pdf-accessibility/api.php

<?php
/**
 * Enterprise PDF Accessibility Checker - API Backend
 * 
 * Handles file uploads, job processing, and result retrieval
 */

// Configuration
define('UPLOAD_DIR', __DIR__ . '/uploads');
define('RESULTS_DIR', __DIR__ . '/results');
define('PYTHON_SCRIPT', __DIR__ . '/enterprise_pdf_checker.py');
define('MAX_FILE_SIZE', 50 * 1024 * 1024); // 50MB
define('ALLOWED_EXTENSIONS', ['pdf']);

// Create directories if they don't exist
if (!is_dir(UPLOAD_DIR)) mkdir(UPLOAD_DIR, 0755, true);
if (!is_dir(RESULTS_DIR)) mkdir(RESULTS_DIR, 0755, true);

// CORS headers for API
header('Access-Control-Allow-Origin: *');
header('Access-Control-Allow-Methods: POST, GET, OPTIONS');
header('Access-Control-Allow-Headers: Content-Type');
header('Content-Type: application/json');

// Handle preflight
if ($_SERVER['REQUEST_METHOD'] === 'OPTIONS') {
    exit(0);
}

// Get action
$action = $_GET['action'] ?? $_POST['action'] ?? '';

switch ($action) {
    case 'upload':
        handleUpload();
        break;
    case 'check':
        handleCheck();
        break;
    case 'status':
        handleStatus();
        break;
    case 'result':
        handleResult();
        break;
    case 'list':
        handleList();
        break;
    case 'delete':
        handleDelete();
        break;
    case 'debug':
        handleDebug();
        break;
    case 'image':
        handleImage();
        break;
    case 'remediate':
        handleRemediate();
        break;
    case 'download':
        handleDownload();
        break;
    default:
        error('Invalid action');
}

/**
 * Handle file upload
 */
function handleUpload() {
    if (!isset($_FILES['pdf'])) {
        error('No file uploaded');
    }
    
    $file = $_FILES['pdf'];
    
    // Validate file
    if ($file['error'] !== UPLOAD_ERR_OK) {
        error('Upload error: ' . $file['error']);
    }
    
    if ($file['size'] > MAX_FILE_SIZE) {
        error('File too large. Max size: ' . (MAX_FILE_SIZE / 1024 / 1024) . 'MB');
    }
    
    $ext = strtolower(pathinfo($file['name'], PATHINFO_EXTENSION));
    if (!in_array($ext, ALLOWED_EXTENSIONS)) {
        error('Invalid file type. Only PDF files allowed.');
    }
    
    // Generate unique ID
    $job_id = uniqid('pdf_', true);
    $filename = $job_id . '.pdf';
    $filepath = UPLOAD_DIR . '/' . $filename;
    
    // Move file
    if (!move_uploaded_file($file['tmp_name'], $filepath)) {
        error('Failed to save file');
    }
    
    // Create job metadata
    $job_data = [
        'job_id' => $job_id,
        'original_filename' => $file['name'],
        'uploaded_at' => date('Y-m-d H:i:s'),
        'file_size' => $file['size'],
        'status' => 'uploaded',
        'filepath' => $filepath
    ];
    
    file_put_contents(
        RESULTS_DIR . '/' . $job_id . '.meta.json',
        json_encode($job_data, JSON_PRETTY_PRINT)
    );
    
    success([
        'job_id' => $job_id,
        'filename' => $file['name'],
        'message' => 'File uploaded successfully'
    ]);
}

/**
 * Handle PDF accessibility check
 */
function handleCheck() {
    $job_id = $_POST['job_id'] ?? '';
    
    if (empty($job_id)) {
        error('Job ID required');
    }
    
    $meta_file = RESULTS_DIR . '/' . $job_id . '.meta.json';
    
    if (!file_exists($meta_file)) {
        error('Job not found');
    }
    
    $job_data = json_decode(file_get_contents($meta_file), true);
    
    // Build command - use venv Python with absolute path
    $pdf_path = $job_data['filepath'];
    $output_path = RESULTS_DIR . '/' . $job_id . '.result.json';

    // Use absolute venv path for MAMP
    $venv_python = '/Users/daveporter/Desktop/CODING-2024/PDF-Accessibility-checker/venv/bin/python3';
    $python_bin = file_exists($venv_python) ? $venv_python : 'python3';

    // Note: Python script will auto-generate page images when --output is specified
    $cmd = escapeshellcmd($python_bin . ' ' . PYTHON_SCRIPT) . ' ' .
           escapeshellarg($pdf_path) . ' ' .
           '--output ' . escapeshellarg($output_path);

    // Handle quick mode
    $quick_mode = $_POST['quick_mode'] ?? false;
    if ($quick_mode) {
        $cmd .= ' --quick';
    }

