feat(cli): sync LeetCode topic tags, generate guide placeholders, and write video frontmatter instead of embeds

apps/cli/sync.ts

@@ -2,20 +2,32 @@
 /**
  * Sync work/1 leetcode solutions into apps/docs/content/ pages.
  *
- * - New problems get a full page (frontmatter, badge, warning, examples,
+ * - New problems get a full page (frontmatter, warning, examples,
  *   constraints, solution) in the gold-standard format.
  * - Already-ported pages only get their script-owned parts regenerated — the
- *   frontmatter `icon:` (`PAGE_ICON`), the `<Badge>` line and the
- *   `## Solution` section — so hand-curated prose is never touched.
+ *   frontmatter `icon:` (`PAGE_ICON`) and the `## Solution` section — so
+ *   hand-curated prose is never touched.
  * - When a problem is solved in both JavaScript and Python the solution
  *   renders as a <CodeGroup> (Python first); single-language solutions
  *   render as a plain fence.
+ * - Every page carries LeetCode's own topic tags as frontmatter `topics:`
+ *   (`{ name, slug }` per tag, LeetCode's order), fetched from the GraphQL
+ *   `topicTags` once — when the page is created, or on any later run that
+ *   finds the key missing — and never refreshed after, so a sync with nothing
+ *   new makes no request. Delete the key to refetch it. The page itself
+ *   renders no badges: the docs `PageHeader` slot
+ *   (`apps/docs/components/ProblemBadges.astro`) turns `topics:` and the
+ *   `video:` key `videos.ts` writes into the badge row above the title.
+ * - Every tag a page carries that no campaign topic teaches (not a key of
+ *   `apps/docs/topic-landings.ts`) gets a placeholder guide page,
+ *   `guides/<slug>.mdx`, with `list:` pointing at LeetCode's problem list for
+ *   the tag. Created once (a missing or empty file), then hand-owned; the tag's
+ *   badge on a problem page links to it.
  *
- * Two classifications, two homes. The sidebar group is the campaign TOPIC
- * from the README table (`tree-dfs/`, ordered by topic number via a
- * script-owned `meta.ts`); the page badge is the data-structure CATEGORY the
- * file sits under in `work/1/<Difficulty>/<Category>/`. A problem outside the
- * plan (warm-ups) has no topic, so it groups under its category instead.
+ * The sidebar group is the campaign TOPIC from the README table (`tree-dfs/`,
+ * ordered by topic number via a script-owned `meta.ts`). A problem outside the
+ * plan (warm-ups) has no topic, so it groups under the data-structure CATEGORY
+ * its file sits under in `work/1/<Difficulty>/<Category>/` instead.
  *
  * Topics nest under their README PHASE: `(01-linear-structures)/tree-dfs/`.
  * The phase folder is a Blume `(group)` — a sidebar section with its own
@@ -38,6 +50,8 @@
 import { mkdir, readdir, rename, rmdir, unlink } from "node:fs/promises";
 import { basename, dirname, join } from "node:path";
 
+import { TOPIC_LANDINGS } from "../docs/topic-landings.ts";
+
 const ROOT = join(import.meta.dir, "..", "..");
 const WORK = join(ROOT, "work", "1");
 const DOCS = join(ROOT, "apps", "docs", "content");
@@ -316,6 +330,83 @@ function groupMeta(topic: Topic): string {
   return `import { defineMeta } from "blume";\n\nexport default defineMeta({ ${fields.join(", ")} });\n`;
 }
 
