Struct DedupStore 

pub struct DedupStore { /* private fields */ }

Deduplication store for managing deduplicated chunks.

Implementations

impl DedupStore

pub async fn new(base_path: PathBuf, config: DedupConfig) -> Result<Self>

Create a new deduplication store.

pub async fn store_chunk( &self, cid: &str, _chunk_index: u64, data: &[u8], ) -> Result<StoreResult>

Store a chunk with deduplication.

pub async fn get_chunk(&self, hash: &[u8; 32]) -> Result<Option<Vec<u8>>>

Retrieve a chunk by hash.

pub async fn get_content_chunk( &self, cid: &str, chunk_index: u64, ) -> Result<Option<Vec<u8>>>

Get a chunk by content CID and chunk index.

pub async fn remove_content(&self, cid: &str) -> Result<u64>

Remove references for a content item.

pub async fn stats(&self) -> DedupStats

Get deduplication statistics.

pub async fn contains(&self, hash: &[u8; 32]) -> bool

Check if a chunk hash exists.

pub async fn ref_count(&self, hash: &[u8; 32]) -> Option<u32>

Get chunk reference count.

pub async fn list_content(&self) -> Vec<String>

List all content CIDs in the store.

pub async fn content_info(&self, cid: &str) -> Option<ContentDedupInfo>

Get content info.

pub async fn gc(&self) -> Result<GcResult>

Run garbage collection to remove orphaned chunks.

impl DedupStore

pub async fn get_chunk_references( &self, hash: &[u8; 32], ) -> Option<Vec<ChunkReference>>

Get all references for a specific chunk hash.

pub async fn get_content_chunks_detailed( &self, cid: &str, ) -> Option<Vec<EnhancedChunkRef>>

List all chunks referenced by a specific content.

pub async fn verify_integrity(&self) -> Result<IntegrityCheckResult>

Verify reference count integrity across the store.

pub async fn repair_references(&self) -> Result<u64>

Repair reference counts based on actual references.

pub async fn ref_count_distribution(&self) -> HashMap<u32, u64>

Get reference count distribution statistics.

pub async fn most_referenced_chunks( &self, limit: usize, ) -> Vec<([u8; 32], u32, u64)>

Find the most frequently referenced chunks.

pub async fn calculate_removal_impact(&self, cid: &str) -> Option<RemovalImpact>

Calculate potential savings if content were removed.

pub async fn add_references_batch( &self, cid: &str, chunk_hashes: Vec<[u8; 32]>, ) -> Result<u64>

Batch add references for multiple chunks.