zic-rs 0.1.0

//! A small, dependency-free **SHA-256** (FIPS 180-4) used to fingerprint compiled TZif files
//! in the alias/canonical manifest (see `manifest`).
//!
//! Why in-house rather than the `sha2` crate: the project deliberately keeps its dependency
//! surface tiny and implements the small, well-specified primitives it needs itself (cf. the
//! in-house calendar). SHA-256 has authoritative published test vectors, so a hand-rolled
//! implementation is easy to *prove* correct — see the tests against the NIST/FIPS examples
//! (also cross-checked against the system `sha256sum`). It is plain safe Rust
//! (`#![forbid(unsafe_code)]` holds crate-wide).
//!
//! ## Scope: provenance/integrity, NOT security
//!
//! This hash is used **only** to fingerprint compiled TZif files for *deterministic artifact
//! provenance and change detection* (the alias map and compile manifest). It is **not** used
//! for — and must not be relied on for — authentication, digital signatures, message
//! authentication codes, password hashing, or any adversarial/security protocol. zic-rs does
//! not implement cryptographic security; a non-malicious build pipeline is assumed. If a
//! security-grade digest is ever needed, depend on a vetted crate rather than this module.

/// The eight SHA-256 initial hash values (FIPS 180-4 §5.3.3): fractional parts of the square
/// roots of the first eight primes.
const H0: [u32; 8] = [
    0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a, 0x510e527f, 0x9b05688c, 0x1f83d9ab, 0x5be0cd19,
];

/// The 64 round constants (FIPS 180-4 §4.2.2): fractional parts of the cube roots of the
/// first 64 primes.
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,
];

/// Compute the SHA-256 digest of `data` and return it as a lowercase hex string (64 chars).
pub fn sha256_hex(data: &[u8]) -> String {
    let digest = sha256(data);
    let mut s = String::with_capacity(64);
    for byte in digest {
        // Two lowercase hex nibbles per byte; deterministic and allocation-light.
        s.push(char::from_digit((byte >> 4) as u32, 16).unwrap());
        s.push(char::from_digit((byte & 0x0f) as u32, 16).unwrap());
    }
    s
}

/// Compute the raw 32-byte SHA-256 digest of `data`.
pub fn sha256(data: &[u8]) -> [u8; 32] {
    let mut h = H0;

    // --- Padding (FIPS 180-4 §5.1.1): append 0x80, then zeros, then the 64-bit big-endian
    //     bit length, so the total is a multiple of 64 bytes. ---
    let bit_len = (data.len() as u64).wrapping_mul(8);
    let mut msg = data.to_vec();
    msg.push(0x80);
    while msg.len() % 64 != 56 {
        msg.push(0);
    }
    msg.extend_from_slice(&bit_len.to_be_bytes());

    // --- Process each 512-bit (64-byte) block. ---
    for block in msg.chunks_exact(64) {
        // Message schedule: first 16 words are the block, big-endian; the rest are derived.
        let mut w = [0u32; 64];
        for (i, word) in block.chunks_exact(4).enumerate() {
            w[i] = u32::from_be_bytes([word[0], word[1], word[2], word[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);
        }

        // Compression function: 64 rounds over the working variables a..h.
        let [mut a, mut b, mut c, mut d, mut e, mut f, mut g, mut hh] = h;
        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 t1 = hh
                .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 t2 = s0.wrapping_add(maj);
            hh = g;
            g = f;
            f = e;
            e = d.wrapping_add(t1);
            d = c;
            c = b;
            b = a;
            a = t1.wrapping_add(t2);
        }
        for (slot, v) in h.iter_mut().zip([a, b, c, d, e, f, g, hh]) {
            *slot = slot.wrapping_add(v);
        }
    }

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

#[cfg(test)]
mod tests {
    use super::*;

    // Authoritative FIPS 180-4 / NIST CAVP vectors.
    #[test]
    fn empty_string() {
        assert_eq!(
            sha256_hex(b""),
            "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
        );
    }

    #[test]
    fn abc() {
        assert_eq!(
            sha256_hex(b"abc"),
            "ba7816bf8f01cfea414140de5dae2223b00361a396177a9cb410ff61f20015ad"
        );
    }

    #[test]
    fn two_block_message() {
        // The classic 56-byte FIPS example that spans two padded blocks.
        let msg = b"abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq";
        assert_eq!(
            sha256_hex(msg),
            "248d6a61d20638b8e5c026930c3e6039a33ce45964ff2167f6ecedd419db06c1"
        );
    }

    #[test]
    fn length_and_charset() {
        let h = sha256_hex(b"zic-rs");
        assert_eq!(h.len(), 64);
        assert!(h
            .bytes()
            .all(|b| b.is_ascii_hexdigit() && !b.is_ascii_uppercase()));
    }
}