+// ── LeetCode topic tags ──────────────────────────────────────────
+
+/** One of LeetCode's topic tags. `slug` is not derivable from `name` (`Graph Theory` → `graph`). */
+interface TopicTag {
+  name: string;
+  slug: string;
+}
+
+/**
+ * The problem's topic tags, in LeetCode's order — or undefined, warned, when
+ * LeetCode cannot answer (offline commit, unknown slug): the page is written
+ * without `topics:` and the next sync fills it in.
+ */
+async function fetchTopicTags(sol: Solution): Promise<TopicTag[] | undefined> {
+  try {
+    const res = await fetch("https://leetcode.com/graphql", {
+      method: "POST",
+      headers: {
+        "content-type": "application/json",
+        "user-agent": "Mozilla/5.0",
+        referer: `https://leetcode.com/problems/${sol.slug}/`,
+      },
+      body: JSON.stringify({
+        query: "query topicTags($titleSlug: String!) { question(titleSlug: $titleSlug) { topicTags { name slug } } }",
+        variables: { titleSlug: sol.slug },
+      }),
+    });
+    if (!res.ok) throw new Error(`POST /graphql -> ${res.status} ${res.statusText}`);
+    const data = (await res.json()) as { data?: { question?: { topicTags?: TopicTag[] } | null } };
+    const tags = data.data?.question?.topicTags;
+    if (!Array.isArray(tags)) throw new Error("POST /graphql -> no such question");
+    return tags.map(({ name, slug }) => ({ name, slug }));
+  } catch (err) {
+    console.warn(`no topics for ${sol.num}.${sol.slug}: ${err instanceof Error ? err.message : err}`);
+    return undefined;
+  }
+}
+
+/** The frontmatter `topics:` block, one flow mapping per tag (JSON strings are valid YAML). */
+function topicsYaml(tags: TopicTag[]): string {
+  if (tags.length === 0) return "topics: []";
+  return ["topics:", ...tags.map((t) => `  - { name: ${JSON.stringify(t.name)}, slug: ${JSON.stringify(t.slug)} }`)].join("\n");
+}
+
+/** The frontmatter's `topics:` as sync wrote them (or a human edited them); [] when absent. */
+function frontmatterTopics(page: string): TopicTag[] {
+  const fm = page.match(/^---\n([\s\S]*?)\n---/)?.[1];
+  const data: unknown = fm ? Bun.YAML.parse(fm) : undefined;
+  if (!data || typeof data !== "object" || !("topics" in data) || !Array.isArray(data.topics)) return [];
+  return data.topics.filter((t): t is TopicTag => typeof t?.name === "string" && typeof t?.slug === "string");
+}
+
+// ── guides ───────────────────────────────────────────────────────
+
+/**
+ * Placeholder for a tag no campaign topic teaches: the `/guides/<slug>` page a
+ * problem's topic badge links to. `list:` is the tag's LeetCode problem list,
+ * rendered as a badge by the docs `PageHeader` slot. Written once — the page
+ * is hand-owned from then on.
+ */
+function guidePage(tag: TopicTag): string {
+  return [
+    "---",
+    `title: ${JSON.stringify(tag.name)}`,
+    `list: ${JSON.stringify(`https://leetcode.com/problem-list/${tag.slug}/`)}`,
+    "---",
+    "",
+    ":::note",
+    `This guide has not been written yet. The LeetCode list above has every problem tagged ${tag.name}.`,
+    ":::",
+    "",
+  ].join("\n");
+}
+
+/** Folder meta for `guides/`: its own header tab (`navigation.tabs` in blume.config.ts), so only the label. */
+const GUIDES_META = `import { defineMeta } from "blume";\n\nexport default defineMeta({ title: "Guides" });\n`;
+
 // ── inline-code formatting heuristics ────────────────────────────
 
 /** Identifiers worth backticking in prose, harvested from the code. */
@@ -420,11 +511,7 @@ function warningText(h: Header): string {
 /** Sidebar/page icon for every problem page (Lucide, resolved by Blume). */
 const PAGE_ICON = "dot";
 
-function badgeLine(sol: Solution): string {
-  return `<Badge variant="accent">${sol.category}</Badge>`;
-}
-
-function renderPage(sol: Solution): string {
+function renderPage(sol: Solution, tags: TopicTag[] | undefined): string {
   const h = sol.header;
   const ids = identifiers(sol);
   const description = h.statement[0]?.replace(/\.\s*$/, "") ?? "";
@@ -435,13 +522,12 @@ function renderPage(sol: Solution): string {
     `title: '${h.num}. ${h.title.replaceAll("'", "''")}'`,
     /[:#]/.test(description) ? `description: '${description.replaceAll("'", "''")}'` : `description: ${description}`,
     `icon: ${PAGE_ICON}`,
+    ...(tags ? [topicsYaml(tags)] : []),
     "sidebar:",
     `  label: '${h.title.replaceAll("'", "''")}'`,
     `  badge: '${h.difficulty}'`,
     "---",
     "",
-    badgeLine(sol),
-    "",
   );
 
   const warning = warningText(h);
@@ -523,10 +609,19 @@ function ensureIcon(page: string): string {
   return next + page.slice(fm[0].length);
 }
 
