GitHub/kill-the-news
1
0
Fork 0
mirror of https://github.com/juherr/kill-the-news.git synced 2026-06-20 22:03:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(attachments): render inline cid images in place, not as attachments

Browse Source 
Inline images (referenced by src="cid:…") are now classified at ingest and
kept out of the downloadable attachment lists, RSS/Atom enclosures, and the
API — while still stored in R2 and cleaned up with the email. Fixes the admin
email preview, which injected raw HTML into the data: iframe so cid refs never
resolved; it now rewrites them to absolute /files URLs.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Julien Herr
2026-05-24 14:39:59 +02:00
parent be45e70571
commit 5137637181
14 changed files with 277 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/infrastructure/feed-generator.ts
+2 -1
View File
@@ -54,7 +54,8 @@ function buildFeed(
for (const email of emails) {
const entryUrl = `${baseUrl}/entries/${feedId}/${email.receivedAt}`;
const firstAttachment = email.attachments?.[0];
// Inline images are rendered in the body, not surfaced as an enclosure.
const firstAttachment = email.attachments?.find((a) => !a.inline);
const bodyContent = processEmailContent(
email.content,
email.attachments,
src/infrastructure/html-processor.test.ts
+21 -1
View File
@@ -1,5 +1,5 @@
import { describe, it, expect } from "vitest";
import { processEmailContent } from "./html-processor";
import { processEmailContent, extractInlineCids } from "./html-processor";
import type { AttachmentData } from "../types";
describe("processEmailContent — body extraction", () => {
@@ -196,3 +196,23 @@ describe("processEmailContent — inline cid: rewriting", () => {
expect(result).toContain('src="https://example.com/a.png"');
});
});
describe("extractInlineCids", () => {
it("collects normalized cids referenced by cid: image sources", () => {
const html = '<body><img src="cid:ii_abc"/><img src="CID:ii_def"/></body>';
expect(extractInlineCids(html)).toEqual(new Set(["ii_abc", "ii_def"]));
});
it("ignores non-cid sources", () => {
const html = '<body><img src="https://example.com/a.png"/></body>';
expect(extractInlineCids(html).size).toBe(0);
});
it("returns an empty set for plain text", () => {
expect(extractInlineCids("just text, no html").size).toBe(0);
});
it("returns an empty set for empty input", () => {
expect(extractInlineCids("").size).toBe(0);
});
});
src/infrastructure/html-processor.ts
+16
View File
@@ -12,6 +12,22 @@ export function normalizeCid(
return trimmed || undefined;
}
// Collect the normalized Content-IDs referenced by `cid:` image sources in the
// email body — exactly the set rewriteCidSrc would turn into inline <img> URLs.
// Used at ingest to flag those attachments as inline (rendered in place, hidden
// from the downloadable attachment lists).
export function extractInlineCids(content: string): Set<string> {
const cids = new Set<string>();
if (!content || isPlainText(content)) return cids;
const { document } = parseHTML(content);
document.querySelectorAll("[src]").forEach((el: Element) => {
const match = (el.getAttribute("src") ?? "").match(/^\s*cid:(.+)$/i);
const cid = match ? normalizeCid(match[1]) : undefined;
if (cid) cids.add(cid);
});
return cids;
}
function cleanMsoStyles(style: string): string {
return style
.split(";")