Files
kill-the-news/src/domain/email-parser.ts
T
Julien HerrandClaude Opus 4.7 1a4a479190 feat: decouple read FeedId from inbound MailboxId
Separate the two feed identities so the public read URL never reveals the
inbound address and vice-versa:

- FeedId becomes an opaque high-entropy token (read id + KV key); MailboxId
  (noun.noun.NN) owns the inbound address and the untrusted-input boundary
  via MailboxId.parse. They map only through the inbound:<mailbox> secondary
  index, resolved solely at reception.
- inbound index lifecycle is owned by FeedRepository: written by save/saveConfig,
  dropped by removeFromList(Bulk) — symmetric, never mirrored by hand (removes the
  manual delete in feed-service + the cron loop, and a silent empty-catch).
- Feed.mailboxId exposes a MailboxId VO (symmetry with Feed.id); the
  mailbox@domain shape lives on MailboxId.emailAddress(domain).
- Distinguish mailbox_unknown (no feed claims the address) from feed_not_found
  (dangling index) for observability; both forwardable, both 404.
- Drop the redundant EmailParser.extractMailbox pass-through so MailboxId.parse
  is the single parse boundary.

Docs (README/INSTALL/CLAUDE.md/landing) and tests updated; 439 tests green,
tsc clean, build dry-run OK.

Co-Authored-By: Claude Opus 4.7 <[email protected]>
2026-05-24 22:46:37 +02:00

78 lines
2.3 KiB
TypeScript

import { EmailData } from "../types";
export class EmailParser {
// 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));
});
}
}