+/** Insert `topics:` before `sidebar:` when the frontmatter lacks it; an existing list is kept as is. */
+async function ensureTopics(page: string, sol: Solution): Promise<string> {
+  const fm = page.match(/^---\n[\s\S]*?\n---/);
+  if (!fm || /^topics:/m.test(fm[0])) return page;
+  const tags = await fetchTopicTags(sol);
+  if (!tags) return page;
+  return fm[0].replace(/^sidebar:$/m, `${topicsYaml(tags)}\nsidebar:`) + page.slice(fm[0].length);
+}
+
 /**
  * Offset just past the script-owned `## Solution` section: the next top-level
  * heading that is not inside a code fence, or end of file. Sections a human
- * appends after the solution (`## Explanation`, …) survive regeneration.
+ * appends after the solution survive regeneration.
  */
 function solutionEnd(page: string, from: number): number {
   const lines = page.slice(from).split("\n");
@@ -555,6 +650,7 @@ const groups = new Map<string, Topic>(); // topic folder -> topic, for meta.ts
 const phases = new Map<string, Phase>(); // phase folder -> phase, for meta.ts
 const vacated = new Set<string>(); // folders a page moved out of; removed below if empty
 const redirects: string[] = []; // `{ from: "/<num>", to: "/<topic>/<slug>" }` rows, numeric order
+const tags = new Map<string, TopicTag>(); // every tag slug any problem page carries -> tag
 
 for (const sol of ordered) {
   const langs = Object.keys(sol.code).sort().join("+");
@@ -579,7 +675,7 @@ for (const sol of ordered) {
     }
     const tail = page.slice(solutionEnd(page, at));
     const body = page.slice(0, at) + solutionSection(sol) + (tail ? `\n${tail}` : "");
-    const next = ensureIcon(ensureLabel(body, sol.header)).replace(/^<Badge variant="accent">.*<\/Badge>$/m, badgeLine(sol));
+    const next = await ensureTopics(ensureIcon(ensureLabel(body, sol.header)), sol);
     const actions: string[] = [];
     if (existing !== name) {
       await rename(join(DOCS, existing), join(DOCS, name));
@@ -591,9 +687,12 @@ for (const sol of ordered) {
       actions.push("updated");
     }
     report.push([workRef, name, actions.join(" + ") || "skipped (in sync)"]);
+    for (const tag of frontmatterTopics(next)) tags.set(tag.slug, tag);
   } else {
-    await Bun.write(join(DOCS, name), renderPage(sol));
+    const page = renderPage(sol, await fetchTopicTags(sol));
+    await Bun.write(join(DOCS, name), page);
     report.push([workRef, name, "created"]);
+    for (const tag of frontmatterTopics(page)) tags.set(tag.slug, tag);
   }
   // The route drops the phase `(group)` and the page's number prefix.
   redirects.push(`  { from: "/${sol.num}", to: ${JSON.stringify(`/${slugify(topic.name)}/${sol.slug}`)} },`);
@@ -615,11 +714,25 @@ for (const sol of ordered) {
   }
 }
 
-// Script-owned folder metas — one per live phase and topic folder — rewritten
-// only when they differ.
+// One guide page per tag that no campaign topic teaches, created when missing
+// (an empty file counts as missing) and never rewritten. A guide whose tag no
+// page carries any more is left alone: it is hand-owned.
+const guideTags = [...tags.values()]
+  .filter((tag) => !TOPIC_LANDINGS[tag.slug])
+  .sort((a, b) => a.slug.localeCompare(b.slug));
+for (const tag of guideTags) {
+  const file = Bun.file(join(DOCS, "guides", `${tag.slug}.mdx`));
+  if ((await file.exists()) && file.size > 0) continue;
+  await Bun.write(file, guidePage(tag));
+  report.push([`tag ${tag.slug}`, `guides/${tag.slug}.mdx`, "created"]);
+}
+
+// Script-owned folder metas — one per live phase and topic folder, plus
+// guides/ — rewritten only when they differ.
 const metas: [label: string, dir: string, meta: string][] = [
   ...[...phases].map(([dir, phase]): [string, string, string] => [`phase ${phase.order}`, dir, phaseMeta(phase)]),
   ...[...groups].map(([dir, topic]): [string, string, string] => [`topic ${topic.order ?? "-"}`, dir, groupMeta(topic)]),
+  ...(guideTags.length ? [["guides", "guides", GUIDES_META] as [string, string, string]] : []),
 ];
 for (const [label, dir, meta] of metas) {
   const path = join(DOCS, dir, "meta.ts");

