // fallback if header missing but parsed date exists as string?
}
let parsedDate: Date | null = null;
if (email.date) {
try {
parsedDate = new Date(email.date);
if (isNaN(parsedDate.getTime())) {
parsedDate = null;
}
} catch {
parsedDate = null;
}
}
return {
subject: email.subject || '(No Subject)',
from,
to,
cc,
bcc,
date: parsedDate,
rawDateString,
htmlBody: email.html || '',
textBody: email.text || '',
attachments,
};
}
export async function parseMsgFile(file: File): Promise<ParsedEmail> {
const arrayBuffer = await file.arrayBuffer();
const msgReader = new MsgReader(arrayBuffer);
const msgData = msgReader.getFileData();
const from =
formatAddress(msgData.senderName, msgData.senderEmail) || 'Unknown Sender';
const to: string[] = [];
const cc: string[] = [];
const bcc: string[] = [];
if (msgData.recipients) {
for (const recipient of msgData.recipients) {
const recipientStr = formatAddress(recipient.name, recipient.email);
if (!recipientStr) continue;
const recipType = String(recipient.recipType).toLowerCase();
if (recipType === 'cc' || recipType === '2') {
cc.push(recipientStr);
} else if (recipType === 'bcc' || recipType === '3') {
bcc.push(recipientStr);
} else {
to.push(recipientStr);
}
}
}
const attachments: EmailAttachment[] = (msgData.attachments || []).map(
(att: any) => ({
filename: att.fileName || att.name || 'unnamed',
size: att.content?.length || 0,
contentType: att.mimeType || 'application/octet-stream',
content: att.content ? new Uint8Array(att.content) : undefined,
contentId: att.pidContentId
? att.pidContentId.replace(/^<|>$/g, '')
: undefined,
})
);
let date: Date | null = null;
let rawDateString = '';
if (msgData.messageDeliveryTime) {
rawDateString = msgData.messageDeliveryTime;
date = new Date(msgData.messageDeliveryTime);
} else if (msgData.clientSubmitTime) {
rawDateString = msgData.clientSubmitTime;
date = new Date(msgData.clientSubmitTime);
}
return {
subject: msgData.subject || '(No Subject)',
from,
to,
cc,
bcc,
date,
rawDateString,
htmlBody: msgData.bodyHtml || '',
textBody: msgData.body || '',
attachments,
};
}
/**
* Formats a raw RFC 2822 date string into a nicer human-readable format,
* while preserving the original timezone and time.
* Example input: "Sun, 8 Jan 2017 20:37:44 +0200"
* Example output: "Sunday, January 8, 2017 at 8:37 PM (+0200)"
*/
function formatRawDate(raw: string): string {
try {
// Regex to parse RFC 2822 date parts: Day, DD Mon YYYY HH:MM:SS Timezone
const match = raw.match(
/([A-Za-z]{3}),\s+(\d{1,2})\s+([A-Za-z]{3})\s+(\d{4})\s+(\d{2}):(\d{2})(?::(\d{2}))?\s+([+-]\d{4})/
);
if (match) {
const [
,
dayAbbr,
dom,
monthAbbr,
year,
hoursStr,
minsStr,
secsStr,
timezone,
] = match;
// Map abbreviations to full names
const days: Record<string, string> = {
Sun: 'Sunday',
Mon: 'Monday',
Tue: 'Tuesday',
Wed: 'Wednesday',
Thu: 'Thursday',
Fri: 'Friday',
Sat: 'Saturday',
};
const months: Record<string, string> = {
Jan: 'January',
Feb: 'February',
Mar: 'March',
Apr: 'April',
May: 'May',
Jun: 'June',
Jul: 'July',
Aug: 'August',
Sep: 'September',
Oct: 'October',
Nov: 'November',
Dec: 'December',
};
const fullDay = days[dayAbbr] || dayAbbr;
const fullMonth = months[monthAbbr] || monthAbbr;
// Convert to 12-hour format manually
let hours = parseInt(hoursStr, 10);
const ampm = hours >= 12 ? 'PM' : 'AM';
hours = hours % 12;
hours = hours ? hours : 12; // the hour '0' should be '12'
// Format timezone: +0200 -> UTC+02:00
const tzSign = timezone.substring(0, 1);
const tzHours = timezone.substring(1, 3);
const tzMins = timezone.substring(3, 5);
const formattedTz = `UTC${tzSign}${tzHours}:${tzMins}`;
return `${fullDay}, ${fullMonth} ${dom}, ${year} at ${hours}:${minsStr} ${ampm} (${formattedTz})`;
}
} catch (e) {
// Fallback to raw string if parsing fails
}
return raw;
}
/**
* Replace CID references in HTML with base64 data URIs
*/
function processInlineImages(
html: string,
attachments: EmailAttachment[]
): string {
if (!html) return html;
// Create a map of contentIds to attachments
const cidMap = new Map<string, EmailAttachment>();
attachments.forEach((att) => {
if (att.contentId) {
cidMap.set(att.contentId, att);
}
});
// Replace src="cid:..."
