Files
kill-the-news/src/utils/email-parser.ts
T
Julien Herr c65aabe7f4 refactor(domain): add FeedId, EmailAddress and Domain value objects
Encapsulate the email/domain/feed-id parsing that was scattered as ad-hoc
regexes and split("@") calls into three small immutable value objects under
src/domain/value-objects/. EmailParser.extractFeedId and generateFeedId now
delegate to FeedId; the sender policy, favicon domain extraction and the admin
SenderField parse through EmailAddress/Domain.

Left as-is on purpose: forwardemail's multi-address free-text extraction and the
admin allow/block list normaliser, which operate on mixed email-or-domain input
that the single-address value objects would reject.

Behaviour-preserving; adds unit tests for each value object.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-24 00:05:46 +02:00

84 lines
2.5 KiB
TypeScript

import { EmailData } from "../types";
import { FeedId } from "../domain/value-objects/feed-id";
export class EmailParser {
// Matches noun1.noun2.XY (the feed ID format) before the @ symbol
static extractFeedId(emailAddress: string): string | null {
return FeedId.parse(emailAddress)?.value ?? null;
}
// eslint-disable-next-line @typescript-eslint/no-explicit-any
static parseForwardEmailPayload(payload: any): EmailData {
if (!payload) {
throw new Error("Missing or invalid webhook payload");
}
const fromAddress =
payload.from?.text ||
(payload.from?.value?.[0]?.address
? `${payload.from.value[0].name || ""} <${payload.from.value[0].address}>`
: "Unknown Sender");
const subject = this.decodeEncodedWords(payload.subject || "No Subject");
const content = payload.html || payload.text || "";
return {
subject,
from: fromAddress,
content,
receivedAt: payload.date ? new Date(payload.date).getTime() : Date.now(),
headers: this.extractHeaders(payload),
};
}
// eslint-disable-next-line @typescript-eslint/no-explicit-any
private static extractHeaders(payload: any): Record<string, string> {
const headers: Record<string, string> = {};
if (payload.headerLines && Array.isArray(payload.headerLines)) {
payload.headerLines.forEach((h: { key: string; line: string }) => {
const key = h.key.toLowerCase();
const value = h.line
.replace(new RegExp(`^${h.key}:\\s*`, "i"), "")
.trim();
headers[key] = value;
});
} else if (typeof payload.headers === "string") {
payload.headers.split(/\r?\n/).forEach((line: string) => {
const match = line.match(/^([^:]+):\s*(.*)$/);
if (match) {
headers[match[1].toLowerCase()] = match[2];
}
});
}
return headers;
}
static decodeEncodedWords(text: string): string {
if (!text) return "";
return text.replace(
/=\?([^?]+)\?([BQ])\?([^?]+)\?=/gi,
(_, charset, encoding, text) => {
if (encoding.toUpperCase() === "B") {
try {
return atob(text);
} catch {
return text;
}
} else if (encoding.toUpperCase() === "Q") {
return this.decodeQuotedPrintable(text.replace(/_/g, " "));
}
return text;
},
);
}
private static decodeQuotedPrintable(text: string): string {
return text.replace(/=([0-9A-F]{2})/gi, (_, hex) => {
return String.fromCharCode(parseInt(hex, 16));
});
}
}