pixa/internal/db/migrations/001_schema.sql

-- Migration 001: Initial schema
-- Creates all tables for the pixa caching image proxy

-- Source content blobs
-- Files stored at: cache/sources/<ab>/<cd>/<sha256>
CREATE TABLE IF NOT EXISTS source_content (
    content_hash TEXT PRIMARY KEY,
    content_type TEXT NOT NULL,
    size_bytes INTEGER NOT NULL,
    fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
    last_accessed_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP
);
CREATE INDEX IF NOT EXISTS idx_source_content_last_accessed
    ON source_content(last_accessed_at);

-- Source URL metadata - maps URLs to content hashes
-- JSON stored at: cache/metadata/<hostname>/<path_hash>.json
CREATE TABLE IF NOT EXISTS source_metadata (
    id INTEGER PRIMARY KEY AUTOINCREMENT,
    source_host TEXT NOT NULL,
    source_path TEXT NOT NULL,
    source_query TEXT NOT NULL DEFAULT '',
    path_hash TEXT NOT NULL,
    content_hash TEXT,
    status_code INTEGER NOT NULL,
    content_type TEXT,
    response_headers TEXT,
    fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
    expires_at DATETIME,
    etag TEXT,
    last_modified TEXT,
    UNIQUE(source_host, source_path, source_query),
    FOREIGN KEY (content_hash) REFERENCES source_content(content_hash)
);
CREATE INDEX IF NOT EXISTS idx_source_meta_host ON source_metadata(source_host);
CREATE INDEX IF NOT EXISTS idx_source_meta_path_hash ON source_metadata(path_hash);
CREATE INDEX IF NOT EXISTS idx_source_meta_expires ON source_metadata(expires_at);
CREATE INDEX IF NOT EXISTS idx_source_meta_content_hash ON source_metadata(content_hash);

-- Processed variant blobs
-- Files stored at: cache/variants/<ab>/<cd>/<cache_key> (plus a .meta
-- sidecar with the content type). Tracked here (like source content
-- blobs above) so total cache usage is known without a directory scan,
-- and so LRU eviction has a timestamp to order on.
CREATE TABLE IF NOT EXISTS variant_content (
    cache_key TEXT PRIMARY KEY,
    size_bytes INTEGER NOT NULL,
    content_type TEXT NOT NULL,
    created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
    last_accessed_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP
);
CREATE INDEX IF NOT EXISTS idx_variant_content_last_accessed
    ON variant_content(last_accessed_at);

-- Total cache usage: the sum of size_bytes over source_content and
-- variant_content, kept by the triggers below in the same statement
-- that adds, removes or resizes a row, so eviction reads this one row
-- instead of summing both tables. Each trigger also adds one to
-- change_count; the reconciliation pass, which sums both tables a page
-- at a time, corrects total_size_bytes only if change_count did not
-- move while it summed.
CREATE TABLE IF NOT EXISTS cache_usage (
    id INTEGER PRIMARY KEY CHECK (id = 1),
    total_size_bytes INTEGER NOT NULL DEFAULT 0,
    change_count INTEGER NOT NULL DEFAULT 0
);
INSERT OR IGNORE INTO cache_usage (id) VALUES (1);

CREATE TRIGGER IF NOT EXISTS source_content_usage_insert
AFTER INSERT ON source_content
BEGIN
    UPDATE cache_usage
    SET total_size_bytes = total_size_bytes + NEW.size_bytes,
        change_count = change_count + 1
    WHERE id = 1;
END;

CREATE TRIGGER IF NOT EXISTS source_content_usage_delete
AFTER DELETE ON source_content
BEGIN
    UPDATE cache_usage
    SET total_size_bytes = total_size_bytes - OLD.size_bytes,
        change_count = change_count + 1
    WHERE id = 1;
END;