return html.replace(/src=["']cid:([^"']+)["']/g, (match, cid) => {
const att = cidMap.get(cid);
if (att && att.content) {
// Convert Uint8Array to base64
let binary = '';
const len = att.content.byteLength;
for (let i = 0; i < len; i++) {
binary += String.fromCharCode(att.content[i]);
}
const base64 =
typeof btoa === 'function'
? btoa(binary)
: Buffer.from(binary, 'binary').toString('base64');
return `src="data:${att.contentType};base64,${base64}"`;
}
return match; // Keep original if not found
});
}
export function renderEmailToHtml(
email: ParsedEmail,
options: EmailRenderOptions = {}
): string {
const { includeCcBcc = true, includeAttachments = true } = options;
let processedHtml = '';
if (email.htmlBody) {
processedHtml = processInlineImages(email.htmlBody, email.attachments);
} else {
processedHtml = `<pre style="white-space: pre-wrap; font-family: inherit; margin: 0;">${escapeHtml(email.textBody)}</pre>`;
}
// Format date in a human-readable way
let dateStr = 'Unknown Date';
if (email.rawDateString) {
dateStr = formatRawDate(email.rawDateString);
} else if (email.date && !isNaN(email.date.getTime())) {
dateStr = email.date.toLocaleString('en-US', {
weekday: 'long',
year: 'numeric',
month: 'long',
day: 'numeric',
hour: 'numeric',
minute: '2-digit',
hour12: true,
});
}
const attachmentHtml =
includeAttachments && email.attachments.length > 0
? `
<div style="margin-top: 20px; padding-top: 15px; border-top: 1px solid #cccccc;">
<p style="margin: 0 0 8px 0; font-size: 11px; color: #666; font-weight: 600;">Attachments (${email.attachments.length})</p>
<ul style="margin: 0; padding-left: 20px; font-size: 10px; color: #555;">
${email.attachments
.map(
(att) =>
`<li style="margin-bottom: 5px;">${escapeHtml(att.filename)} <span style="color: #999;">(${formatBytes(att.size)})</span></li>`
)
.join('')}
</ul>
</div>
`
: '';
// Build CC/BCC rows
let ccBccHtml = '';
if (includeCcBcc) {
if (email.cc.length > 0) {
ccBccHtml += `
<div style="margin-bottom: 8px;">
<span style="font-weight: 600; color: #666; margin-right: 8px;">CC:</span>
<span style="color: #333;">${escapeHtml(email.cc.join(', '))}</span>
</div>`;
}
if (email.bcc.length > 0) {
ccBccHtml += `
<div style="margin-bottom: 8px;">
<span style="font-weight: 600; color: #666; margin-right: 8px;">BCC:</span>
<span style="color: #333;">${escapeHtml(email.bcc.join(', '))}</span>
</div>`;
}
}
return `<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
</head>
<body style="font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif; line-height: 1.6; color: #333; max-width: 800px; margin: 0 auto; padding: 40px 20px; background: #fff;">
<div style="border-bottom: 2px solid #999999; padding-bottom: 20px; margin-bottom: 30px;">
<h1 style="font-size: 18px; font-weight: 600; color: #1a1a1a; margin: 0 0 12px 0;">${escapeHtml(email.subject)}</h1>
<div style="font-size: 12px; color: #555;">
<div style="margin-bottom: 8px;">
<span style="font-weight: 600; color: #666; margin-right: 8px;">From:</span>
<span style="color: #333;">${escapeHtml(email.from)}</span>
</div>
<div style="margin-bottom: 8px;">
<span style="font-weight: 600; color: #666; margin-right: 8px;">To:</span>
<span style="color: #333;">${escapeHtml(email.to.join(', ') || 'Unknown')}</span>
</div>
${ccBccHtml}
<div style="margin-bottom: 8px;">
<span style="font-weight: 600; color: #666; margin-right: 8px;">Date:</span>
<span style="color: #333;">${escapeHtml(dateStr)}</span>
</div>
</div>
</div>
<div style="font-size: 12px; color: #333;">
${processedHtml}
</div>
${attachmentHtml}
</body>
</html>`;
}
export async function parseEmailFile(file: File): Promise<ParsedEmail> {
const ext = file.name.toLowerCase().split('.').pop();
if (ext === 'eml') {
return parseEmlFile(file);
} else if (ext === 'msg') {
return parseMsgFile(file);
} else {
throw new Error(`Unsupported file type: .${ext}`);
}
}