feat: populate note files with problem descriptions and code stubs

Add populate-notes.mjs that fetches problem descriptions and Python/C++ code stubs from LeetCode's GraphQL API. Populated all 197 NeetCode 150 note files with: - Problem description (examples, constraints) - Python code stub (function signature) - C++ code stub (function signature + includes) API responses cached in leetcode/.cache/leetcode/ for instant re-runs.
2026-06-01 17:22:07 +08:00
parent e798e449bd
commit 1dec88aaf2
198 changed files with 10459 additions and 534 deletions
@@ -0,0 +1,277 @@
+#!/usr/bin/env node
+
+/**
+ * Populate DSA note files with problem descriptions and code stubs
+ * from LeetCode's GraphQL API.
+ *
+ * Usage:
+ *   node populate-notes.mjs              # populate all missing
+ *   node populate-notes.mjs --force      # overwrite existing content
+ *   node populate-notes.mjs --dry-run    # show what would change
+ */
+
+import {
+  readFileSync,
+  writeFileSync,
+  existsSync,
+  mkdirSync,
+} from "node:fs";
+import { join, dirname } from "node:path";
+import { fileURLToPath } from "node:url";
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+
+const args = process.argv.slice(2);
+const force = args.includes("--force");
+const dryRun = args.includes("--dry-run");
+
+const roadmap = JSON.parse(
+  readFileSync(join(__dirname, "out/roadmap.json"), "utf8")
+);
+const dsaDir = join(__dirname, "../org/study_deck_02/dsa");
+const cacheDir = join(__dirname, ".cache/leetcode");
+mkdirSync(cacheDir, { recursive: true });
+
+const API = "https://leetcode.com/graphql";
+const DELAY_MS = 300;
+
+const topicSlug = (name) =>
+  name
+    .toLowerCase()
+    .replace(/[^a-z0-9]+/g, "-")
+    .replace(/(^-|-$)/g, "");
+
+function sleep(ms) {
+  return new Promise((r) => setTimeout(r, ms));
+}
+
+async function fetchProblem(titleSlug) {
+  const cachePath = join(cacheDir, `${titleSlug}.json`);
+  if (existsSync(cachePath)) {
+    return JSON.parse(readFileSync(cachePath, "utf8"));
+  }
+
+  const res = await fetch(API, {
+    method: "POST",
+    headers: { "Content-Type": "application/json" },
+    body: JSON.stringify({
+      query: `query {
+        question(titleSlug: "${titleSlug}") {
+          title
+          content
+          difficulty
+          codeSnippets { lang langSlug code }
+        }
+      }`,
+    }),
+  });
+
+  if (!res.ok) {
+    console.error(`  HTTP ${res.status} for ${titleSlug}`);
+    return null;
+  }
+
+  const data = await res.json();
+  const q = data?.data?.question;
+  if (!q) {
+    console.error(`  No data for ${titleSlug}`);
+    return null;
+  }
+
+  writeFileSync(cachePath, JSON.stringify(q, null, 2), "utf8");
+  return q;
+}
+
+function htmlToOrg(html) {
+  if (!html) return "";
+
+  let text = html;
+
+  // Preserve code blocks
+  const codeBlocks = [];
+  text = text.replace(
+    /<pre>([\s\S]*?)<\/pre>/g,
+    (_, code) => {
+      const cleaned = code
+        .replace(/<[^>]+>/g, "")
+        .replace(/&lt;/g, "<")
+        .replace(/&gt;/g, ">")
+        .replace(/&amp;/g, "&")
+        .replace(/&nbsp;/g, " ")
+        .replace(/&quot;/g, '"')
+        .trim();
+      codeBlocks.push(cleaned);
+      return `__CODE_BLOCK_${codeBlocks.length - 1}__`;
+    }
+  );
+
+  // Inline code
+  text = text.replace(/<code>([\s\S]*?)<\/code>/g, "~$1~");
+
+  // Bold
+  text = text.replace(/<strong[^>]*>([\s\S]*?)<\/strong>/g, "*$1*");
+
+  // Italic
+  text = text.replace(/<em>([\s\S]*?)<\/em>/g, "/$1/");
+
+  // Line breaks and paragraphs
+  text = text.replace(/<br\s*\/?>/g, "\n");
+  text = text.replace(/<\/p>/g, "\n");
+  text = text.replace(/<p[^>]*>/g, "");
+
+  // Lists
+  text = text.replace(/<li[^>]*>/g, "- ");
+  text = text.replace(/<\/li>/g, "\n");
+  text = text.replace(/<\/?[ou]l[^>]*>/g, "");
+
+  // Sup/sub
+  text = text.replace(/<sup>([\s\S]*?)<\/sup>/g, "^{$1}");
+  text = text.replace(/<sub>([\s\S]*?)<\/sub>/g, "_{$1}");
+
+  // Example blocks — flatten to plain text
