leetcode/apps/cli/db.ts

/**
 * Local LeetCode problem cache backed by SQLite at
 * ~/.local/share/leetcode/data.db (XDG_DATA_HOME honored).
 *
 * One `problems` table, two freshness rules:
 *   - the full problem index (id / title / slug / difficulty / paid flag) is
 *     refreshed from leetcode.com at most once per 24h (`meta.index_fetched_at`);
 *   - descriptions (HTML from GraphQL `question.content`) are fetched once per
 *     slug and kept forever. Only the campaign problems linked from README.md
 *     are ever fetched, and paid-only problems are skipped because GraphQL
 *     returns null content for them.
 * Everything goes through /graphql: Cloudflare challenges the REST endpoints
 * (`/api/problems/all/`, `/api/submissions/`) with a 403 for any non-browser
 * client, signed in or not.
 *
 * A `solutions` table tracks the lifecycle of each work/ file by LC number:
 * `created_at` (backfilled from the file's birthtime on every picker run),
 * `last_tested` and `last_submitted` (stamped on exit 0 of leetcode-cli).
 * The test picker sorts by last_tested, the submit picker by created_at.
 * Local stamps die with the db and birthtimes with a clone, so at most once
 * per 24h (`meta.history_fetched_at`) the signed-in profile's submission
 * history is folded in: a problem's first submission caps `created_at`, its
 * latest raises `last_submitted` and `last_tested` (a submission is a judge
 * run too; LeetCode keeps no record of `leetcode test` runs). Folding only
 * ever moves a timestamp outward, so a re-run is a no-op.
 *
 * Library: side-effect-free on import — nothing is opened or fetched until
 * problemDb() is called. Index upserts never touch the description column, so
 * a daily refresh cannot evict cached statements.
 */
import { Database } from "bun:sqlite";
import { mkdirSync } from "node:fs";
import { homedir } from "node:os";
import { dirname, join } from "node:path";

export interface Problem {
  id: number;
  title: string;
  slug: string;
  difficulty: "Easy" | "Medium" | "Hard";
  paidOnly: boolean;
}

/** Lifecycle of one work/ solution, keyed by LC number. ISO timestamps. */
export interface SolutionActivity {
  createdAt: string;
  lastTested: string | null;
  lastSubmitted: string | null;
}

const DIFFICULTY = { EASY: "Easy", MEDIUM: "Medium", HARD: "Hard" } as const;
const TTL_MS = 24 * 60 * 60 * 1000;

export const DB_PATH = join(
  process.env.XDG_DATA_HOME ?? join(homedir(), ".local", "share"),
  "leetcode",
  "data.db",
);

// ── README parsing ───────────────────────────────────────────────

/** Campaign problem slugs linked from README.md, in order, deduplicated. */
export function readmeSlugs(markdown: string): string[] {
  const slugs = new Set<string>();
  for (const m of markdown.matchAll(/https:\/\/leetcode\.com\/problems\/([\w-]+)\//g)) {
    slugs.add(m[1]!);
  }
  return [...slugs];
}

// ── remote fetches ───────────────────────────────────────────────

/** leetcode-cli's login: the two cookies every signed-in request carries. */
export interface Credentials {
  session: string;
  csrfToken: string;
}

/**
 * POST one query to leetcode.com/graphql. Throws on an HTTP error or a
 * response with no `data`; partial `errors` beside data are the caller's.
 */
async function graphql<T>(
  query: string,
  variables: Record<string, unknown>,
  { referer = "https://leetcode.com/", auth }: { referer?: string; auth?: Credentials } = {},
): Promise<T> {
  const res = await fetch("https://leetcode.com/graphql", {
    method: "POST",
    headers: {
      "content-type": "application/json",
      "user-agent": "Mozilla/5.0",
      referer,
      ...(auth && {
        cookie: `LEETCODE_SESSION=${auth.session}; csrftoken=${auth.csrfToken}`,
        "x-csrftoken": auth.csrfToken,
      }),
    },
    body: JSON.stringify({ query, variables }),
  });
  if (!res.ok) throw new Error(`POST /graphql -> ${res.status} ${res.statusText}`);
  const body = (await res.json()) as { data?: T | null; errors?: { message: string }[] };
  if (!body.data) {
    throw new Error(`POST /graphql: ${body.errors?.map((e) => e.message).join("; ") || "no data"}`);
  }
  return body.data;
}

