vaultik/internal/database/schema/001.sql

-- Migration 001: Initial Vaultik schema
-- All core tables for tracking files, chunks, blobs, snapshots, and uploads.

-- Files table: stores metadata about files in the filesystem
CREATE TABLE IF NOT EXISTS files (
    id TEXT PRIMARY KEY,  -- UUID
    path TEXT NOT NULL UNIQUE,
    source_path TEXT NOT NULL DEFAULT '',  -- The source directory this file came from (for restore path stripping)
    mtime INTEGER NOT NULL,
    size INTEGER NOT NULL,
    mode INTEGER NOT NULL,
    uid INTEGER NOT NULL,
    gid INTEGER NOT NULL,
    link_target TEXT
);

-- Create index on path for efficient lookups
CREATE INDEX IF NOT EXISTS idx_files_path ON files(path);

-- File chunks table: maps files to their constituent chunks
CREATE TABLE IF NOT EXISTS file_chunks (
    file_id TEXT NOT NULL,
    idx INTEGER NOT NULL,
    chunk_hash TEXT NOT NULL,
    PRIMARY KEY (file_id, idx),
    FOREIGN KEY (file_id) REFERENCES files(id) ON DELETE CASCADE,
    FOREIGN KEY (chunk_hash) REFERENCES chunks(chunk_hash)
);

-- Index for efficient chunk lookups (used in orphan detection)
CREATE INDEX IF NOT EXISTS idx_file_chunks_chunk_hash ON file_chunks(chunk_hash);

-- Chunks table: stores unique content-defined chunks
CREATE TABLE IF NOT EXISTS chunks (
    chunk_hash TEXT PRIMARY KEY,
    size INTEGER NOT NULL
);

-- Blobs table: stores packed, compressed, and encrypted blob information
CREATE TABLE IF NOT EXISTS blobs (
    id TEXT PRIMARY KEY,
    blob_hash TEXT UNIQUE,
    created_ts INTEGER NOT NULL,
    finished_ts INTEGER,
    uncompressed_size INTEGER NOT NULL DEFAULT 0,
    compressed_size INTEGER NOT NULL DEFAULT 0,
    uploaded_ts INTEGER
);

-- Blob chunks table: maps chunks to the blobs that contain them
CREATE TABLE IF NOT EXISTS blob_chunks (
    blob_id TEXT NOT NULL,
    chunk_hash TEXT NOT NULL,
    offset INTEGER NOT NULL,
    length INTEGER NOT NULL,
    PRIMARY KEY (blob_id, chunk_hash),
    FOREIGN KEY (blob_id) REFERENCES blobs(id) ON DELETE CASCADE,
    FOREIGN KEY (chunk_hash) REFERENCES chunks(chunk_hash)
);

-- Index for efficient chunk lookups (used in orphan detection)
CREATE INDEX IF NOT EXISTS idx_blob_chunks_chunk_hash ON blob_chunks(chunk_hash);

-- Chunk files table: reverse mapping of chunks to files
CREATE TABLE IF NOT EXISTS chunk_files (
    chunk_hash TEXT NOT NULL,
    file_id TEXT NOT NULL,
    file_offset INTEGER NOT NULL,
    length INTEGER NOT NULL,
    PRIMARY KEY (chunk_hash, file_id),
    FOREIGN KEY (chunk_hash) REFERENCES chunks(chunk_hash),
    FOREIGN KEY (file_id) REFERENCES files(id) ON DELETE CASCADE
);

-- Index for efficient file lookups (used in orphan detection)
CREATE INDEX IF NOT EXISTS idx_chunk_files_file_id ON chunk_files(file_id);

-- Snapshots table: tracks backup snapshots
CREATE TABLE IF NOT EXISTS snapshots (
    id TEXT PRIMARY KEY,
    hostname TEXT NOT NULL,
    vaultik_version TEXT NOT NULL,
    vaultik_git_revision TEXT NOT NULL,
    started_at INTEGER NOT NULL,
    completed_at INTEGER,
    file_count INTEGER NOT NULL DEFAULT 0,
    chunk_count INTEGER NOT NULL DEFAULT 0,
    blob_count INTEGER NOT NULL DEFAULT 0,
    total_size INTEGER NOT NULL DEFAULT 0,
    blob_size INTEGER NOT NULL DEFAULT 0,
    blob_uncompressed_size INTEGER NOT NULL DEFAULT 0,
    compression_ratio REAL NOT NULL DEFAULT 1.0,
    compression_level INTEGER NOT NULL DEFAULT 3,
    upload_bytes INTEGER NOT NULL DEFAULT 0,
    upload_duration_ms INTEGER NOT NULL DEFAULT 0
);

-- Snapshot files table: maps snapshots to files
CREATE TABLE IF NOT EXISTS snapshot_files (
    snapshot_id TEXT NOT NULL,
    file_id TEXT NOT NULL,
    PRIMARY KEY (snapshot_id, file_id),
    FOREIGN KEY (snapshot_id) REFERENCES snapshots(id) ON DELETE CASCADE,
    FOREIGN KEY (file_id) REFERENCES files(id) ON DELETE CASCADE
);

-- Index for efficient file lookups (used in orphan detection)
CREATE INDEX IF NOT EXISTS idx_snapshot_files_file_id ON snapshot_files(file_id);

-- Snapshot blobs table: maps snapshots to blobs
CREATE TABLE IF NOT EXISTS snapshot_blobs (
    snapshot_id TEXT NOT NULL,
    blob_id TEXT NOT NULL,
    blob_hash TEXT NOT NULL,
    PRIMARY KEY (snapshot_id, blob_id),
    FOREIGN KEY (snapshot_id) REFERENCES snapshots(id) ON DELETE CASCADE,
    FOREIGN KEY (blob_id) REFERENCES blobs(id) ON DELETE CASCADE
);

-- Index for efficient blob lookups (used in orphan detection)
CREATE INDEX IF NOT EXISTS idx_snapshot_blobs_blob_id ON snapshot_blobs(blob_id);

-- Uploads table: tracks blob upload metrics
CREATE TABLE IF NOT EXISTS uploads (
    blob_hash TEXT PRIMARY KEY,
    snapshot_id TEXT NOT NULL,
    uploaded_at INTEGER NOT NULL,
    size INTEGER NOT NULL,
    duration_ms INTEGER NOT NULL,
    FOREIGN KEY (blob_hash) REFERENCES blobs(blob_hash),
    FOREIGN KEY (snapshot_id) REFERENCES snapshots(id) ON DELETE CASCADE
);

-- Index for efficient snapshot lookups
CREATE INDEX IF NOT EXISTS idx_uploads_snapshot_id ON uploads(snapshot_id);

-- Local metadata: keyed, host-local settings that bind the state of the
-- local index database to external context. The primary use is
-- storage_url: once a backup writes blobs to a destination, the local
-- index is only valid against that destination — if the configured
-- storage_url later changes, the scanner would silently think already-
-- known chunks are still on the new (empty) destination and skip
-- uploading them, corrupting future snapshots. On every mutating
-- command startup, we compare the configured storage_url to the stored
-- one and refuse to proceed on mismatch.
CREATE TABLE IF NOT EXISTS local_meta (
    key TEXT PRIMARY KEY,
    value TEXT NOT NULL
);