+  text = text.replace(
+    /<div class="example-block">([\s\S]*?)<\/div>/g,
+    (_, inner) => inner.replace(/<[^>]+>/g, "").trim() + "\n"
+  );
+
+  // Strip remaining HTML tags
+  text = text.replace(/<[^>]+>/g, "");
+
+  // Decode HTML entities
+  text = text.replace(/&lt;/g, "<");
+  text = text.replace(/&gt;/g, ">");
+  text = text.replace(/&amp;/g, "&");
+  text = text.replace(/&nbsp;/g, " ");
+  text = text.replace(/&quot;/g, '"');
+  text = text.replace(/&#39;/g, "'");
+
+  // Collapse whitespace but preserve intentional newlines
+  text = text.replace(/[ \t]+/g, " ");
+  text = text.replace(/\n\s*\n\s*\n+/g, "\n\n");
+  text = text.trim();
+
+  // Restore code blocks
+  for (let i = 0; i < codeBlocks.length; i++) {
+    text = text.replace(
+      `__CODE_BLOCK_${i}__`,
+      `\n#+begin_src\n${codeBlocks[i]}\n#+end_src\n`
+    );
+  }
+
+  return text;
+}
+
+function buildNoteContent(num, name, diff, description, stubs, relPath) {
+  const py = stubs.find((s) => s.langSlug === "python3");
+  const cpp = stubs.find((s) => s.langSlug === "cpp");
+
+  let out = `#+PROPERTY: STUDY_DECK_02
+* TODO ${num}. ${name} :${diff}:
+:PROPERTIES:
+:NEETCODE: [[file:${relPath}][${num}. ${name}]]
+:END:
+`;
+
+  if (description) {
+    out += `\n${description}\n`;
+  }
+
+  out += `
+** TODO Approach
+Write your approach here.
+
+** TODO Python
+#+begin_src python
+${py ? py.code.trim() : ""}
+#+end_src
+
+** TODO C++
+#+begin_src cpp
+${cpp ? cpp.code.trim() : ""}
+#+end_src
+`;
+
+  return out;
+}
+
+// ── Main ────────────────────────────────────────────────────────────────
+
+async function main() {
+  const allProblems = [];
+  for (const [topic, problems] of Object.entries(roadmap.problemsByTopic)) {
+    for (const p of problems) {
+      if (p.neetcode150) {
+        allProblems.push({ ...p, topicSlug: topicSlug(topic) });
+      }
+    }
+  }
+
+  console.log(`Processing ${allProblems.length} NeetCode 150 problems...`);
+  if (dryRun) console.log("(dry run — no files written)\n");
+
+  let populated = 0;
+  let skipped = 0;
+  let errors = 0;
+
+  for (let i = 0; i < allProblems.length; i++) {
+    const p = allProblems[i];
+    const titleSlug = p.link.replace(/\/$/, "");
+    const filePath = join(dsaDir, p.topicSlug, `${p.code}.org`);
+
+    process.stdout.write(`[${i + 1}/${allProblems.length}] ${p.code}...`);
+
+    if (!existsSync(filePath)) {
+      console.log(" SKIP (no note file)");
+      skipped++;
+      continue;
+    }
+
+    const existing = readFileSync(filePath, "utf8");
+    const hasDescription = existing.includes("** TODO Approach\nWrite your approach here.") === false ||
+                           existing.split("\n").filter(l => l.trim() && !l.startsWith("#") && !l.startsWith(":") && !l.startsWith("*") && !l.startsWith("**") && !l.startsWith("-") && !l.startsWith("Write your approach")).length > 10;
+
+    if (!force && hasDescription && !existing.includes("Write your approach here.")) {
+      console.log(" SKIP (already populated)");
+      skipped++;
+      continue;
+    }
+
+    const question = await fetchProblem(titleSlug);
+    if (!question) {
+      console.log(" ERROR");
+      errors++;
+      await sleep(DELAY_MS);
+      continue;
+    }
+
+    const description = htmlToOrg(question.content);
+    const stubs = question.codeSnippets || [];
+    const num = p.code.split("-")[0];
+    const relPath = `../../roadmap.org::*${num}. ${p.name}`;
+
+    const content = buildNoteContent(
+      num,
+      p.name,
+      p.difficulty.toLowerCase(),
+      description,
+      stubs,
+      relPath
+    );
+
+    if (!dryRun) {
+      writeFileSync(filePath, content, "utf8");
+    }
+
+    console.log(` OK (${description.length} chars)`);
+    populated++;
+
+    await sleep(DELAY_MS);
+  }
+
+  console.log(`\nDone: ${populated} populated, ${skipped} skipped, ${errors} errors`);
+}
+
+main().catch((err) => {
+  console.error(err);
+  process.exit(1);
+});