feat: Enhance email processing to include parsed HTML body content in inbound email records

Closes #342
This commit is contained in:
Dries Augustyns
2026-04-13 17:58:52 +02:00
parent ae64c2dbb5
commit e3395083db
5 changed files with 116 additions and 27 deletions
+2
View File
@@ -36,6 +36,7 @@
"ioredis": "^5.8.2", "ioredis": "^5.8.2",
"jsonwebtoken": "^9.0.2", "jsonwebtoken": "^9.0.2",
"mailchecker": "^6.0.19", "mailchecker": "^6.0.19",
"mailparser": "^3.9.8",
"morgan": "^1.10.0", "morgan": "^1.10.0",
"multer": "^2.1.1", "multer": "^2.1.1",
"signale": "^1.4.0", "signale": "^1.4.0",
@@ -48,6 +49,7 @@
"@types/express": "^5.0.5", "@types/express": "^5.0.5",
"@types/helmet": "^4.0.0", "@types/helmet": "^4.0.0",
"@types/jsonwebtoken": "^9.0.6", "@types/jsonwebtoken": "^9.0.6",
"@types/mailparser": "^3.4.6",
"@types/morgan": "^1.9.9", "@types/morgan": "^1.9.9",
"@types/multer": "^2.0.0", "@types/multer": "^2.0.0",
"@types/signale": "^1.4.7", "@types/signale": "^1.4.7",
+21 -3
View File
@@ -2,6 +2,7 @@ import {Controller, Post} from '@overnightjs/core';
import type {Prisma} from '@plunk/db'; import type {Prisma} from '@plunk/db';
import {EmailSourceType, EmailStatus} from '@plunk/db'; import {EmailSourceType, EmailStatus} from '@plunk/db';
import type {Request, Response} from 'express'; import type {Request, Response} from 'express';
import {simpleParser} from 'mailparser';
import signale from 'signale'; import signale from 'signale';
import type Stripe from 'stripe'; import type Stripe from 'stripe';
@@ -146,6 +147,21 @@ export class Webhooks {
const senderEmail = body.mail?.source; const senderEmail = body.mail?.source;
const senderFromHeader = body.mail?.commonHeaders?.from?.[0] || senderEmail; const senderFromHeader = body.mail?.commonHeaders?.from?.[0] || senderEmail;
// Parse email content if available
let htmlBody: string | undefined;
if (body.content) {
try {
const parsed = await simpleParser(body.content);
// Prefer HTML body, fallback to text if no HTML available
htmlBody = parsed.html ? String(parsed.html) : parsed.text || undefined;
signale.info('[WEBHOOK] Email content parsed successfully');
} catch (parseError) {
signale.error('[WEBHOOK] Failed to parse email content:', parseError);
// Continue processing without content
}
}
// Process inbound email for each project that has this domain verified // Process inbound email for each project that has this domain verified
for (const domainRecord of domainRecords) { for (const domainRecord of domainRecords) {
signale.info(`[WEBHOOK] Processing inbound email for project: ${domainRecord.project.name}`); signale.info(`[WEBHOOK] Processing inbound email for project: ${domainRecord.project.name}`);
@@ -171,13 +187,13 @@ export class Webhooks {
); );
} }
// Create an Email record for tracking (no actual email content since it's inbound) // Create an Email record for tracking with parsed content
const inboundEmail = await prisma.email.create({ const inboundEmail = await prisma.email.create({
data: { data: {
projectId: domainRecord.projectId, projectId: domainRecord.projectId,
contactId: contact!.id, contactId: contact!.id,
subject: body.mail?.commonHeaders?.subject || '(No subject)', subject: body.mail?.commonHeaders?.subject || '(No subject)',
body: '', // Inbound emails don't have body content in our system body: htmlBody || '', // Store HTML body in the body field
from: recipientEmail, // The recipient address that received the email from: recipientEmail, // The recipient address that received the email
sourceType: EmailSourceType.INBOUND, sourceType: EmailSourceType.INBOUND,
status: EmailStatus.RECEIVED, // Inbound emails use RECEIVED status status: EmailStatus.RECEIVED, // Inbound emails use RECEIVED status
@@ -197,7 +213,7 @@ export class Webhooks {
); );
} }
