//! Object store (spec §13.1, §13.3, §13.4): loose objects, one file per //! object under `objects/loose//`, and packs, `pack-.pack` //! with a sorted `pack-.idx`, holding zstd-compressed objects. Reads //! check loose objects first, then every pack; every read re-hashes. //! //! Pack file: `OXYPACK1` then entries of //! `type u8 | flags u8 (bit 0: zstd) | stored_len u32 | raw_len u32 | ref 32 | body`. //! Index file: `OXYIDX01` then `count u32` then sorted entries of //! `ref 32 | offset u64 | stored_len u32 | raw_len u32 | type u8 | flags u8`. use crate::attest::Attest; use crate::hash::{hash_object, header, ObjectRef, ObjectType}; use crate::identity::{Identity, Signature}; use crate::objects::{Change, ObjectError, StateObject}; use rand::RngCore; use std::cell::RefCell; use std::fs; use std::io::{self, Read, Seek, SeekFrom, Write}; use std::path::{Path, PathBuf}; const PACK_MAGIC: &[u8; 8] = b"OXYPACK1"; const IDX_MAGIC: &[u8; 8] = b"OXYIDX01"; const IDX_ENTRY: usize = 32 + 8 + 4 + 4 + 1 + 1; const FLAG_ZSTD: u8 = 1; const ZSTD_LEVEL: i32 = 3; #[derive(Clone, Copy, Debug)] struct PackEntry { offset: u64, stored_len: u32, raw_len: u32, ty: ObjectType, flags: u8, } /// One pack's index, fully in memory and sorted by ObjectRef. #[derive(Debug)] struct PackIndex { path: PathBuf, refs: Vec, entries: Vec, } impl PackIndex { fn load(idx_path: &Path, pack_path: &Path) -> Result { let data = fs::read(idx_path)?; let bad = |m: &str| StoreError::Corrupt(ObjectRef::ZERO, format!("{}: {m}", idx_path.display())); if data.len() < 12 || &data[..8] != IDX_MAGIC { return Err(bad("bad index header")); } let count = u32::from_le_bytes(data[8..12].try_into().unwrap()) as usize; if data.len() != 12 + count * IDX_ENTRY { return Err(bad("index length mismatch")); } let mut refs = Vec::with_capacity(count); let mut entries = Vec::with_capacity(count); for i in 0..count { let e = &data[12 + i * IDX_ENTRY..12 + (i + 1) * IDX_ENTRY]; let r = ObjectRef::from_slice(&e[..32]).unwrap(); if let Some(prev) = refs.last() { if r <= *prev { return Err(bad("index not sorted")); } } refs.push(r); entries.push(PackEntry { offset: u64::from_le_bytes(e[32..40].try_into().unwrap()), stored_len: u32::from_le_bytes(e[40..44].try_into().unwrap()), raw_len: u32::from_le_bytes(e[44..48].try_into().unwrap()), ty: ObjectType::ALL.get(e[48] as usize).copied().ok_or_else(|| bad("unknown object type"))?, flags: e[49], }); } Ok(PackIndex { path: pack_path.to_path_buf(), refs, entries }) } fn find(&self, r: &ObjectRef) -> Option { self.refs.binary_search(r).ok().map(|i| self.entries[i]) } fn read(&self, r: &ObjectRef, e: PackEntry) -> Result<(ObjectType, Vec)> { let mut f = fs::File::open(&self.path)?; f.seek(SeekFrom::Start(e.offset))?; let mut stored = vec![0u8; e.stored_len as usize]; f.read_exact(&mut stored)?; let body = if e.flags & FLAG_ZSTD != 0 { zstd::bulk::decompress(&stored, e.raw_len as usize).map_err(|err| StoreError::Corrupt(*r, format!