diigo-cache: RSS in diigo's export shape, from cached items

src/rss.ts renders items as RSS 2.0 in the shape of diigo's RSS export:
title, link, and a description packing Tags:…;Description:…;
Annotations and Sticky notes:… (Highlight:/Sticky notes: lines). Unlike
the export it is well-formed (characters XML forbids are dropped; the
export carries some raw) and keeps whole titles (the export cuts at
255). Pure: dates come from the caller.

scripts/compare-export.ts (a program script: node, node:sqlite) loads a
cache's items, writes the RSS, and compares it with an export, keyed on
link, reporting counts by category.

Generated-by: Claude Opus 5.5

diigo-cache/src/rss.ts

@@ -0,0 +1,61 @@
+/**
+ * @file cached diigo items as RSS 2.0, in the shape of diigo's RSS export
+ * (`Tags:…;Description:…;Annotations and Sticky notes:…`), but well-formed
+ * and with titles uncut. Pure: the caller supplies the dates.
+ */
+
+import type { Item } from "./items.js";
+
+/** characters XML 1.0 forbids (the C0 controls but tab, LF, CR);
+ * diigo's export carries some raw, so strict parsers reject it */
+const XML_FORBIDDEN = /[\u0000-\u0008\u000B\u000C\u000E-\u001F]/g;
+
+/** text as one or more CDATA sections: forbidden characters dropped,
+ * a literal `]]>` split across two sections */
+function cdata(text: string): string {
+	return `<![CDATA[${text.replace(XML_FORBIDDEN, "").replaceAll("]]>", "]]]]><![CDATA[>")}]]>`;
+}
+
+const str = (v: unknown): string => (typeof v === "string" ? v : "");
+const list = (v: unknown): Record<string, unknown>[] => (Array.isArray(v) ? (v as Record<string, unknown>[]) : []);
+
+/**
+ * the packed description diigo's export uses:
+ * `Tags:a,b;Description:…;Annotations and Sticky notes:…` — tags
+ * comma-separated (`no_tag` when none), then each highlight as
+ * `Highlight:<text>\n` followed by its sticky notes, one
+ * `Sticky notes:<text>\n` each (notes may span lines)
+ */
+export function itemDescription(item: Item): string {
+	const tags = str(item.tags) || "no_tag";
+	const notes = list(item.annotations)
+		.map((a) => `Highlight:${str(a.content)}\n${list(a.stickyNotes).map((n) => `Sticky notes:${str(n.content)}\n`).join("")}`)
+		.join("");
+	return `Tags:${tags};Description:${str(item.description)};Annotations and Sticky notes:${notes}`;
+}
+
+/** one `<item>`: title, link, packed description. The title is whole
+ * (diigo's export cuts titles at 255 characters). */
+export function rssItem(item: Item): string {
+	return `<item><title>${cdata(str(item.title))}</title><link>${cdata(str(item.url))}</link><description>${cdata(itemDescription(item))}</description></item>`;
+}
+
+/**
+ * a whole feed
+ *
+ * @param channel `pubDate` in RFC 822 form is the caller's to supply
+ * (no clock here)
+ */
+export function toRss(items: Item[], channel: { title: string; pubDate: string }): string {
+	return `<?xml version="1.0"?>
+<rss version="2.0">
+<channel>
+<title>${cdata(channel.title)}</title>
+<link></link>
+<pubDate>${channel.pubDate}</pubDate>
+<lastBuildDate>${channel.pubDate}</lastBuildDate>
+${items.map(rssItem).join("\n")}
+</channel>
+</rss>
+`;
+}