Migrate legacy archive pages

src/lib/archive.ts

@@ -0,0 +1,134 @@
+import type { CollectionEntry } from "astro:content";
+import { getCollection } from "astro:content";
+
+export type ArchiveEntry = CollectionEntry<"archive">;
+
+const entityMap: Record<string, string> = {
+  amp: "&",
+  apos: "'",
+  hellip: "...",
+  laquo: "<<",
+  nbsp: " ",
+  quot: '"',
+  raquo: ">>",
+  rsquo: "'",
+  lsquo: "'",
+  rdquo: '"',
+  ldquo: '"',
+};
+
+export function decodeEntities(value = ""): string {
+  return value.replace(/&(#x?[0-9a-f]+|[a-z]+);/gi, (match, entity) => {
+    const key = entity.toLowerCase();
+    if (key.startsWith("#x")) {
+      return String.fromCodePoint(Number.parseInt(key.slice(2), 16));
+    }
+    if (key.startsWith("#")) {
+      return String.fromCodePoint(Number.parseInt(key.slice(1), 10));
+    }
+    return entityMap[key] ?? match;
+  });
+}
+
+export function textFromHtml(html = ""): string {
+  return decodeEntities(
+    html
+      .replace(/<script[\s\S]*?<\/script>/gi, " ")
+      .replace(/<style[\s\S]*?<\/style>/gi, " ")
+      .replace(/<[^>]+>/g, " "),
+  )
+    .replace(/\s+/g, " ")
+    .trim();
+}
+
+export function excerptFromBody(body = "", maxLength = 230): string {
+  const text = textFromHtml(body);
+  if (text.length <= maxLength) {
+    return text;
+  }
+
+  const clipped = text.slice(0, maxLength - 3);
+  const finalSpace = clipped.lastIndexOf(" ");
+  return `${finalSpace > 80 ? clipped.slice(0, finalSpace) : clipped}...`;
+}
+
+export function slugify(value: string): string {
+  return value
+    .toLowerCase()
+    .replace(/&amp;/g, "and")
+    .replace(/[^a-z0-9]+/g, "-")
+    .replace(/^-|-$/g, "");
+}
+
+export function formatDate(value?: string): string | undefined {
+  if (!value) {
+    return undefined;
+  }
+
+  const date = new Date(value);
+  if (Number.isNaN(date.valueOf())) {
+    return undefined;
+  }
+
+  return new Intl.DateTimeFormat("en-US", {
+    month: "long",
+    day: "numeric",
+    year: "numeric",
+  }).format(date);
+}
+
+export function sortByPublishedDesc(entries: ArchiveEntry[]): ArchiveEntry[] {
+  return [...entries].sort((a, b) => {
+    const dateA = Date.parse(a.data.published ?? "");
+    const dateB = Date.parse(b.data.published ?? "");
+
+    if (!Number.isNaN(dateA) && !Number.isNaN(dateB) && dateA !== dateB) {
+      return dateB - dateA;
+    }
+
+    return (a.data.title ?? a.id).localeCompare(b.data.title ?? b.id);
+  });
+}
+
+export async function getArchiveEntries(type?: "blog" | "speech"): Promise<ArchiveEntry[]> {
+  const entries = await getCollection("archive");
+  return sortByPublishedDesc(type ? entries.filter((entry) => entry.data.type === type) : entries);
+}
+
+export function uniqueSorted(values: string[]): string[] {
+  return Array.from(new Set(values.filter(Boolean))).sort((a, b) => a.localeCompare(b));
+}
+
+export function blogCategorySlug(category: string): string {
+  return slugify(category);
+}
+
+export function blogTagSlug(tag: string): string {
+  return slugify(tag);
+}
+
+export function speechCategorySlug(category: string): string {
+  if (category.toLowerCase().includes("hak ja han moon")) {
+    return "mrs-hak-ja-han-moon";
+  }
+
+  const year = category.match(/\b(1\d{3}|20\d{2})\b/)?.[1];
+  if (year === "1956") {
+    return "rev-sun-myung-moon";
+  }
+
+  return year ? `rev-sun-myung-moon-${year}` : "rev-sun-myung-moon";
+}
+
+export function categoryHref(entry: ArchiveEntry, category: string): string {
+  if (entry.data.type === "speech") {
+    return `/speeches/categories/${speechCategorySlug(category)}.html`;
+  }
+
+  return `/blog/categories/${blogCategorySlug(category)}.html`;
+}
+
+export function tagHref(tag: string): string {
+  return `/blog/tags/${blogTagSlug(tag)}.html`;
+}
+

src/lib/legacy-page.ts

@@ -0,0 +1,15 @@
+import fs from "node:fs";
+import path from "node:path";
+import { legacyHtmlRoot } from "./static-pages";
+
+export function legacyPageArticle(relativePath: string): string {
+  const html = fs.readFileSync(path.join(legacyHtmlRoot, relativePath), "utf8");
+  const match = html.match(/<div id="post-[\s\S]*?<\/div><!-- #post-## -->/);
+
+  if (!match) {
+    throw new Error(`Could not find page article in ${relativePath}`);
+  }
+
+  return match[0];
+}
+

src/lib/static-pages.ts

@@ -4,16 +4,37 @@ import path from "node:path";
 export const repoRoot = process.cwd();
 export const legacyHtmlRoot = path.join(repoRoot, "archive-source");
 export const migratedHtmlPages = new Set([
+  "2013-sunday-service-archive.html",
+  "2014-sunday-services.html",
+  "2015-sunday-services-archive.html",
+  "2016-sunday-service-archive.html",
+  "2017-sunday-service-archive.html",
+  "2018-sunday-service-archive.html",
   "about.html",
+  "about-us-organizations.html",
+  "archive-sunday-services-2013.html",
+  "archive-sunday-services-2014.html",
+  "archive-sunday-services-2015.html",
+  "archive-sunday-services-2016.html",
+  "archive-sunday-services-2017.html",
+  "archive-sunday-services-2018.html",
   "contact.html",
   "events.html",
   "index.html",
+  "register.html",
   "services.html",
   "speeches/index.html",
   "the-founders.html",
   "videos.html",
 ]);
 
+const migratedHtmlPrefixes = [
+  "blog/categories/",
+  "blog/tags/",
+  "speeches/categories/",
+  "speeches/rev-dr-sun-myung-moon/",
+];
+
 export function walkHtmlFiles(dir = legacyHtmlRoot): string[] {
   return fs.readdirSync(dir, { withFileTypes: true }).flatMap((entry) => {
     const fullPath = path.join(dir, entry.name);
@@ -37,7 +58,7 @@ export function routeFromRelativePath(relativePath: string): string {
 }
 
 export function isMigratedHtmlPage(relativePath: string): boolean {
-  return migratedHtmlPages.has(relativePath);
+  return migratedHtmlPages.has(relativePath) || migratedHtmlPrefixes.some((prefix) => relativePath.startsWith(prefix));
 }
 
 export function sourcePathFromRoute(route = ""): string {