65 lines
1.6 KiB
PHP
Executable File
65 lines
1.6 KiB
PHP
Executable File
<?php
|
|
|
|
declare(strict_types=1);
|
|
|
|
namespace App\Services;
|
|
|
|
use Illuminate\Support\Facades\Log;
|
|
use Illuminate\Support\Facades\Storage;
|
|
use Smalot\PdfParser\Parser;
|
|
|
|
/**
|
|
* Service for extracting text content from PDF files.
|
|
*/
|
|
class PdfExtractionService
|
|
{
|
|
/**
|
|
* Extract text from a PDF file.
|
|
*
|
|
* @param string $filePath The path to the PDF file
|
|
* @return array{success: bool, content: string|null, error: string|null}
|
|
*/
|
|
public function extract(string $filePath): array
|
|
{
|
|
if (!file_exists($filePath)) {
|
|
return [
|
|
'success' => false,
|
|
'content' => null,
|
|
'error' => 'PDF file not found.',
|
|
];
|
|
}
|
|
|
|
try {
|
|
$parser = new Parser();
|
|
$pdf = $parser->parseFile($filePath);
|
|
$text = $pdf->getText();
|
|
|
|
$text = trim($text);
|
|
|
|
if (empty($text)) {
|
|
return [
|
|
'success' => false,
|
|
'content' => null,
|
|
'error' => 'The PDF appears to be empty or contains no extractable text.',
|
|
];
|
|
}
|
|
|
|
return [
|
|
'success' => true,
|
|
'content' => $text,
|
|
'error' => null,
|
|
];
|
|
} catch (\Exception $e) {
|
|
Log::error('PDF extraction error: ' . $e->getMessage(), [
|
|
'file' => $filePath,
|
|
]);
|
|
|
|
return [
|
|
'success' => false,
|
|
'content' => null,
|
|
'error' => 'Failed to extract text from PDF: ' . $e->getMessage(),
|
|
];
|
|
}
|
|
}
|
|
}
|