("zstd: {err}")))? } else { stored }; if body.len() != e.raw_len as usize || hash_object(e.ty, &body) != *r { return Err(StoreError::Corrupt(*r, "packed object does not match its reference".into())); } Ok((e.ty, body)) } } fn type_index(ty: ObjectType) -> u8 { ObjectType::ALL.iter().position(|t| *t == ty).unwrap() as u8 } /// What `pack_loose` did. #[derive(Debug, Clone, Default, PartialEq, Eq)] pub struct PackReport { pub objects: usize, pub raw_bytes: u64, pub packed_bytes: u64, } #[derive(Debug, thiserror::Error)] pub enum StoreError { #[error("io: {0}")] Io(#[from] io::Error), #[error("corrupt object {0}: {1}")] Corrupt(ObjectRef, String), #[error("object {0}")] Object(#[from] ObjectError), #[error("object {0} is a {1}, expected {2}")] WrongType(ObjectRef, &'static str, &'static str), #[error("object {0} not found")] NotFound(ObjectRef), } pub type Result = std::result::Result; #[derive(Debug)] pub struct Store { dir: PathBuf, packs: RefCell>, } impl Store { pub fn open(dir: impl Into) -> io::Result { let dir = dir.into(); fs::create_dir_all(dir.join("loose"))?; let store = Store { dir, packs: RefCell::new(Vec::new()) }; store.reload_packs().map_err(|e| io::Error::other(e.to_string()))?; Ok(store) } fn reload_packs(&self) -> Result<()> { let mut packs = Vec::new(); let mut names: Vec = fs::read_dir(&self.dir)? .filter_map(|e| e.ok().map(|e| e.path())) .filter(|p| p.extension().is_some_and(|x| x == "idx") && p.file_name().is_some_and(|n| n.to_string_lossy().starts_with("pack-"))) .collect(); names.sort(); for idx in names { let pack = idx.with_extension("pack"); if pack.is_file() { packs.push(PackIndex::load(&idx, &pack)?); } } *self.packs.borrow_mut() = packs; Ok(()) } pub fn pack_count(&self) -> usize { self.packs.borrow().len() } fn find_packed(&self, r: &ObjectRef) -> Option<(usize, PackEntry)> { self.packs.borrow().iter().enumerate().find_map(|(i, p)| p.find(r).map(|e| (i, e))) } /// Loose objects on disk, with their paths. fn loose_objects(&self) -> io::Result> { let mut out = Vec::new(); let loose = self.dir.join("loose"); for d in fs::read_dir(&loose)? { let d = d?; if !d.file_type()?.is_dir() { continue; } let prefix = d.file_name().to_string_lossy().to_string(); for f in fs::read_dir(d.path())? { let f = f?; let name = f.file_name().to_string_lossy().to_string(); if let Some(r) = ObjectRef::from_hex(&format!("{prefix}{name}")) { out.push((r, f.path())); } } } out.sort(); Ok(out) } pub fn loose_count(&self) -> io::Result { Ok(self.loose_objects()?.len()) } /// Move every loose object into a new pack (spec §13.4). Loose files are /// deleted only after the pack and its index are durable. pub fn pack_loose(&self) -> Result { let loose = self.loose_objects()?; if loose.is_empty() { return Ok(PackReport::default()); } let mut nonce = [0u8; 8]; rand::rngs::OsRng.fill_bytes(&mut nonce); let id = hex::encode(nonce); let pack_path = self.dir.join(format!("pack-{id}.pack")); let idx_path = self.dir.join(format!("pack-{id}.idx")); let tmp_pack = self.dir.join(format!("tmp-{id}.pack")); let tmp_idx = self.dir.join(format!("tmp-{id}.idx")); let mut report = PackReport::default(); let mut index: Vec<(ObjectRef, PackEntry)> = Vec::with_capacity(loose.len()); { let mut f = io::BufWriter::new(fs::File::create(&tmp_pack)?); f.write_all(PACK_MAGIC)?; let mut offset = PACK_MAGIC.len() as u64; for (r, _) in &loose { let (ty, body) = self.get(r)?; let compressed = zstd::bulk::compress(&body, ZSTD_LEVEL).map_err(|e| StoreError::Corrupt(*r, format!