Add Rust extension module (myfsio_core) for SigV4, hashing, and validation hot paths

myfsio_core/src/hashing.rs

@@ -0,0 +1,90 @@
+use md5::{Digest, Md5};
+use pyo3::exceptions::PyIOError;
+use pyo3::prelude::*;
+use sha2::Sha256;
+use std::fs::File;
+use std::io::Read;
+
+const CHUNK_SIZE: usize = 65536;
+
+#[pyfunction]
+pub fn md5_file(py: Python<'_>, path: &str) -> PyResult<String> {
+    let path = path.to_owned();
+    py.detach(move || {
+        let mut file = File::open(&path)
+            .map_err(|e| PyIOError::new_err(format!("Failed to open file: {}", e)))?;
+        let mut hasher = Md5::new();
+        let mut buf = vec![0u8; CHUNK_SIZE];
+        loop {
+            let n = file
+                .read(&mut buf)
+                .map_err(|e| PyIOError::new_err(format!("Failed to read file: {}", e)))?;
+            if n == 0 {
+                break;
+            }
+            hasher.update(&buf[..n]);
+        }
+        Ok(format!("{:x}", hasher.finalize()))
+    })
+}
+
+#[pyfunction]
+pub fn md5_bytes(data: &[u8]) -> String {
+    let mut hasher = Md5::new();
+    hasher.update(data);
+    format!("{:x}", hasher.finalize())
+}
+
+#[pyfunction]
+pub fn sha256_file(py: Python<'_>, path: &str) -> PyResult<String> {
+    let path = path.to_owned();
+    py.detach(move || {
+        let mut file = File::open(&path)
+            .map_err(|e| PyIOError::new_err(format!("Failed to open file: {}", e)))?;
+        let mut hasher = Sha256::new();
+        let mut buf = vec![0u8; CHUNK_SIZE];
+        loop {
+            let n = file
+                .read(&mut buf)
+                .map_err(|e| PyIOError::new_err(format!("Failed to read file: {}", e)))?;
+            if n == 0 {
+                break;
+            }
+            hasher.update(&buf[..n]);
+        }
+        Ok(format!("{:x}", hasher.finalize()))
+    })
+}
+
+#[pyfunction]
+pub fn sha256_bytes(data: &[u8]) -> String {
+    let mut hasher = Sha256::new();
+    hasher.update(data);
+    format!("{:x}", hasher.finalize())
+}
+
+#[pyfunction]
+pub fn md5_sha256_file(py: Python<'_>, path: &str) -> PyResult<(String, String)> {
+    let path = path.to_owned();
+    py.detach(move || {
+        let mut file = File::open(&path)
+            .map_err(|e| PyIOError::new_err(format!("Failed to open file: {}", e)))?;
+        let mut md5_hasher = Md5::new();
+        let mut sha_hasher = Sha256::new();
+        let mut buf = vec![0u8; CHUNK_SIZE];
+        loop {
+            let n = file
+                .read(&mut buf)
+                .map_err(|e| PyIOError::new_err(format!("Failed to read file: {}", e)))?;
+            if n == 0 {
+                break;
+            }
+            md5_hasher.update(&buf[..n]);
+            sha_hasher.update(&buf[..n]);
+        }
+        Ok((
+            format!("{:x}", md5_hasher.finalize()),
+            format!("{:x}", sha_hasher.finalize()),
+        ))
+    })
+}

myfsio_core/src/lib.rs

@@ -0,0 +1,30 @@
+mod hashing;
+mod sigv4;
+mod validation;
+
+use pyo3::prelude::*;
+
+#[pymodule]
+mod myfsio_core {
+    use super::*;
+
+    #[pymodule_init]
+    fn init(m: &Bound<'_, PyModule>) -> PyResult<()> {
+        m.add_function(wrap_pyfunction!(sigv4::derive_signing_key, m)?)?;
+        m.add_function(wrap_pyfunction!(sigv4::compute_signature, m)?)?;
+        m.add_function(wrap_pyfunction!(sigv4::build_string_to_sign, m)?)?;
+        m.add_function(wrap_pyfunction!(sigv4::constant_time_compare, m)?)?;
+        m.add_function(wrap_pyfunction!(sigv4::clear_signing_key_cache, m)?)?;
+
+        m.add_function(wrap_pyfunction!(hashing::md5_file, m)?)?;
+        m.add_function(wrap_pyfunction!(hashing::md5_bytes, m)?)?;
+        m.add_function(wrap_pyfunction!(hashing::sha256_file, m)?)?;
+        m.add_function(wrap_pyfunction!(hashing::sha256_bytes, m)?)?;
+        m.add_function(wrap_pyfunction!(hashing::md5_sha256_file, m)?)?;
+
+        m.add_function(wrap_pyfunction!(validation::validate_object_key, m)?)?;
+        m.add_function(wrap_pyfunction!(validation::validate_bucket_name, m)?)?;
+
+        Ok(())
+    }
+}