/** Server-side cap on `limit` for the problem list. */
const INDEX_PAGE = 100;

async function fetchIndex(): Promise<Problem[]> {
  type Page = {
    problemsetQuestionListV2: {
      totalLength: number;
      questions: Array<{
        questionFrontendId: string;
        title: string;
        titleSlug: string;
        difficulty: keyof typeof DIFFICULTY;
        paidOnly: boolean;
      }>;
    };
  };
  const page = async (skip: number) =>
    (
      await graphql<Page>(
        `query problemIndex($skip: Int!, $limit: Int!) {
          problemsetQuestionListV2(skip: $skip, limit: $limit) {
            totalLength
            questions { questionFrontendId title titleSlug difficulty paidOnly }
          }
        }`,
        { skip, limit: INDEX_PAGE },
        { referer: "https://leetcode.com/problemset/" },
      )
    ).problemsetQuestionListV2;

  // The first page names the total; the rest go six at a time.
  const first = await page(0);
  const questions = [...first.questions];
  const skips = Array.from({ length: Math.ceil(first.totalLength / INDEX_PAGE) - 1 }, (_, i) => (i + 1) * INDEX_PAGE);
  await Promise.all(
    Array.from({ length: 6 }, async () => {
      for (let skip = skips.shift(); skip !== undefined; skip = skips.shift()) {
        questions.push(...(await page(skip)).questions);
      }
    }),
  );
  if (questions.length < first.totalLength) {
    throw new Error(`problem index came back short: ${questions.length} of ${first.totalLength}`);
  }

  return questions
    .map((q) => ({
      id: Number(q.questionFrontendId),
      title: q.title,
      slug: q.titleSlug,
      difficulty: DIFFICULTY[q.difficulty],
      paidOnly: q.paidOnly,
    }))
    .filter((p) => Number.isInteger(p.id))
    .sort((a, b) => a.id - b.id);
}

/** HTML problem statement, or null when LeetCode withholds it (paid-only). */
export async function fetchDescription(slug: string): Promise<string | null> {
  const data = await graphql<{ question?: { content?: string | null } | null }>(
    "query questionContent($titleSlug: String!) { question(titleSlug: $titleSlug) { content } }",
    { titleSlug: slug },
    { referer: `https://leetcode.com/problems/${slug}/` },
  );
  return data.question?.content ?? null;
}

/**
 * The login leetcode-cli holds, read from where it keeps it: its own
 * LEETCODE_SESSION + LEETCODE_CSRF_TOKEN override, else the OS keychain entry
 * `leetcode login` writes through keytar (service `leetcode-cli`, account
 * `auth`). Null when signed out, or when the login lives in leetcode-cli's
 * encrypted-file fallback, whose key is the CLI's own.
 */
export function leetcodeCredentials(): Credentials | null {
  const { LEETCODE_SESSION: session, LEETCODE_CSRF_TOKEN: csrfToken } = process.env;
  if (session && csrfToken) return { session, csrfToken };

  const lookup =
    process.platform === "darwin"
      ? ["security", "find-generic-password", "-s", "leetcode-cli", "-a", "auth", "-w"]
      : ["secret-tool", "lookup", "service", "leetcode-cli", "account", "auth"];
  let stored: string;
  try {
    const out = Bun.spawnSync(lookup, { stderr: "ignore" });
    if (!out.success) return null;
    stored = out.stdout.toString();
  } catch {
    return null; // no keychain CLI on this machine
  }
  let parsed: unknown;
  try {
    parsed = JSON.parse(stored);
  } catch {
    return null;
  }
  if (
    !parsed ||
    typeof parsed !== "object" ||
    !("session" in parsed) ||
    typeof parsed.session !== "string" ||
    !("csrfToken" in parsed) ||
    typeof parsed.csrfToken !== "string"
  ) {
    return null;
  }
  return { session: parsed.session, csrfToken: parsed.csrfToken };
}

