pakker/src/utils/hash.rs

use std::{
  fs::File,
  io::{BufReader, Read},
  path::Path,
};

use md5::{Digest as Md5Digest, Md5};
use sha1::Sha1;
use sha2::{Sha256, Sha512};

use crate::error::{PakkerError, Result};

pub fn hash_to_hex(hash: impl AsRef<[u8]>) -> String {
  use std::fmt::Write;
  let bytes = hash.as_ref();
  let mut hex = String::with_capacity(bytes.len() * 2);
  for byte in bytes {
    let _ = write!(hex, "{byte:02x}");
  }
  hex
}

/// Compute SHA1 hash of a file
pub fn compute_sha1<P: AsRef<Path>>(path: P) -> Result<String> {
  let file = File::open(path)?;
  let mut reader = BufReader::new(file);
  let mut hasher = Sha1::new();
  let mut buffer = [0; 8192];

  loop {
    let n = reader.read(&mut buffer)?;
    if n == 0 {
      break;
    }
    hasher.update(&buffer[..n]);
  }

  Ok(hash_to_hex(hasher.finalize().as_slice()))
}

/// Compute SHA256 hash of a file
pub fn compute_sha256<P: AsRef<Path>>(path: P) -> Result<String> {
  let file = File::open(path)?;
  let mut reader = BufReader::new(file);
  let mut hasher = Sha256::new();
  let mut buffer = [0; 8192];

  loop {
    let n = reader.read(&mut buffer)?;
    if n == 0 {
      break;
    }
    hasher.update(&buffer[..n]);
  }

  Ok(hash_to_hex(hasher.finalize().as_slice()))
}

/// Compute SHA256 hash of byte data
pub fn compute_sha256_bytes(data: &[u8]) -> String {
  let mut hasher = Sha256::new();
  hasher.update(data);
  hash_to_hex(hasher.finalize().as_slice())
}

/// Compute SHA512 hash of a file
pub fn compute_sha512<P: AsRef<Path>>(path: P) -> Result<String> {
  let file = File::open(path)?;
  let mut reader = BufReader::new(file);
  let mut hasher = Sha512::new();
  let mut buffer = [0; 8192];

  loop {
    let n = reader.read(&mut buffer)?;
    if n == 0 {
      break;
    }
    hasher.update(&buffer[..n]);
  }

  Ok(hash_to_hex(hasher.finalize().as_slice()))
}

/// Compute MD5 hash of a file
pub fn compute_md5<P: AsRef<Path>>(path: P) -> Result<String> {
  let file = File::open(path)?;
  let mut reader = BufReader::new(file);
  let mut hasher = Md5::new();
  let mut buffer = [0; 8192];

  loop {
    let n = reader.read(&mut buffer)?;
    if n == 0 {
      break;
    }
    hasher.update(&buffer[..n]);
  }

  let hash = hasher.finalize();
  let mut hex = String::with_capacity(hash.len() * 2);
  for byte in hash {
    let _ = std::fmt::write(&mut hex, format_args!("{byte:02x}"));
  }
  Ok(hex)
}

/// Verify a file's hash against expected value
pub fn verify_hash<P: AsRef<Path>>(
  path: P,
  algorithm: &str,
  expected: &str,
) -> Result<bool> {
  let path = path.as_ref();
  let actual = match algorithm {
    "sha1" => compute_sha1(path)?,
    "sha256" => compute_sha256(path)?,
    "sha512" => compute_sha512(path)?,
    "md5" => compute_md5(path)?,
    _ => {
      return Err(PakkerError::InternalError(format!(
        "Unknown hash algorithm: {algorithm}"
      )));
    },
  };

  Ok(actual.eq_ignore_ascii_case(expected))
}

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

  #[test]
  fn test_sha256_bytes_deterministic() {
    let data = b"test data";
    let hash1 = compute_sha256_bytes(data);
    let hash2 = compute_sha256_bytes(data);
    assert_eq!(hash1, hash2, "SHA256 must be deterministic");
  }

  #[test]
  fn test_sha256_bytes_format() {
    let data = b"hello";
    let hash = compute_sha256_bytes(data);
    assert_eq!(hash.len(), 64, "SHA256 hex should be 64 characters");
    assert!(
      hash.chars().all(|c| c.is_ascii_hexdigit()),
      "SHA256 should only contain hex digits"
    );
  }

  #[test]
  fn test_sha256_bytes_empty() {
    let hash = compute_sha256_bytes(b"");
    assert_eq!(
      hash,
      "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
    );
  }

  #[test]
  fn test_sha256_bytes_known_value() {
    // SHA256 of "hello" in hex
    let expected =
      "2cf24dba5fb0a30e26e83b2ac5b9e29e1b161e5c1fa7425e73043362938b9824";
    let hash = compute_sha256_bytes(b"hello");
    assert_eq!(hash, expected);
  }
}