thoughtsync/desktop/src-tauri/src/sync/blobs.rs

//! Local storage for attachment bytes (M10.7d).
//!
//! Content-addressed: a blob is filed under its own sha256, so the same image
//! attached to five notes is stored once and re-downloading it is free. The hash is
//! also the integrity check — bytes that don't hash to what the server advertised
//! are refused rather than filed under a name that lies about them.
//!
//! Attachment METADATA rides the delta feed; only the bytes come through here
//! (docs/sync.md).

use std::fs;
use std::path::{Path, PathBuf};

/// A sha256 in lowercase hex, and nothing else.
///
/// This is a **path-safety** check, not a formatting nicety: the hash is taken
/// straight from a server response and used as a filename. Without it, a hostile or
/// buggy server could send `../../…` and steer a write outside the blob directory.
fn is_hash(candidate: &str) -> bool {
    candidate.len() == 64 && candidate.bytes().all(|b| b.is_ascii_hexdigit())
}

fn digest(bytes: &[u8]) -> String {
    use sha2::{Digest, Sha256};
    let mut hasher = Sha256::new();
    hasher.update(bytes);
    hasher
        .finalize()
        .iter()
        .map(|b| format!("{b:02x}"))
        .collect()
}

pub struct BlobStore {
    root: PathBuf,
}

impl BlobStore {
    /// Open (creating if needed) the blob directory.
    pub fn new(root: PathBuf) -> std::io::Result<Self> {
        fs::create_dir_all(&root)?;
        Ok(Self { root })
    }

    pub fn root(&self) -> &Path {
        &self.root
    }

    /// Where a blob lives, or `None` if the hash isn't one.
    pub fn path(&self, sha256: &str) -> Option<PathBuf> {
        let lower = sha256.to_ascii_lowercase();
        is_hash(&lower).then(|| self.root.join(lower))
    }

    /// Whether we already hold these bytes. Drives the "don't download it twice"
    /// skip, which is the entire point of keying by content.
    pub fn has(&self, sha256: &str) -> bool {
        self.path(sha256).is_some_and(|p| p.is_file())
    }

    /// File bytes under `expected`, refusing them if they don't hash to it.
    ///
    /// Verifying on the way IN rather than on the way out means a corrupted transfer
    /// can never be served later as if it were genuine — and the next sync simply
    /// tries again, because the blob still counts as missing.
    pub fn store(&self, expected: &str, bytes: &[u8]) -> Result<PathBuf, String> {
        let path = self
            .path(expected)
            .ok_or_else(|| format!("refusing an attachment with a malformed hash: {expected}"))?;
        let actual = digest(bytes);
        if actual != expected.to_ascii_lowercase() {
            return Err(format!(
                "attachment failed its integrity check (expected {expected}, got {actual})"
            ));
        }
        fs::write(&path, bytes).map_err(|e| format!("couldn't save an attachment: {e}"))?;
        Ok(path)
    }

    pub fn read(&self, sha256: &str) -> Option<Vec<u8>> {
        fs::read(self.path(sha256)?).ok()
    }
}

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

    /// A blob store in a throwaway directory. No tempfile dependency for one test
    /// fixture — the process id keeps concurrent runs apart.
    fn store(tag: &str) -> BlobStore {
        let dir = std::env::temp_dir().join(format!("ts-blobs-{}-{tag}", std::process::id()));
        let _ = fs::remove_dir_all(&dir);
        BlobStore::new(dir).expect("store")
    }

    /// sha256("hello") — a fixed vector, so a broken digest can't agree with itself.
    const HELLO: &str = "2cf24dba5fb0a30e26e83b2ac5b9e29e1b161e5c1fa7425e73043362938b9824";

    #[test]
    fn digest_matches_a_known_vector() {
        assert_eq!(digest(b"hello"), HELLO);
    }

    #[test]
    fn stores_and_reads_back() {
        let store = store("roundtrip");
        assert!(!store.has(HELLO));
        store.store(HELLO, b"hello").expect("store");
        assert!(store.has(HELLO));
        assert_eq!(store.read(HELLO).as_deref(), Some(&b"hello"[..]));
    }

    #[test]
    fn refuses_bytes_that_dont_match_the_hash() {
        // A corrupted or substituted transfer must never be filed under a name that
        // claims it's genuine.
        let store = store("mismatch");
        let err = store.store(HELLO, b"goodbye").expect_err("must reject");
        assert!(err.contains("integrity"), "got {err}");
        assert!(!store.has(HELLO), "nothing should have been written");
    }

    #[test]
    fn rejects_a_hash_that_could_escape_the_directory() {
        // The hash arrives from a server response and becomes a filename.
        let store = store("traversal");
        assert!(store.path("../../etc/passwd").is_none());
        assert!(store.store("../../etc/passwd", b"x").is_err());
        assert!(store.path("").is_none());
        assert!(store.path("nothex!!").is_none());
    }

    #[test]
    fn accepts_an_uppercase_hash() {
        // The wire format isn't guaranteed to be lowercase; the filename is.
        let store = store("case");
        store
            .store(&HELLO.to_ascii_uppercase(), b"hello")
            .expect("store");
        assert!(store.has(HELLO), "should be found under the lowercase name");
    }

    #[test]
    fn missing_blob_reads_as_none() {
        let store = store("missing");
        assert!(store.read(HELLO).is_none());
        assert!(!store.has(HELLO));
    }
}