at-container-registry/pkg/appview/db/schema.go

package db

import (
	"database/sql"
	"strings"

	_ "github.com/mattn/go-sqlite3"
)

const schema = `
CREATE TABLE IF NOT EXISTS users (
    did TEXT PRIMARY KEY,
    handle TEXT NOT NULL,
    pds_endpoint TEXT NOT NULL,
    avatar TEXT,
    last_seen TIMESTAMP NOT NULL,
    UNIQUE(handle)
);
CREATE INDEX IF NOT EXISTS idx_users_handle ON users(handle);

CREATE TABLE IF NOT EXISTS manifests (
    id INTEGER PRIMARY KEY AUTOINCREMENT,
    did TEXT NOT NULL,
    repository TEXT NOT NULL,
    digest TEXT NOT NULL,
    hold_endpoint TEXT NOT NULL,
    schema_version INTEGER NOT NULL,
    media_type TEXT NOT NULL,
    config_digest TEXT,
    config_size INTEGER,
    raw_manifest TEXT NOT NULL,
    created_at TIMESTAMP NOT NULL,
    UNIQUE(did, repository, digest),
    FOREIGN KEY(did) REFERENCES users(did) ON DELETE CASCADE
);
CREATE INDEX IF NOT EXISTS idx_manifests_did_repo ON manifests(did, repository);
CREATE INDEX IF NOT EXISTS idx_manifests_created_at ON manifests(created_at DESC);
CREATE INDEX IF NOT EXISTS idx_manifests_digest ON manifests(digest);

CREATE TABLE IF NOT EXISTS layers (
    manifest_id INTEGER NOT NULL,
    digest TEXT NOT NULL,
    size INTEGER NOT NULL,
    media_type TEXT NOT NULL,
    layer_index INTEGER NOT NULL,
    PRIMARY KEY(manifest_id, layer_index),
    FOREIGN KEY(manifest_id) REFERENCES manifests(id) ON DELETE CASCADE
);
CREATE INDEX IF NOT EXISTS idx_layers_digest ON layers(digest);

CREATE TABLE IF NOT EXISTS tags (
    id INTEGER PRIMARY KEY AUTOINCREMENT,
    did TEXT NOT NULL,
    repository TEXT NOT NULL,
    tag TEXT NOT NULL,
    digest TEXT NOT NULL,
    created_at TIMESTAMP NOT NULL,
    UNIQUE(did, repository, tag),
    FOREIGN KEY(did) REFERENCES users(did) ON DELETE CASCADE
);
CREATE INDEX IF NOT EXISTS idx_tags_did_repo ON tags(did, repository);

CREATE TABLE IF NOT EXISTS firehose_cursor (
    id INTEGER PRIMARY KEY CHECK (id = 1),
    cursor INTEGER NOT NULL,
    updated_at TIMESTAMP NOT NULL
);

CREATE TABLE IF NOT EXISTS backfill_state (
    id INTEGER PRIMARY KEY CHECK (id = 1),
    start_cursor INTEGER NOT NULL,
    current_cursor INTEGER NOT NULL,
    completed BOOLEAN NOT NULL DEFAULT 0,
    updated_at TIMESTAMP NOT NULL
);
`

// InitDB initializes the SQLite database with the schema
func InitDB(path string) (*sql.DB, error) {
	db, err := sql.Open("sqlite3", path)
	if err != nil {
		return nil, err
	}

	// Enable foreign keys
	if _, err := db.Exec("PRAGMA foreign_keys = ON"); err != nil {
		return nil, err
	}

	// Create schema
	if _, err := db.Exec(schema); err != nil {
		return nil, err
	}

	// Migration: Add avatar column if it doesn't exist
	_, err = db.Exec(`ALTER TABLE users ADD COLUMN avatar TEXT`)
	// Ignore error if column already exists
	if err != nil && !strings.Contains(err.Error(), "duplicate column") {
		// Log but don't fail - column might already exist
	}

	// Migration: Convert old cdn.bsky.app avatar URLs to imgs.blue
	if err := migrateCDNURLs(db); err != nil {
		// Log but don't fail - not critical
		println("Warning: Failed to migrate CDN URLs:", err.Error())
	}

	return db, nil
}

// migrateCDNURLs converts old cdn.bsky.app avatar URLs to imgs.blue format
// Old format: https://cdn.bsky.app/img/avatar/plain/did:plc:abc123/bafkreibxuy73...@jpeg
// New format: https://imgs.blue/did:plc:abc123/bafkreibxuy73...
func migrateCDNURLs(db *sql.DB) error {
	// Find all users with cdn.bsky.app avatars
	rows, err := db.Query(`SELECT did, avatar FROM users WHERE avatar LIKE 'https://cdn.bsky.app/%'`)
	if err != nil {
		return err
	}
	defer rows.Close()

	updates := []struct {
		did    string
		newURL string
	}{}

	for rows.Next() {
		var did, oldURL string
		if err := rows.Scan(&did, &oldURL); err != nil {
			continue
		}

		// Extract CID from old URL
		// Format: https://cdn.bsky.app/img/avatar/plain/did:plc:abc123/bafkreibxuy73...@jpeg
		parts := strings.Split(oldURL, "/")
		if len(parts) < 7 {
			continue
		}

		// Get the last part which contains CID@format
		cidPart := parts[len(parts)-1]
		// Strip off @jpeg or @png suffix
		cid := strings.Split(cidPart, "@")[0]

		// Construct new imgs.blue URL
		newURL := "https://imgs.blue/" + did + "/" + cid

		updates = append(updates, struct {
			did    string
			newURL string
		}{did, newURL})
	}

	// Update all users
	stmt, err := db.Prepare(`UPDATE users SET avatar = ? WHERE did = ?`)
	if err != nil {
		return err
	}
	defer stmt.Close()

	for _, update := range updates {
		if _, err := stmt.Exec(update.newURL, update.did); err != nil {
			// Log but continue
			println("Warning: Failed to update avatar for", update.did, ":", err.Error())
		}
	}

	if len(updates) > 0 {
		println("Migrated", len(updates), "avatar URLs from cdn.bsky.app to imgs.blue")
	}

	return nil
}