sha256.ts

/**
 * A minimal, dependency-free, synchronous SHA-256 (FIPS 180-4) implementation.
 *
 * The hashing embedder (`hashEmbedding.ts`, mirroring `providers/deterministic.py`'s
 * `HashingEmbedding`) needs a token -> 32-byte digest map that is byte-identical to
 * Python's `hashlib.sha256(tok.encode("utf-8")).digest()`. The Web Crypto API's
 * `crypto.subtle.digest` is the "real" browser API for this, but it is async — and the
 * embedder is called deep inside synchronous scoring loops (BM25 ranking, dense cosine
 * search) that mirror the Python call graph exactly. Rather than restructure the whole
 * retrieval path around `await`, this ships the ~70-line reference SHA-256 algorithm
 * directly, exactly as `text.py`/`lexical.py` are "reimplementable in ~1k lines of TS"
 * (EXP-08's own estimate). It is used only as a stable, non-cryptographic token->
 * dimension hash (the same non-cryptographic-use note `deterministic.py` makes about
 * `hashlib.sha256`), never for anything security-sensitive.
 */

const K: readonly number[] = [
  0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
  0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3, 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174,
  0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc, 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
  0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967,
  0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13, 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85,
  0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3, 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
  0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3,
  0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208, 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2,
];

const H0: readonly number[] = [
  0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a, 0x510e527f, 0x9b05688c, 0x1f83d9ab, 0x5be0cd19,
];

function rotr(x: number, n: number): number {
  return (x >>> n) | (x << (32 - n));
}

/** SHA-256 digest of `data` (UTF-8 bytes go in via `utf8Encode` before calling this). */
function sha256Bytes(message: Uint8Array): Uint8Array {
  const bitLen = message.length * 8;
  // Pad: 0x80, then zeros, then 8-byte big-endian bit length, to a multiple of 64 bytes.
  const paddedLen = Math.ceil((message.length + 9) / 64) * 64;
  const padded = new Uint8Array(paddedLen);
  padded.set(message);
  padded[message.length] = 0x80;
  // 64-bit big-endian length; bitLen fits in Number for any realistic token length.
  const view = new DataView(padded.buffer);
  view.setUint32(paddedLen - 4, bitLen >>> 0, false);
  view.setUint32(paddedLen - 8, Math.floor(bitLen / 0x100000000), false);

  const h = H0.slice();
  const w = new Int32Array(64);

  for (let chunkStart = 0; chunkStart < paddedLen; chunkStart += 64) {
    for (let i = 0; i < 16; i++) {
      w[i] = view.getUint32(chunkStart + i * 4, false);
    }
    for (let i = 16; i < 64; i++) {
      const w15 = w[i - 15] as number;
      const w2 = w[i - 2] as number;
      const s0 = rotr(w15, 7) ^ rotr(w15, 18) ^ (w15 >>> 3);
      const s1 = rotr(w2, 17) ^ rotr(w2, 19) ^ (w2 >>> 10);
      w[i] = ((w[i - 16] as number) + s0 + (w[i - 7] as number) + s1) | 0;
    }

    let [a, b, c, d, e, f, g, hh] = h as [
      number, number, number, number, number, number, number, number,
    ];

    for (let i = 0; i < 64; i++) {
      const s1 = rotr(e, 6) ^ rotr(e, 11) ^ rotr(e, 25);
      const ch = (e & f) ^ (~e & g);
      const temp1 = (hh + s1 + ch + (K[i] as number) + (w[i] as number)) | 0;
      const s0 = rotr(a, 2) ^ rotr(a, 13) ^ rotr(a, 22);
      const maj = (a & b) ^ (a & c) ^ (b & c);
      const temp2 = (s0 + maj) | 0;

      hh = g;
      g = f;
      f = e;
      e = (d + temp1) | 0;
      d = c;
      c = b;
      b = a;
      a = (temp1 + temp2) | 0;
    }

    h[0] = (h[0] as number) + a;
    h[1] = (h[1] as number) + b;
    h[2] = (h[2] as number) + c;
    h[3] = (h[3] as number) + d;
    h[4] = (h[4] as number) + e;
    h[5] = (h[5] as number) + f;
    h[6] = (h[6] as number) + g;
    h[7] = (h[7] as number) + hh;
  }

  const out = new Uint8Array(32);
  const outView = new DataView(out.buffer);
  for (let i = 0; i < 8; i++) {
    outView.setUint32(i * 4, (h[i] as number) >>> 0, false);
  }
  return out;
}

const utf8Encoder = new TextEncoder();

/** SHA-256 digest of a string's UTF-8 encoding — mirrors `hashlib.sha256(s.encode()).digest()`. */
export function sha256(text: string): Uint8Array {
  return sha256Bytes(utf8Encoder.encode(text));
}