/** One submission of the signed-in profile, any verdict. */
export interface Submission {
  slug: string;
  /** ISO timestamp. */
  at: string;
}

/** Server-side cap on `limit` for the submission list. */
const SUBMISSION_PAGE = 20;

/** The signed-in profile's whole submission history, newest first. */
export async function fetchSubmissions(auth: Credentials): Promise<Submission[]> {
  type Page = {
    submissionList: { hasNext: boolean; submissions: Array<{ titleSlug: string; timestamp: string }> } | null;
  };
  const all: Submission[] = [];
  for (let offset = 0; ; offset += SUBMISSION_PAGE) {
    const { submissionList } = await graphql<Page>(
      `query submissionList($offset: Int!, $limit: Int!) {
        submissionList(offset: $offset, limit: $limit) {
          hasNext
          submissions { titleSlug timestamp }
        }
      }`,
      { offset, limit: SUBMISSION_PAGE },
      { referer: "https://leetcode.com/submissions/", auth },
    );
    // An expired session is answered with a null list, not an HTTP error.
    if (!submissionList) throw new Error("submission history unavailable — session expired? run `leetcode login`");
    for (const s of submissionList.submissions) {
      all.push({ slug: s.titleSlug, at: new Date(Number(s.timestamp) * 1000).toISOString() });
    }
    if (!submissionList.hasNext) return all;
  }
}

// ── the cache ────────────────────────────────────────────────────

export function problemDb(path = DB_PATH) {
  mkdirSync(dirname(path), { recursive: true });
  const db = new Database(path);
  db.exec(`
    CREATE TABLE IF NOT EXISTS problems (
      id          INTEGER PRIMARY KEY,
      title       TEXT NOT NULL,
      slug        TEXT NOT NULL UNIQUE,
      difficulty  TEXT NOT NULL,
      paid_only   INTEGER NOT NULL,
      description TEXT
    );
    CREATE TABLE IF NOT EXISTS solutions (
      id             INTEGER PRIMARY KEY,
      created_at     TEXT NOT NULL,
      last_tested    TEXT,
      last_submitted TEXT
    );
    DROP TABLE IF EXISTS submissions;
    CREATE TABLE IF NOT EXISTS meta (
      key   TEXT PRIMARY KEY,
      value TEXT NOT NULL
    );
  `);

  const getMeta = db.query<{ value: string }, [string]>("SELECT value FROM meta WHERE key = ?1");
  const setMeta = db.query<never, [string, string]>(
    "INSERT INTO meta (key, value) VALUES (?1, ?2) ON CONFLICT(key) DO UPDATE SET value = excluded.value",
  );
  const upsert = db.query<never, [number, string, string, string, number]>(
    `INSERT INTO problems (id, title, slug, difficulty, paid_only)
     VALUES (?1, ?2, ?3, ?4, ?5)
     ON CONFLICT(id) DO UPDATE SET
       title = excluded.title, slug = excluded.slug,
       difficulty = excluded.difficulty, paid_only = excluded.paid_only`,
  );
  const descState = db.query<{ paid_only: number; described: number }, [string]>(
    "SELECT paid_only, description IS NOT NULL AS described FROM problems WHERE slug = ?1",
  );
  // MIN/MAX on TEXT compare ISO timestamps chronologically; COALESCE because
  // SQLite's scalar MAX returns NULL when any argument is NULL.
  const fold = db.query<never, [number, string, string]>(
    `UPDATE solutions SET
       created_at     = MIN(created_at, ?2),
       last_tested    = MAX(COALESCE(last_tested, ''), ?3),
       last_submitted = MAX(COALESCE(last_submitted, ''), ?3)
     WHERE id = ?1`,
  );