// Prepare event data with all inbound email details // Prepare event data with all inbound email details including body content
const eventData = { const eventData = {
messageId: body.mail?.messageId, messageId: body.mail?.messageId,
from: senderEmail, from: senderEmail,
@@ -207,6 +223,8 @@ export class Webhooks {
timestamp: body.mail?.timestamp, timestamp: body.mail?.timestamp,
recipients: body.receipt?.recipients, recipients: body.receipt?.recipients,
hasContent: !!body.content, hasContent: !!body.content,
// Email body content
body: htmlBody,
// Security verdicts // Security verdicts
spamVerdict: body.receipt?.spamVerdict?.status, spamVerdict: body.receipt?.spamVerdict?.status,
virusVerdict: body.receipt?.virusVerdict?.status, virusVerdict: body.receipt?.virusVerdict?.status,
@@ -65,24 +65,58 @@ Create a new workflow and use `email.received` as the trigger event. This workfl
The `email.received` event includes the following data that you can use in your workflow steps: The `email.received` event includes the following data that you can use in your workflow steps:
| Field | Type | Description | | Field | Type | Description |
| ---------------------- | -------- | ---------------------------------------------- | | ---------------------- | -------- | ------------------------------------------------- |
| `messageId` | string | Unique identifier for the received message | | `messageId` | string | Unique identifier for the received message |
| `from` | string | Email address of the sender | | `from` | string | Email address of the sender |
| `fromHeader` | string | Full "From" header including display name | | `fromHeader` | string | Full "From" header including display name |
| `to` | string | Primary recipient email address | | `to` | string | Primary recipient email address |
| `subject` | string | Email subject line | | `subject` | string | Email subject line |
| `timestamp` | string | ISO 8601 timestamp when the email was received | | `timestamp` | string | ISO 8601 timestamp when the email was received |
| `recipients` | string[] | All recipient email addresses | | `recipients` | string[] | All recipient email addresses |
| `hasContent` | boolean | Whether the email body was captured | | `hasContent` | boolean | Whether the email body was captured |
| `spamVerdict` | string | Spam check result (e.g., "PASS", "FAIL") | | `body` | string | HTML body of the email (or plain text if no HTML) |
| `virusVerdict` | string | Virus scan result (e.g., "PASS", "FAIL") | | `spamVerdict` | string | Spam check result (e.g., "PASS", "FAIL") |
| `spfVerdict` | string | SPF authentication result | | `virusVerdict` | string | Virus scan result (e.g., "PASS", "FAIL") |
| `dkimVerdict` | string | DKIM authentication result | | `spfVerdict` | string | SPF authentication result |
| `dmarcVerdict` | string | DMARC authentication result | | `dkimVerdict` | string | DKIM authentication result |
| `processingTimeMillis` | number | Time taken to process the email | | `dmarcVerdict` | string | DMARC authentication result |
| `processingTimeMillis` | number | Time taken to process the email |
You can access these fields in your workflow using variable syntax, for example: `{{event.subject}}` or `{{event.from}}`. You can access these fields in your workflow using variable syntax, for example: `{{event.subject}}`, `{{event.from}}`, or `{{event.body}}`.
### Example: Auto-reply workflow
Here's a simple workflow that sends an automatic reply when an email is received at `[email protected]`:
1. **Trigger**: `email.received`
2. **Condition**: Check if `{{event.to}}` equals `[email protected]`
3. **Send Email**:
- **To**: `{{event.from}}`
- **Subject**: `Re: {{event.subject}}`
- **Body**: `Thank you for your message. We received: "{{event.body}}". We'll get back to you soon!`
This workflow reads the incoming email body and includes it in the auto-reply response.