("zstd: {e}")))?; let (flags, stored) = if compressed.len() < body.len() { (FLAG_ZSTD, compressed) } else { (0, body.clone()) }; let header_len = 1 + 1 + 4 + 4 + 32; f.write_all(&[type_index(ty), flags])?; f.write_all(&(stored.len() as u32).to_le_bytes())?; f.write_all(&(body.len() as u32).to_le_bytes())?; f.write_all(&r.0)?; f.write_all(&stored)?; index.push((*r, PackEntry { offset: offset + header_len, stored_len: stored.len() as u32, raw_len: body.len() as u32, ty, flags })); offset += header_len + stored.len() as u64; report.objects += 1; report.raw_bytes += body.len() as u64; report.packed_bytes += stored.len() as u64; } f.flush()?; f.get_ref().sync_all()?; } { let mut f = io::BufWriter::new(fs::File::create(&tmp_idx)?); f.write_all(IDX_MAGIC)?; f.write_all(&(index.len() as u32).to_le_bytes())?; for (r, e) in &index { f.write_all(&r.0)?; f.write_all(&e.offset.to_le_bytes())?; f.write_all(&e.stored_len.to_le_bytes())?; f.write_all(&e.raw_len.to_le_bytes())?; f.write_all(&[type_index(e.ty), e.flags])?; } f.flush()?; f.get_ref().sync_all()?; } fs::rename(&tmp_pack, &pack_path)?; fs::rename(&tmp_idx, &idx_path)?; self.reload_packs()?; for (_, path) in &loose { fs::remove_file(path)?; if let Some(dir) = path.parent() { let _ = fs::remove_dir(dir); } } Ok(report) } pub fn dir(&self) -> &Path { &self.dir } fn path_for(&self, r: &ObjectRef) -> PathBuf { let h = r.to_hex(); self.dir.join("loose").join(&h[..2]).join(&h[2..]) } pub fn has(&self, r: &ObjectRef) -> bool { self.path_for(r).is_file() || self.find_packed(r).is_some() } /// Store `body` as an object of type `ty`; idempotent. pub fn put(&self, ty: ObjectType, body: &[u8]) -> Result { let r = hash_object(ty, body); let path = self.path_for(&r); if path.is_file() || self.find_packed(&r).is_some() { return Ok(r); } fs::create_dir_all(path.parent().unwrap())?; let mut nonce = [0u8; 8]; rand::rngs::OsRng.fill_bytes(&mut nonce); let tmp = self.dir.join("loose").join(format!("tmp-{}", hex::encode(nonce))); { let mut f = fs::File::create(&tmp)?; f.write_all(&header(ty, body.len()))?; f.write_all(body)?; f.sync_all()?; } fs::rename(&tmp, &path)?; Ok(r) } /// Read and verify an object, loose or packed. pub fn get(&self, r: &ObjectRef) -> Result<(ObjectType, Vec)> { let path = self.path_for(r); let data = match fs::read(&path) { Ok(d) => d, Err(e) if e.kind() == io::ErrorKind::NotFound => { return match self.find_packed(r) { Some((i, e)) => self.packs.borrow()[i].read(r, e), None => Err(StoreError::NotFound(*r)), }; } Err(e) => return Err(e.into()), }; let nul = data.iter().position(|&b| b == 0).ok_or_else(|| StoreError::Corrupt(*r, "no header".into()))?; let head = std::str::from_utf8(&data[..nul]).map_err(|_| StoreError::Corrupt(*r, "header not UTF-8".into()))?; let mut parts = head.split(' '); let (Some("oxy1"), Some(ty), Some(len), None) = (parts.next(), parts.next(), parts.next(), parts.next()) else { return Err(StoreError::Corrupt(*r, format!("bad header {head:?}"))); }; let ty = ObjectType::from_name(ty).ok_or_else(|| StoreError::Corrupt(*r, format!("unknown type {ty}")))?; let len: usize = len.parse().map_err(|_| StoreError::Corrupt(*r, "bad length".into()))?; let body = &data[nul + 1..]; if body.len() != len { return Err(StoreError::Corrupt(*r, format!("length {} != header {len}", body.len()))); } if hash_object(ty, body) != *r { return Err(StoreError::Corrupt(*r, "hash mismatch".into())); } Ok((ty, body.to_vec())) } pub fn get_typed(&self, r: &ObjectRef, want: ObjectType) -> Result> { let (ty, body) = self.get(r)?; if ty != want { return Err(StoreError::WrongType(*r, ty.name(), want.name())); } Ok(body) } pub fn put_change(&self, c: &Change) -> Result { self.put(ObjectType::Change, &c.encode()) } pub fn get_change(&self, r: &ObjectRef) -> Result { Ok(Change::decode(&self.get_typed(r, ObjectType::Change)?)