CREATE TRIGGER IF NOT EXISTS source_content_usage_update
AFTER UPDATE OF size_bytes ON source_content
BEGIN
    UPDATE cache_usage
    SET total_size_bytes = total_size_bytes - OLD.size_bytes + NEW.size_bytes,
        change_count = change_count + 1
    WHERE id = 1;
END;

CREATE TRIGGER IF NOT EXISTS variant_content_usage_insert
AFTER INSERT ON variant_content
BEGIN
    UPDATE cache_usage
    SET total_size_bytes = total_size_bytes + NEW.size_bytes,
        change_count = change_count + 1
    WHERE id = 1;
END;

CREATE TRIGGER IF NOT EXISTS variant_content_usage_delete
AFTER DELETE ON variant_content
BEGIN
    UPDATE cache_usage
    SET total_size_bytes = total_size_bytes - OLD.size_bytes,
        change_count = change_count + 1
    WHERE id = 1;
END;

CREATE TRIGGER IF NOT EXISTS variant_content_usage_update
AFTER UPDATE OF size_bytes ON variant_content
BEGIN
    UPDATE cache_usage
    SET total_size_bytes = total_size_bytes - OLD.size_bytes + NEW.size_bytes,
        change_count = change_count + 1
    WHERE id = 1;
END;

-- Output/transformed content blobs
-- Not written: transformed images are stored in cache/variants and
-- tracked in variant_content above.
CREATE TABLE IF NOT EXISTS output_content (
    content_hash TEXT PRIMARY KEY,
    content_type TEXT NOT NULL,
    size_bytes INTEGER NOT NULL,
    fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP
);

-- Request cache - maps full request params to output content
CREATE TABLE IF NOT EXISTS request_cache (
    id INTEGER PRIMARY KEY AUTOINCREMENT,
    cache_key TEXT NOT NULL UNIQUE,
    source_metadata_id INTEGER NOT NULL,
    output_hash TEXT NOT NULL,
    width INTEGER NOT NULL,
    height INTEGER NOT NULL,
    format TEXT NOT NULL,
    quality INTEGER NOT NULL DEFAULT 85,
    fit_mode TEXT NOT NULL DEFAULT 'cover',
    fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
    access_count INTEGER NOT NULL DEFAULT 1,
    FOREIGN KEY (source_metadata_id) REFERENCES source_metadata(id),
    FOREIGN KEY (output_hash) REFERENCES output_content(content_hash)
);
CREATE INDEX IF NOT EXISTS idx_request_cache_key ON request_cache(cache_key);
CREATE INDEX IF NOT EXISTS idx_request_cache_source ON request_cache(source_metadata_id);
CREATE INDEX IF NOT EXISTS idx_request_cache_output ON request_cache(output_hash);
CREATE INDEX IF NOT EXISTS idx_request_cache_fetched ON request_cache(fetched_at);

-- Negative cache for failed fetches (404s, timeouts, etc.)
CREATE TABLE IF NOT EXISTS negative_cache (
    id INTEGER PRIMARY KEY AUTOINCREMENT,
    source_host TEXT NOT NULL,
    source_path TEXT NOT NULL,
    source_query TEXT NOT NULL DEFAULT '',
    status_code INTEGER NOT NULL,
    error_message TEXT,
    fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
    expires_at DATETIME NOT NULL,
    UNIQUE(source_host, source_path, source_query)
);
CREATE INDEX IF NOT EXISTS idx_negative_cache_expires ON negative_cache(expires_at);

-- Cache statistics for monitoring
CREATE TABLE IF NOT EXISTS cache_stats (
    id INTEGER PRIMARY KEY CHECK (id = 1),
    hit_count INTEGER NOT NULL DEFAULT 0,
    miss_count INTEGER NOT NULL DEFAULT 0,
    upstream_fetch_count INTEGER NOT NULL DEFAULT 0,
    upstream_fetch_bytes INTEGER NOT NULL DEFAULT 0,
    transform_count INTEGER NOT NULL DEFAULT 0,
    last_updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
INSERT OR IGNORE INTO cache_stats (id) VALUES (1);