### Example: Forward to webhook
For more advanced processing (like ticket creation or AI analysis), you can forward the email content to your own API:
1. **Trigger**: `email.received`
2. **Webhook**:
- **URL**: `https://api.example.com/support/tickets`
- **Method**: `POST`
- **Body**:
```json
{
"from": "{{event.from}}",
"subject": "{{event.subject}}",
"body": "{{event.body}}",
"timestamp": "{{event.timestamp}}"
}
```
Your backend receives the full email content and can process it (create a ticket, run AI analysis, etc.).
## Multi-project domains ## Multi-project domains
@@ -96,12 +130,6 @@ This allows you to segment inbound email handling across different projects if n
## Limitations ## Limitations
<Callout title="Email body content" variant="warning">
Currently, the email body content is not stored or made available in the event data. Only metadata (sender, subject,
recipients, timestamps, and security verdicts) is captured. The `hasContent` field indicates whether body content was
present, but the content itself is not accessible in workflows.
</Callout>
- **Catch-all addresses**: Plunk receives emails sent to any address at your verified domain (e.g., `[email protected]`). You can use workflow conditions to route emails based on the `to` field. - **Catch-all addresses**: Plunk receives emails sent to any address at your verified domain (e.g., `[email protected]`). You can use workflow conditions to route emails based on the `to` field.
- **Attachments**: Email attachments are not currently captured or stored. - **Attachments**: Email attachments are not currently captured or stored.
- **Email size**: AWS SES has a maximum message size limit of 40 MB for inbound emails. - **Email size**: AWS SES has a maximum message size limit of 40 MB for inbound emails.
@@ -324,6 +324,7 @@ This event fires when an email is received at your verified domain. See [Receivi
"timestamp": "2025-01-15T10:30:00.000Z", "timestamp": "2025-01-15T10:30:00.000Z",
"recipients": ["[email protected]"], "recipients": ["[email protected]"],
"hasContent": true, "hasContent": true,
"body": "<html><body>This is the email body content...</body></html>",
"spamVerdict": "PASS", "spamVerdict": "PASS",
"virusVerdict": "PASS", "virusVerdict": "PASS",
"spfVerdict": "PASS", "spfVerdict": "PASS",
@@ -343,6 +344,7 @@ This event fires when an email is received at your verified domain. See [Receivi
| `timestamp` | When SES received the email | | `timestamp` | When SES received the email |
| `recipients` | All recipient addresses in the envelope | | `recipients` | All recipient addresses in the envelope |
| `hasContent` | Whether the email body content is available | | `hasContent` | Whether the email body content is available |
| `body` | HTML body of the email (or plain text if no HTML available) |
| `spamVerdict` | SES spam check result: `PASS`, `FAIL`, `GRAY`, or `PROCESSING_FAILED` | | `spamVerdict` | SES spam check result: `PASS`, `FAIL`, `GRAY`, or `PROCESSING_FAILED` |
| `virusVerdict` | SES virus check result | | `virusVerdict` | SES virus check result |