?) } pub fn put_chunk(&self, bytes: &[u8]) -> Result { self.put(ObjectType::Chunk, bytes) } pub fn put_state(&self, st: &StateObject) -> Result { self.put(ObjectType::State, &st.encode()) } pub fn get_state(&self, r: &ObjectRef) -> Result { Ok(StateObject::decode(&self.get_typed(r, ObjectType::State)?)?) } pub fn put_attest(&self, a: &Attest) -> Result { self.put(ObjectType::Attest, &a.encode()) } pub fn get_attest(&self, r: &ObjectRef) -> Result { Ok(Attest::decode(&self.get_typed(r, ObjectType::Attest)?)?) } fn seal_index_path(&self, change: &ObjectRef) -> PathBuf { let h = change.to_hex(); self.dir.join("seals").join(&h[..2]).join(&h[2..]) } /// Record that seal attestation `attest` covers `change`. pub fn index_seal(&self, change: &ObjectRef, attest: &ObjectRef) -> Result<()> { let mut seals = self.seals_for(change)?; if seals.contains(attest) { return Ok(()); } seals.push(*attest); seals.sort(); let path = self.seal_index_path(change); fs::create_dir_all(path.parent().unwrap())?; let text: String = seals.iter().map(|s| format!("{}\n", s.to_hex())).collect(); let tmp = path.with_extension("tmp"); fs::write(&tmp, text)?; fs::rename(&tmp, &path)?; Ok(()) } /// Seal attestations known to cover `change`. pub fn seals_for(&self, change: &ObjectRef) -> Result> { match fs::read_to_string(self.seal_index_path(change)) { Ok(t) => Ok(t.lines().filter_map(ObjectRef::from_hex).collect()), Err(e) if e.kind() == io::ErrorKind::NotFound => Ok(vec![]), Err(e) => Err(e.into()), } } pub fn put_identity(&self, id: &Identity) -> Result { self.put(ObjectType::Identity, &id.encode()) } pub fn get_identity(&self, r: &ObjectRef) -> Result { Ok(Identity::decode(&self.get_typed(r, ObjectType::Identity)?)?) } fn sig_path(&self, r: &ObjectRef) -> PathBuf { let h = r.to_hex(); self.dir.join("sigs").join(&h[..2]).join(&h[2..]) } /// Signatures stored alongside object `r` (spec §5.4). Empty if none. pub fn signatures(&self, r: &ObjectRef) -> Result> { match fs::read(self.sig_path(r)) { Ok(b) => Ok(Signature::decode_list(&b)?), Err(e) if e.kind() == io::ErrorKind::NotFound => Ok(vec![]), Err(e) => Err(e.into()), } } /// Attach a signature to object `r`, replacing any earlier one by the same key. pub fn put_signature(&self, r: &ObjectRef, sig: &Signature) -> Result<()> { let mut sigs = self.signatures(r)?; sigs.retain(|s| s.key != sig.key); sigs.push(sig.clone()); sigs.sort_by_key(|s| s.key); let path = self.sig_path(r); fs::create_dir_all(path.parent().unwrap())?; let mut nonce = [0u8; 8]; rand::rngs::OsRng.fill_bytes(&mut nonce); let tmp = self.dir.join(format!("sigs-tmp-{}", hex::encode(nonce))); { let mut f = fs::File::create(&tmp)?; f.write_all(&Signature::encode_list(&sigs))?; f.sync_all()?; } fs::rename(&tmp, &path)?; Ok(()) } /// Every object reference in the store, loose and packed (slow; for gc and tests). pub fn list(&self) -> io::Result> { let mut out: Vec = self.loose_objects()?.into_iter().map(|(r, _)| r).collect(); for p in self.packs.borrow().iter() { out.extend(p.refs.iter().copied()); } out.sort(); out.dedup(); Ok(out) } } #[cfg(test)] mod tests { use super::*; #[test] fn put_get_verify() { let dir = tempfile::tempdir().unwrap(); let s = Store::open(dir.path().join("objects")).unwrap(); let r = s.put(ObjectType::Chunk, b"hello").unwrap(); assert!(s.has(&r)); assert_eq!(s.get(&r).unwrap(), (ObjectType::Chunk, b"hello".to_vec())); assert_eq!(s.put(ObjectType::Chunk, b"hello").unwrap(), r); assert_eq!(s.list().unwrap(), vec![r]); assert!(matches!