<?php
/**
 * PDF Document Text Extractor.
 *
 * @package AISupportAssistant\Documents
 */

namespace AISupportAssistant\Documents;

use AISupportAssistant\Helpers\TextHelper;
use AISupportAssistant\Helpers\Logger;

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

/**
 * Class PdfExtractor
 */
class PdfExtractor implements ExtractorInterface {

	/**
	 * Extract text from a PDF document.
	 *
	 * @param string $file_path Absolute path to the file.
	 * @return string Cleaned text.
	 */
	public function extract( string $file_path ): string {
		return implode( "\n\n", $this->extract_pages( $file_path ) );
	}

	/** Extract each physical PDF page, preserving blank-page numbering. */
	public function extract_pages( string $file_path ): array {
		if ( ! file_exists( $file_path ) ) {
			Logger::error( 'PdfExtractor failed: File does not exist.', array( 'path' => $file_path ) );
			return array();
		}

		try {
			$parser = new \Smalot\PdfParser\Parser();
			$pdf    = $parser->parseFile( $file_path );
			$pages = array();
			foreach ( $pdf->getPages() as $index => $page ) {
				$pages[ $index + 1 ] = TextHelper::clean_text( $page->getText() );
			}
			return $pages;
		} catch ( \Exception $e ) {
			Logger::error( 'PdfExtractor failed: ' . $e->getMessage(), array( 'path' => $file_path ) );
			return array();
		}
	}
}