apps/cli/videos.ts

@@ -2,24 +2,23 @@
 /**
  * Find the NeetCode explanation video for every docs page that has none.
  *
- * A finished solution page ends with `## Explanation` holding one
- * `<YouTube id="…" title="…" />` — NeetCode's walkthrough of the problem.
- * `sync.ts` never writes that section (it owns only `## Solution`), so pages
- * accumulate without one. This script lists every numbered page lacking a
- * `<YouTube` embed and looks each up on NeetCode's two channels, main channel
- * first, accepting only a title that names the page's exact LC number
- * (`… - Leetcode 226 - …`) and is not a #short. No YouTube API key: the
- * channel search page embeds its results as `ytInitialData` JSON, which is
- * all we parse. Ranking is the channel's own — the first exact-number match
- * wins.
+ * A finished solution page carries frontmatter `video: <YouTube id>` —
+ * NeetCode's walkthrough of the problem — which the docs `PageHeader` slot
+ * (`apps/docs/components/ProblemBadges.astro`) renders as the red
+ * "Explanation" badge beside the topic badges. `sync.ts` never writes that key
+ * (it owns `icon:`, `topics:` and `## Solution`), so pages accumulate without
+ * one. This script lists every numbered page lacking `video:` and looks each
+ * up on NeetCode's two channels, main channel first, accepting only a title
+ * that names the page's exact LC number (`… - Leetcode 226 - …`) and is not a
+ * #short. No YouTube API key: the channel search page embeds its results as
+ * `ytInitialData` JSON, which is all we parse. Ranking is the channel's own —
+ * the first exact-number match wins.
  *
  *   bun apps/cli/videos.ts           # report: page → video (or "no match")
- *   bun apps/cli/videos.ts --write   # also append `## Explanation` + embed
+ *   bun apps/cli/videos.ts --write   # also add `video:` to the frontmatter
  *
- * --write appends at end of file (below `## Solution`, where sync.ts leaves
- * human sections alone) and adds the `## Explanation` heading only when the
- * page lacks it. A page with no match is left untouched, so re-runs are
- * no-ops once every page has its embed.
+ * --write inserts the key before `sidebar:`. A page with no match is left
+ * untouched, so re-runs are no-ops once every page has its video.
  */
 import { join } from "node:path";
 
@@ -126,23 +125,21 @@ interface Page {
   text: string;
 }
 
-/** Numbered solution pages without a `<YouTube` embed, by LC number. */
+/** The page's frontmatter block, `---` to `---`. */
+const FRONTMATTER = /^---\n[\s\S]*?\n---/;
+
+/** Numbered solution pages without a `video:` key, by LC number. */
 async function pagesMissingVideo(): Promise<Page[]> {
   const pages: Page[] = [];
   for (const rel of await Array.fromAsync(new Bun.Glob("**/*.mdx").scan(DOCS))) {
     const text = await Bun.file(join(DOCS, rel)).text();
     const t = text.match(/^title: '(\d+)\./m);
-    if (t && !text.includes("<YouTube")) pages.push({ num: Number(t[1]), rel, text });
+    const fm = text.match(FRONTMATTER)?.[0] ?? "";
+    if (t && !/^video:/m.test(fm)) pages.push({ num: Number(t[1]), rel, text });
   }
   return pages.sort((a, b) => a.num - b.num);
 }
 
-function withEmbed(page: Page, video: Video): string {
-  const embed = `<YouTube id="${video.id}" title="${video.title.replaceAll('"', "'")}" />`;
-  const heading = /^## Explanation\s*$/m.test(page.text) ? "" : "## Explanation\n\n";
-  return `${page.text.replace(/\s*$/, "\n")}\n${heading}${embed}\n`;
-}
-
 // ── main ─────────────────────────────────────────────────────────
 
 const missing = await pagesMissingVideo();
@@ -162,7 +159,8 @@ for (const page of missing) {
   found++;
   let status = "";
   if (WRITE) {
-    await Bun.write(join(DOCS, page.rel), withEmbed(page, video));
+    const next = page.text.replace(FRONTMATTER, (fm) => fm.replace(/^sidebar:$/m, `video: ${JSON.stringify(video.id)}\nsidebar:`));
+    await Bun.write(join(DOCS, page.rel), next);
     status = "written";
   }
   rows.push([page.rel, `https://youtu.be/${video.id}`, `${video.title} (${video.channel})`, status]);