myfsio_core/src/sigv4.rs

@@ -0,0 +1,108 @@
+use hmac::{Hmac, Mac};
+use lru::LruCache;
+use parking_lot::Mutex;
+use pyo3::prelude::*;
+use sha2::{Digest, Sha256};
+use std::num::NonZeroUsize;
+use std::sync::LazyLock;
+use std::time::Instant;
+
+type HmacSha256 = Hmac<Sha256>;
+
+struct CacheEntry {
+    key: Vec<u8>,
+    created: Instant,
+}
+
+static SIGNING_KEY_CACHE: LazyLock<Mutex<LruCache<(String, String, String, String), CacheEntry>>> =
+    LazyLock::new(|| Mutex::new(LruCache::new(NonZeroUsize::new(256).unwrap())));
+
+const CACHE_TTL_SECS: u64 = 60;
+
+fn hmac_sha256(key: &[u8], msg: &[u8]) -> Vec<u8> {
+    let mut mac = HmacSha256::new_from_slice(key).expect("HMAC key length is always valid");
+    mac.update(msg);
+    mac.finalize().into_bytes().to_vec()
+}
+
+#[pyfunction]
+pub fn derive_signing_key(
+    secret_key: &str,
+    date_stamp: &str,
+    region: &str,
+    service: &str,
+) -> Vec<u8> {
+    let cache_key = (
+        secret_key.to_owned(),
+        date_stamp.to_owned(),
+        region.to_owned(),
+        service.to_owned(),
+    );
+
+    {
+        let mut cache = SIGNING_KEY_CACHE.lock();
+        if let Some(entry) = cache.get(&cache_key) {
+            if entry.created.elapsed().as_secs() < CACHE_TTL_SECS {
+                return entry.key.clone();
+            }
+            cache.pop(&cache_key);
+        }
+    }
+
+    let k_date = hmac_sha256(format!("AWS4{}", secret_key).as_bytes(), date_stamp.as_bytes());
+    let k_region = hmac_sha256(&k_date, region.as_bytes());
+    let k_service = hmac_sha256(&k_region, service.as_bytes());
+    let k_signing = hmac_sha256(&k_service, b"aws4_request");
+
+    {
+        let mut cache = SIGNING_KEY_CACHE.lock();
+        cache.put(
+            cache_key,
+            CacheEntry {
+                key: k_signing.clone(),
+                created: Instant::now(),
+            },
+        );
+    }
+
+    k_signing
+}
+
+#[pyfunction]
+pub fn compute_signature(signing_key: &[u8], string_to_sign: &str) -> String {
+    let sig = hmac_sha256(signing_key, string_to_sign.as_bytes());
+    hex::encode(sig)
+}
+
+fn sha256_hex(data: &[u8]) -> String {
+    let mut hasher = Sha256::new();
+    hasher.update(data);
+    hex::encode(hasher.finalize())
+}
+
+#[pyfunction]
+pub fn build_string_to_sign(
+    amz_date: &str,
+    credential_scope: &str,
+    canonical_request: &str,
+) -> String {
+    let cr_hash = sha256_hex(canonical_request.as_bytes());
+    format!("AWS4-HMAC-SHA256\n{}\n{}\n{}", amz_date, credential_scope, cr_hash)
+}
+
+#[pyfunction]
+pub fn constant_time_compare(a: &str, b: &str) -> bool {
+    if a.len() != b.len() {
+        return false;
+    }
+    let mut result: u8 = 0;
+    for (x, y) in a.bytes().zip(b.bytes()) {
+        result |= x ^ y;
+    }
+    result == 0
+}
+
+#[pyfunction]
+pub fn clear_signing_key_cache() {
+    SIGNING_KEY_CACHE.lock().clear();
+}