  /** True when `key` has never been stamped or was stamped over 24h ago. */
  const stale = (key: string) => {
    const row = getMeta.get(key);
    return !row || Date.now() - Number(row.value) > TTL_MS;
  };

  return {
    path,

    /** True when the index has never been fetched or is older than 24h. */
    indexStale(): boolean {
      return stale("index_fetched_at");
    },

    /** Pull the full index from leetcode.com and upsert it. Returns the count. */
    async refreshIndex(): Promise<number> {
      const problems = await fetchIndex();
      db.transaction(() => {
        for (const p of problems) upsert.run(p.id, p.title, p.slug, p.difficulty, p.paidOnly ? 1 : 0);
        setMeta.run("index_fetched_at", String(Date.now()));
      })();
      return problems.length;
    },

    /** Every cached problem, ordered by LC number. */
    all(): Problem[] {
      const rows = db
        .query<{ id: number; title: string; slug: string; difficulty: string; paid_only: number }, []>(
          "SELECT id, title, slug, difficulty, paid_only FROM problems ORDER BY id",
        )
        .all();
      return rows.map((r) => ({
        id: r.id,
        title: r.title,
        slug: r.slug,
        difficulty: r.difficulty as Problem["difficulty"],
        paidOnly: r.paid_only === 1,
      }));
    },

    /** Free (non-premium) slugs among `slugs` with no cached description yet. */
    missingDescriptions(slugs: string[]): string[] {
      return slugs.filter((slug) => {
        const row = descState.get(slug);
        return row !== null && !row.paid_only && !row.described;
      });
    },

    saveDescription(slug: string, html: string): void {
      db.query("UPDATE problems SET description = ?2 WHERE slug = ?1").run(slug, html);
    },

    /** Per-solution lifecycle rows keyed by LC number. */
    solutionActivity(): Map<number, SolutionActivity> {
      const rows = db
        .query<{ id: number; created_at: string; last_tested: string | null; last_submitted: string | null }, []>(
          "SELECT id, created_at, last_tested, last_submitted FROM solutions",
        )
        .all();
      return new Map(
        rows.map((r) => [r.id, { createdAt: r.created_at, lastTested: r.last_tested, lastSubmitted: r.last_submitted }]),
      );
    },

    /** Register a solution's creation time; existing rows are left alone. */
    ensureSolution(id: number, createdAt: string): void {
      db.query("INSERT INTO solutions (id, created_at) VALUES (?1, ?2) ON CONFLICT(id) DO NOTHING").run(id, createdAt);
    },

    markTested(id: number): void {
      db.query(
        `INSERT INTO solutions (id, created_at, last_tested) VALUES (?1, ?2, ?2)
         ON CONFLICT(id) DO UPDATE SET last_tested = excluded.last_tested`,
      ).run(id, new Date().toISOString());
    },

    markSubmitted(id: number): void {
      db.query(
        `INSERT INTO solutions (id, created_at, last_submitted) VALUES (?1, ?2, ?2)
         ON CONFLICT(id) DO UPDATE SET last_submitted = excluded.last_submitted`,
      ).run(id, new Date().toISOString());
    },

    /** True when submission history has never been folded in or over 24h ago. */
    historyStale(): boolean {
      return stale("history_fetched_at");
    },

    /**
     * Fold the profile's submissions (LC number → first and latest submission,
     * ISO) into existing solution rows and stamp the refresh. Rows are never
     * created here — the table holds work/ files only — and a timestamp only
     * ever moves outward, so folding twice changes nothing. Returns the number
     * of solutions that have submissions.
     */
    foldHistory(history: Map<number, { first: string; last: string }>): number {
      let matched = 0;
      db.transaction(() => {
        for (const [id, { first, last }] of history) matched += fold.run(id, first, last).changes;
        setMeta.run("history_fetched_at", String(Date.now()));
      })();
      return matched;
    },

    close(): void {
      db.close();
    },
  };
}