| `spfVerdict` | SPF authentication result | | `spfVerdict` | SPF authentication result |
+40 -1
View File
@@ -6710,7 +6710,7 @@ __metadata:
languageName: node languageName: node
linkType: hard linkType: hard
"@types/mailparser@npm:^3.4.4": "@types/mailparser@npm:^3.4.4, @types/mailparser@npm:^3.4.6":
version: 3.4.6 version: 3.4.6
resolution: "@types/mailparser@npm:3.4.6" resolution: "@types/mailparser@npm:3.4.6"
dependencies: dependencies:
@@ -7871,6 +7871,7 @@ __metadata:
"@types/express": "npm:^5.0.5" "@types/express": "npm:^5.0.5"
"@types/helmet": "npm:^4.0.0" "@types/helmet": "npm:^4.0.0"
"@types/jsonwebtoken": "npm:^9.0.6" "@types/jsonwebtoken": "npm:^9.0.6"
"@types/mailparser": "npm:^3.4.6"
"@types/morgan": "npm:^1.9.9" "@types/morgan": "npm:^1.9.9"
"@types/multer": "npm:^2.0.0" "@types/multer": "npm:^2.0.0"
"@types/signale": "npm:^1.4.7" "@types/signale": "npm:^1.4.7"
@@ -7889,6 +7890,7 @@ __metadata:
ioredis: "npm:^5.8.2" ioredis: "npm:^5.8.2"
jsonwebtoken: "npm:^9.0.2" jsonwebtoken: "npm:^9.0.2"
mailchecker: "npm:^6.0.19" mailchecker: "npm:^6.0.19"
mailparser: "npm:^3.9.8"
morgan: "npm:^1.10.0" morgan: "npm:^1.10.0"
multer: "npm:^2.1.1" multer: "npm:^2.1.1"
signale: "npm:^1.4.0" signale: "npm:^1.4.0"
@@ -12996,6 +12998,18 @@ __metadata:
languageName: node languageName: node
linkType: hard linkType: hard
"libmime@npm:5.3.8":
version: 5.3.8
resolution: "libmime@npm:5.3.8"
dependencies:
encoding-japanese: "npm:2.2.0"
iconv-lite: "npm:0.7.2"
libbase64: "npm:1.3.0"
libqp: "npm:2.1.1"
checksum: 10c0/4fb65f7c07a9bdb0c0ee25bb80fac94a803807f9ac15a3d6cafc2c93303500d92c8ceb6dfe0ab938c871406fc01cb69a7a457f28b2037c47c283574e8900d8c4
languageName: node
linkType: hard
"libqp@npm:2.1.1": "libqp@npm:2.1.1":
version: 2.1.1 version: 2.1.1
resolution: "libqp@npm:2.1.1" resolution: "libqp@npm:2.1.1"
@@ -13400,6 +13414,24 @@ __metadata:
languageName: node languageName: node
linkType: hard linkType: hard
"mailparser@npm:^3.9.8":
version: 3.9.8
resolution: "mailparser@npm:3.9.8"
dependencies:
"@zone-eu/mailsplit": "npm:5.4.8"
encoding-japanese: "npm:2.2.0"
he: "npm:1.2.0"
html-to-text: "npm:9.0.5"
iconv-lite: "npm:0.7.2"
libmime: "npm:5.3.8"
linkify-it: "npm:5.0.0"
nodemailer: "npm:8.0.5"
punycode.js: "npm:2.3.1"
tlds: "npm:1.261.0"
checksum: 10c0/7d86b57cb6b676902d4547d573bb40c660b5adf1024b418ddd02a584af3b5a64b20d2153d94ea8b666034939e1f156b823f9f6ee3ddfbd2a2ae61920c7c3fc0a
languageName: node
linkType: hard
"make-dir@npm:^4.0.0": "make-dir@npm:^4.0.0":
version: 4.0.0 version: 4.0.0
resolution: "make-dir@npm:4.0.0" resolution: "make-dir@npm:4.0.0"
@@ -14832,6 +14864,13 @@ __metadata:
languageName: node languageName: node
linkType: hard linkType: hard
"nodemailer@npm:8.0.5":
version: 8.0.5
resolution: "nodemailer@npm:8.0.5"
checksum: 10c0/5e8450499bd059c56d74ba96fa5f9928de2ecdae0d53c083dba5661d797114c1f9524d30f992d0263cc5a7dcf5a54b9c1d92dc1f766da150c9d0bde7d3798431
languageName: node
linkType: hard
"nopt@npm:^9.0.0": "nopt@npm:^9.0.0":
version: 9.0.0 version: 9.0.0
resolution: "nopt@npm:9.0.0" resolution: "nopt@npm:9.0.0"