gigastt-core 2.17.0

//! In-tree SHA-256 (FIPS 180-4) and lowercase hex encoding.
//!
//! Replaces `sha2` + `hex` (8 transitive packages) for the only thing gigastt
//! hashes: model files, verified against pinned digests before an atomic
//! rename. Correctness is pinned by the NIST CAVP vectors in the tests below —
//! do not relax them.

const K: [u32; 64] = [
    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: [u32; 8] = [
    0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a, 0x510e527f, 0x9b05688c, 0x1f83d9ab, 0x5be0cd19,
];

/// Streaming SHA-256 hasher. Feed with [`Sha256::update`], close with
/// [`Sha256::finalize`].
pub(crate) struct Sha256 {
    state: [u32; 8],
    buf: [u8; 64],
    buf_len: usize,
    total_bytes: u64,
}

impl Sha256 {
    pub(crate) fn new() -> Self {
        Self {
            state: H0,
            buf: [0u8; 64],
            buf_len: 0,
            total_bytes: 0,
        }
    }

    pub(crate) fn update(&mut self, data: &[u8]) {
        self.total_bytes = self.total_bytes.wrapping_add(data.len() as u64);
        let mut rest = data;

        // Top up a partially filled block first.
        if self.buf_len > 0 {
            let need = 64 - self.buf_len;
            let take = need.min(rest.len());
            self.buf[self.buf_len..self.buf_len + take].copy_from_slice(&rest[..take]);
            self.buf_len += take;
            rest = &rest[take..];
            if self.buf_len == 64 {
                let block = self.buf;
                self.compress(&block);
                self.buf_len = 0;
            }
        }

        // Whole blocks straight from the input.
        while rest.len() >= 64 {
            let mut block = [0u8; 64];
            block.copy_from_slice(&rest[..64]);
            self.compress(&block);
            rest = &rest[64..];
        }

        // Keep the tail for next time.
        if !rest.is_empty() {
            self.buf[..rest.len()].copy_from_slice(rest);
            self.buf_len = rest.len();
        }
    }

    pub(crate) fn finalize(mut self) -> [u8; 32] {
        // Captured before padding: the length field counts message bytes only.
        let bit_len = self.total_bytes.wrapping_mul(8);

        self.update(&[0x80]);
        while self.buf_len != 56 {
            self.update(&[0x00]);
        }
        let mut block = self.buf;
        block[56..64].copy_from_slice(&bit_len.to_be_bytes());
        self.compress(&block);

        let mut out = [0u8; 32];
        for (i, word) in self.state.iter().enumerate() {
            out[i * 4..i * 4 + 4].copy_from_slice(&word.to_be_bytes());
        }
        out
    }

    fn compress(&mut self, block: &[u8; 64]) {
        let mut w = [0u32; 64];
        for i in 0..16 {
            w[i] = u32::from_be_bytes([
                block[i * 4],
                block[i * 4 + 1],
                block[i * 4 + 2],
                block[i * 4 + 3],
            ]);
        }
        for i in 16..64 {
            let s0 = w[i - 15].rotate_right(7) ^ w[i - 15].rotate_right(18) ^ (w[i - 15] >> 3);
            let s1 = w[i - 2].rotate_right(17) ^ w[i - 2].rotate_right(19) ^ (w[i - 2] >> 10);
            w[i] = w[i - 16]
                .wrapping_add(s0)
                .wrapping_add(w[i - 7])
                .wrapping_add(s1);
        }

        let [mut a, mut b, mut c, mut d, mut e, mut f, mut g, mut h] = self.state;

        for i in 0..64 {
            let s1 = e.rotate_right(6) ^ e.rotate_right(11) ^ e.rotate_right(25);
            let ch = (e & f) ^ ((!e) & g);
            let temp1 = h
                .wrapping_add(s1)
                .wrapping_add(ch)
                .wrapping_add(K[i])
                .wrapping_add(w[i]);
            let s0 = a.rotate_right(2) ^ a.rotate_right(13) ^ a.rotate_right(22);
            let maj = (a & b) ^ (a & c) ^ (b & c);
            let temp2 = s0.wrapping_add(maj);

            h = g;
            g = f;
            f = e;
            e = d.wrapping_add(temp1);
            d = c;
            c = b;
            b = a;
            a = temp1.wrapping_add(temp2);
        }

        for (slot, v) in self.state.iter_mut().zip([a, b, c, d, e, f, g, h]) {
            *slot = slot.wrapping_add(v);
        }
    }
}

/// Lowercase hex encoding of a byte slice.
pub(crate) fn hex_lower(bytes: &[u8]) -> String {
    const DIGITS: &[u8; 16] = b"0123456789abcdef";
    let mut s = String::with_capacity(bytes.len() * 2);
    for &b in bytes {
        s.push(DIGITS[(b >> 4) as usize] as char);
        s.push(DIGITS[(b & 0x0f) as usize] as char);
    }
    s
}

#[cfg(test)]
mod tests {
    use super::{Sha256, hex_lower};

    fn digest(data: &[u8]) -> String {
        let mut h = Sha256::new();
        h.update(data);
        hex_lower(&h.finalize())
    }

    /// FIPS 180-4 / NIST CAVP vectors.
    #[test]
    fn test_sha256_matches_nist_vectors() {
        assert_eq!(
            digest(b""),
            "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        );
        assert_eq!(
            digest(b"abc"),
            "ba7816bf8f01cfea414140de5dae2223b00361a396177a9cb410ff61f20015ad"
        );
        assert_eq!(
            digest(b"abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq"),
            "248d6a61d20638b8e5c026930c3e6039a33ce45964ff2167f6ecedd419db06c1"
        );
    }

    /// One million 'a' — exercises multi-block streaming and the length field.
    #[test]
    fn test_sha256_million_a() {
        let mut h = Sha256::new();
        let chunk = vec![b'a'; 1000];
        for _ in 0..1000 {
            h.update(&chunk);
        }
        assert_eq!(
            hex_lower(&h.finalize()),
            "cdc76e5c9914fb9281a1c7e284d73e67f1809a48a497200e046d39ccc7112cd0"
        );
    }

    /// Feeding the same bytes in ragged pieces must not change the digest:
    /// the internal 64-byte block buffer has to stitch them correctly.
    #[test]
    fn test_sha256_chunking_is_transparent() {
        let data: Vec<u8> = (0..1000u32).map(|i| (i % 251) as u8).collect();
        let mut whole = Sha256::new();
        whole.update(&data);
        let expected = hex_lower(&whole.finalize());

        for step in [1usize, 3, 7, 63, 64, 65, 127] {
            let mut h = Sha256::new();
            for piece in data.chunks(step) {
                h.update(piece);
            }
            assert_eq!(hex_lower(&h.finalize()), expected, "step {step}");
        }
    }

    #[test]
    fn test_hex_lower_pads_single_digit_bytes() {
        assert_eq!(hex_lower(&[0x00, 0x0f, 0xff]), "000fff");
    }
}