myfsio_core/src/validation.rs

@@ -0,0 +1,149 @@
+use pyo3::prelude::*;
+use std::sync::LazyLock;
+use unicode_normalization::UnicodeNormalization;
+
+const WINDOWS_RESERVED: &[&str] = &[
+    "CON", "PRN", "AUX", "NUL", "COM0", "COM1", "COM2", "COM3", "COM4", "COM5", "COM6", "COM7",
+    "COM8", "COM9", "LPT0", "LPT1", "LPT2", "LPT3", "LPT4", "LPT5", "LPT6", "LPT7", "LPT8",
+    "LPT9",
+];
+
+const WINDOWS_ILLEGAL_CHARS: &[char] = &['<', '>', ':', '"', '/', '\\', '|', '?', '*'];
+
+const INTERNAL_FOLDERS: &[&str] = &[".meta", ".versions", ".multipart"];
+const SYSTEM_ROOT: &str = ".myfsio.sys";
+
+static IP_REGEX: LazyLock<regex::Regex> =
+    LazyLock::new(|| regex::Regex::new(r"^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$").unwrap());
+
+#[pyfunction]
+#[pyo3(signature = (object_key, max_length_bytes=1024, is_windows=false, reserved_prefixes=None))]
+pub fn validate_object_key(
+    object_key: &str,
+    max_length_bytes: usize,
+    is_windows: bool,
+    reserved_prefixes: Option<Vec<String>>,
+) -> PyResult<Option<String>> {
+    if object_key.is_empty() {
+        return Ok(Some("Object key required".to_string()));
+    }
+
+    if object_key.contains('\0') {
+        return Ok(Some("Object key contains null bytes".to_string()));
+    }
+
+    let normalized: String = object_key.nfc().collect();
+
+    if normalized.len() > max_length_bytes {
+        return Ok(Some(format!(
+            "Object key exceeds maximum length of {} bytes",
+            max_length_bytes
+        )));
+    }
+
+    if normalized.starts_with('/') || normalized.starts_with('\\') {
+        return Ok(Some("Object key cannot start with a slash".to_string()));
+    }
+
+    let parts: Vec<&str> = if cfg!(windows) || is_windows {
+        normalized.split(['/', '\\']).collect()
+    } else {
+        normalized.split('/').collect()
+    };
+
+    for part in &parts {
+        if part.is_empty() {
+            continue;
+        }
+
+        if *part == ".." {
+            return Ok(Some(
+                "Object key contains parent directory references".to_string(),
+            ));
+        }
+
+        if *part == "." {
+            return Ok(Some("Object key contains invalid segments".to_string()));
+        }
+
+        if part.chars().any(|c| (c as u32) < 32) {
+            return Ok(Some(
+                "Object key contains control characters".to_string(),
+            ));
+        }
+
+        if is_windows {
+            if part.chars().any(|c| WINDOWS_ILLEGAL_CHARS.contains(&c)) {
+                return Ok(Some(
+                    "Object key contains characters not supported on Windows filesystems"
+                        .to_string(),
+                ));
+            }
+            if part.ends_with(' ') || part.ends_with('.') {
+                return Ok(Some(
+                    "Object key segments cannot end with spaces or periods on Windows".to_string(),
+                ));
+            }
+            let trimmed = part.trim_end_matches(['.', ' ']).to_uppercase();
+            if WINDOWS_RESERVED.contains(&trimmed.as_str()) {
+                return Ok(Some(format!("Invalid filename segment: {}", part)));
+            }
+        }
+    }
+
+    let non_empty_parts: Vec<&str> = parts.iter().filter(|p| !p.is_empty()).copied().collect();
+    if let Some(top) = non_empty_parts.first() {
+        if INTERNAL_FOLDERS.contains(top) || *top == SYSTEM_ROOT {
+            return Ok(Some("Object key uses a reserved prefix".to_string()));
+        }
+
+        if let Some(ref prefixes) = reserved_prefixes {
+            for prefix in prefixes {
+                if *top == prefix.as_str() {
+                    return Ok(Some("Object key uses a reserved prefix".to_string()));
+                }
+            }
+        }
+    }
+
+    Ok(None)
+}
+
+#[pyfunction]
+pub fn validate_bucket_name(bucket_name: &str) -> Option<String> {
+    let len = bucket_name.len();
+    if len < 3 || len > 63 {
+        return Some("Bucket name must be between 3 and 63 characters".to_string());
+    }
+
+    let bytes = bucket_name.as_bytes();
+    if !bytes[0].is_ascii_lowercase() && !bytes[0].is_ascii_digit() {
+        return Some(
+            "Bucket name must start and end with a lowercase letter or digit".to_string(),
+        );
+    }
+    if !bytes[len - 1].is_ascii_lowercase() && !bytes[len - 1].is_ascii_digit() {
+        return Some(
+            "Bucket name must start and end with a lowercase letter or digit".to_string(),
+        );
+    }
+
+    for &b in bytes {
+        if !b.is_ascii_lowercase() && !b.is_ascii_digit() && b != b'.' && b != b'-' {
+            return Some(
+                "Bucket name can only contain lowercase letters, digits, dots, and hyphens"
+                    .to_string(),
+            );
+        }
+    }
+
+    if bucket_name.contains("..") {
+        return Some("Bucket name must not contain consecutive periods".to_string());
+    }
+
+    if IP_REGEX.is_match(bucket_name) {
+        return Some("Bucket name must not be formatted as an IP address".to_string());
+    }
+
+    None
+}