(s.get_typed(&r, ObjectType::Blob), Err(StoreError::WrongType(..)))); assert!(matches!(s.get(&ObjectRef([9; 32])), Err(StoreError::NotFound(_)))); // Tamper: flip a byte, read must fail. let path = s.path_for(&r); let mut data = fs::read(&path).unwrap(); let last = data.len() - 1; data[last] ^= 1; fs::write(&path, data).unwrap(); assert!(matches!(s.get(&r), Err(StoreError::Corrupt(..)))); } #[test] fn packing_keeps_every_object_readable() { let dir = tempfile::tempdir().unwrap(); let s = Store::open(dir.path()).unwrap(); let mut refs = Vec::new(); for i in 0..300u32 { let body = format!("object {i} ").repeat(1 + (i % 7) as usize); refs.push((s.put(ObjectType::Chunk, body.as_bytes()).unwrap(), body)); } let c = crate::objects::tests::sample_change(); let cr = s.put_change(&c).unwrap(); assert_eq!(s.loose_count().unwrap(), 301); let report = s.pack_loose().unwrap(); assert_eq!(report.objects, 301); assert!(report.packed_bytes < report.raw_bytes, "{report:?}"); assert_eq!(s.loose_count().unwrap(), 0); assert_eq!(s.pack_count(), 1); for (r, body) in &refs { assert!(s.has(r)); assert_eq!(s.get(r).unwrap(), (ObjectType::Chunk, body.as_bytes().to_vec())); } assert_eq!(s.get_change(&cr).unwrap(), c); assert_eq!(s.list().unwrap().len(), 301); // Re-putting a packed object is a no-op; new objects go loose and a // second pack coexists with the first. assert_eq!(s.put(ObjectType::Chunk, refs[0].1.as_bytes()).unwrap(), refs[0].0); assert_eq!(s.loose_count().unwrap(), 0); let extra = s.put(ObjectType::Chunk, b"after packing").unwrap(); s.pack_loose().unwrap(); assert_eq!(s.pack_count(), 2); assert_eq!(s.get(&extra).unwrap().1, b"after packing"); // A reopened store sees the packs. let s2 = Store::open(dir.path()).unwrap(); assert_eq!(s2.pack_count(), 2); assert_eq!(s2.get(&refs[5].0).unwrap().1, refs[5].1.as_bytes()); assert!(matches!(s2.get(&ObjectRef([9; 32])), Err(StoreError::NotFound(_)))); // Corrupting an object's body inside the pack is detected on read. let target = refs[5].0; let (pack_path, offset) = { let packs = s2.packs.borrow(); let (i, e) = s2.find_packed(&target).unwrap(); (packs[i].path.clone(), e.offset as usize) }; let mut data = fs::read(&pack_path).unwrap(); data[offset] ^= 0xff; fs::write(&pack_path, data).unwrap(); let s3 = Store::open(dir.path()).unwrap(); assert!(matches!(s3.get(&target), Err(StoreError::Corrupt(..)))); assert_eq!(s3.get(&refs[6].0).unwrap().1, refs[6].1.as_bytes(), "other objects are unaffected"); } #[test] fn signatures_are_stored_beside_objects() { use crate::identity::{Domain, SecretKey}; let dir = tempfile::tempdir().unwrap(); let s = Store::open(dir.path()).unwrap(); let r = s.put(ObjectType::Chunk, b"x").unwrap(); assert!(s.signatures(&r).unwrap().is_empty()); let sk = SecretKey { ed_seed: [1; 32], ml_seed: [2; 32] }; let id = sk.identity("a", "b", 0); let key = s.put_identity(&id).unwrap(); assert_eq!(s.get_identity(&key).unwrap(), id); let sig = sk.sign(Domain::Change, &key, &r); s.put_signature(&r, &sig).unwrap(); s.put_signature(&r, &sig).unwrap(); assert_eq!(s.signatures(&r).unwrap(), vec![sig]); // The object itself is untouched by its signatures. assert_eq!(s.get(&r).unwrap().1, b"x"); } #[test] fn change_round_trip_through_store() { let dir = tempfile::tempdir().unwrap(); let s = Store::open(dir.path()).unwrap(); let c = crate::objects::tests::sample_change(); let r = s.put_change(&c).unwrap(); assert_eq!(r, c.hash()); assert_eq!(s.get_change(&r).unwrap(), c); } }