h4b-image-optim/includes/class-cli-migrate.php

<?php
/**
 * wp h4b-img migrate-from-smush
 *
 * Reads Smush's `wp-smpro-smush-data` postmeta and writes an equivalent
 * `_h4b_img_optim` marker so our bulk command skips already-processed images.
 *
 * @package H4B\ImageOptim
 */

namespace H4B\ImageOptim;

if ( ! defined( 'ABSPATH' ) ) {
	exit;
}

final class CLI_Migrate {

	public const SMUSH_META_KEY = 'wp-smpro-smush-data';

	/**
	 * Migrate Smush optimisation history into h4b-image-optim's tracking.
	 *
	 * ## OPTIONS
	 *
	 * [--dry-run]
	 * : Count only — do not write any postmeta.
	 *
	 * [--force-rescan]
	 * : Mark Smush-processed images as UNPROCESSED so our bulk command
	 *   re-runs them through our pipeline. Use this when migrating off
	 *   Smush and you want to re-optimise everything with our ICC-safe
	 *   settings. Default: false (skip them, trust Smush did fine).
	 *
	 * [--remove-smush-meta]
	 * : After migration, delete the wp-smpro-smush-data postmeta. Frees
	 *   ~1KB per attachment. Default: false (keep for audit).
	 *
	 * [--limit=<n>]
	 * : Max attachments to migrate. 0 = unlimited.
	 *
	 * ## EXAMPLES
	 *     # See how many Smush-processed images exist
	 *     wp h4b-img migrate-from-smush --dry-run
	 *
	 *     # Trust Smush's prior work — just mark them processed
	 *     wp h4b-img migrate-from-smush
	 *
	 *     # Re-optimise everything from scratch through our pipeline
	 *     wp h4b-img migrate-from-smush --force-rescan
	 *
	 *     # Also strip the Smush postmeta after migration
	 *     wp h4b-img migrate-from-smush --remove-smush-meta
	 */
	public function __invoke( $args, $assoc ): void {
		$dry_run      = ! empty( $assoc['dry-run'] );
		$force_rescan = ! empty( $assoc['force-rescan'] );
		$remove_smush = ! empty( $assoc['remove-smush-meta'] );
		$limit        = (int) ( $assoc['limit'] ?? 0 );

		global $wpdb;

		$base_sql = "SELECT pm.post_id, pm.meta_value, p.post_mime_type
			FROM {$wpdb->postmeta} pm
			INNER JOIN {$wpdb->posts} p ON p.ID = pm.post_id
			WHERE pm.meta_key = %s
			ORDER BY pm.post_id ASC";
		if ( $limit > 0 ) {
			$base_sql .= ' LIMIT ' . (int) $limit;
		}
		$rows = $wpdb->get_results( $wpdb->prepare( $base_sql, self::SMUSH_META_KEY ) );

		$total = count( $rows );
		\WP_CLI::log( "Found $total attachments with Smush optimisation history." );
		if ( $total === 0 ) {
			\WP_CLI::success( 'Nothing to migrate.' );
			return;
		}

		if ( $dry_run ) {
			$action = $force_rescan ? 'mark for re-optimisation' : 'mark as already processed';
			$remove = $remove_smush ? ' + remove Smush meta' : '';
			\WP_CLI::success( "Dry-run only. Would $action $total attachments$remove." );
			return;
		}

		$progress  = \WP_CLI\Utils\make_progress_bar( 'Migrating', $total );
		$migrated  = 0;
		$skipped   = 0;
		$errored   = 0;
		$removed_meta = 0;

		foreach ( $rows as $row ) {
			$id = (int) $row->post_id;
			try {
				if ( $force_rescan ) {
					// Wipe our marker so bulk treats this as unprocessed
					delete_post_meta( $id, Attachment_Meta::META_KEY );
				} else {
					$existing = Attachment_Meta::get( $id );
					if ( ! empty( $existing['processed_at'] ) ) {
						$skipped++;
						$progress->tick();
						continue;
					}
					$stats = self::translate_smush_stats( (string) $row->meta_value );
					$meta = [
						'version'      => H4B_IMG_OPTIM_VERSION,
						'processed_at' => current_time( 'c' ),
						'migrated_from' => 'smush',
						'tool_chain'   => [ 'smush_legacy' ],
						'sizes'        => $stats['sizes'],
						'totals'       => $stats['totals'],
						'note'         => 'Migrated from Smush — not re-processed by h4b-image-optim.',
					];
					Attachment_Meta::set( $id, $meta );
				}

				if ( $remove_smush ) {
					if ( delete_post_meta( $id, self::SMUSH_META_KEY ) ) {
						$removed_meta++;
					}
				}
				$migrated++;
			} catch ( \Throwable $e ) {
				$errored++;
			}
			$progress->tick();
		}
		$progress->finish();

		\WP_CLI::success( sprintf(
			"Migration done.\n  Migrated: %d\n  Already-marked (skipped): %d\n  Errors: %d\n  Smush meta removed: %d",
			$migrated, $skipped, $errored, $removed_meta
		) );
	}

	/**
	 * Translate Smush's serialized stats into our schema.
	 *
	 * Smush stores:
	 *   a:2:{
	 *     s:"stats" => [ time, bytes, percent, size_before, size_after, lossy, keep_exif, api_version ],
	 *     s:"sizes" => [ <size_key> => stdClass{ time, bytes, percent, size_before, size_after }, ... ]
	 *   }
	 */
	private static function translate_smush_stats( string $raw ): array {
		$result = [
			'sizes'  => [],
			'totals' => [
				'bytes_saved'  => 0,
				'bytes_before' => 0,
				'bytes_after'  => 0,
				'percent'      => 0,
			],
		];

		// Smush uses PHP serialize. Allow stdClass.
		$data = @unserialize( $raw, [ 'allowed_classes' => [ \stdClass::class ] ] );
		if ( ! is_array( $data ) ) {
			return $result;
		}

		if ( isset( $data['stats'] ) && is_array( $data['stats'] ) ) {
			$result['totals']['bytes_saved']  = (int) ( $data['stats']['bytes'] ?? 0 );
			$result['totals']['bytes_before'] = (int) ( $data['stats']['size_before'] ?? 0 );
			$result['totals']['bytes_after']  = (int) ( $data['stats']['size_after'] ?? 0 );
			$result['totals']['percent']      = (float) ( $data['stats']['percent'] ?? 0 );
		}

		if ( isset( $data['sizes'] ) && is_array( $data['sizes'] ) ) {
			foreach ( $data['sizes'] as $size_key => $info ) {
				// $info can be stdClass or array
				$arr = is_object( $info ) ? get_object_vars( $info ) : (array) $info;
				$result['sizes'][ (string) $size_key ] = [
					'status'        => 'migrated_from_smush',
					'before'        => (int) ( $arr['size_before'] ?? 0 ),
					'after'         => (int) ( $arr['size_after']  ?? 0 ),
					'percent'       => (float) ( $arr['percent']    ?? 0 ),
					'icc_preserved' => false, // unknown — Smush stripped it
					'tool_chain'    => [ 'smush_legacy' ],
					'webp'          => null,
					'avif'          => null,
					'avif_status'   => 'never_generated',
					'backup'        => null,
					'error'         => null,
				];
			}
		}

		return $result;
	}
}