    // Handle API keys - accept both formats
    $anthropic_key = $_POST['anthropic_key'] ?? getenv('ANTHROPIC_API_KEY');
    $google_key = $_POST['google_key'] ?? $_POST['google_credentials'] ?? getenv('GOOGLE_API_KEY') ?? getenv('GOOGLE_APPLICATION_CREDENTIALS');
    
    if ($anthropic_key) {
        $cmd .= ' --anthropic-key ' . escapeshellarg($anthropic_key);
    }
    
    if ($google_key) {
        // Check if it's a file path or an API key
        if (file_exists($google_key)) {
            // It's a JSON credentials file
            $cmd .= ' --google-credentials ' . escapeshellarg($google_key);
        } else {
            // It's an API key string
            $cmd .= ' --google-key ' . escapeshellarg($google_key);
        }
    }
    
    // Update status
    $job_data['status'] = 'processing';
    $job_data['started_at'] = date('Y-m-d H:i:s');
    $job_data['command'] = $cmd; // Store for debugging
    file_put_contents($meta_file, json_encode($job_data, JSON_PRETTY_PRINT));

    // Set PATH to include Homebrew (for poppler)
    $env_path = getenv('PATH');
    $poppler_paths = '/opt/homebrew/bin:/usr/local/bin';
    putenv("PATH={$poppler_paths}:{$env_path}");

    // Log errors to a file for debugging
    $error_log = RESULTS_DIR . '/' . $job_id . '.error.log';
    $cmd .= ' > ' . escapeshellarg($error_log) . ' 2>&1 &';

    exec($cmd, $output, $return_code);

    success([
        'job_id' => $job_id,
        'status' => 'processing',
        'message' => 'Check started',
        'debug' => [
            'command' => $cmd,
            'return_code' => $return_code
        ]
    ]);
}

/**
 * Check job status
 */
function handleStatus() {
    $job_id = $_GET['job_id'] ?? '';

    if (empty($job_id)) {
        error('Job ID required');
    }

    $meta_file = RESULTS_DIR . '/' . $job_id . '.meta.json';
    $result_file = RESULTS_DIR . '/' . $job_id . '.result.json';
    $error_log = RESULTS_DIR . '/' . $job_id . '.error.log';

    if (!file_exists($meta_file)) {
        error('Job not found');
    }

    $job_data = json_decode(file_get_contents($meta_file), true);

    // Check if result exists
    if (file_exists($result_file)) {
        $job_data['status'] = 'completed';
        $job_data['completed_at'] = date('Y-m-d H:i:s', filemtime($result_file));

        // Update meta
        file_put_contents($meta_file, json_encode($job_data, JSON_PRETTY_PRINT));
    } else if (file_exists($error_log)) {
        // Check if there are errors
        $error_content = file_get_contents($error_log);
        if (!empty($error_content) && $job_data['status'] == 'processing') {
            // Check if it's been more than 5 minutes
            $started = strtotime($job_data['started_at']);
            if (time() - $started > 300) {
                $job_data['status'] = 'failed';
                $job_data['error'] = 'Process timeout or error';
                $job_data['error_log'] = substr($error_content, -1000); // Last 1000 chars
            }
        }
    }

    success($job_data);
}

/**
 * Get check results
 */
function handleResult() {
    $job_id = $_GET['job_id'] ?? '';
    
    if (empty($job_id)) {
        error('Job ID required');
    }
    
    $result_file = RESULTS_DIR . '/' . $job_id . '.result.json';
    
    if (!file_exists($result_file)) {
        error('Results not found. Check may still be processing.');
    }
    
    $result = json_decode(file_get_contents($result_file), true);
    
    success($result);
}

/**
 * List all jobs
 */
function handleList() {
    $jobs = [];
    
    $files = glob(RESULTS_DIR . '/*.meta.json');
    
    foreach ($files as $file) {
        $job_data = json_decode(file_get_contents($file), true);
        
        // Check if completed
        $result_file = str_replace('.meta.json', '.result.json', $file);
        if (file_exists($result_file)) {
            $job_data['status'] = 'completed';
        }
        
        $jobs[] = $job_data;
    }
    
    // Sort by upload time (newest first)
    usort($jobs, function($a, $b) {
        return strtotime($b['uploaded_at']) - strtotime($a['uploaded_at']);
    });
    
    success(['jobs' => $jobs]);
}

/**
 * Delete a job
 */
function handleDelete() {
    $job_id = $_POST['job_id'] ?? $_GET['job_id'] ?? '';
    
    if (empty($job_id)) {
        error('Job ID required');
    }
    
    $meta_file = RESULTS_DIR . '/' . $job_id . '.meta.json';
    
    if (!file_exists($meta_file)) {
        error('Job not found');
    }
    
    $job_data = json_decode(file_get_contents($meta_file), true);
    
    // Delete files
    @unlink($job_data['filepath']);
    @unlink($meta_file);
    @unlink(RESULTS_DIR . '/' . $job_id . '.result.json');
    
    success(['message' => 'Job deleted']);
}

/**
 * Debug endpoint
 */
function handleDebug() {
    $job_id = $_GET['job_id'] ?? '';

    if (empty($job_id)) {
        error('Job ID required');
    }

    $meta_file = RESULTS_DIR . '/' . $job_id . '.meta.json';
    $result_file = RESULTS_DIR . '/' . $job_id . '.result.json';
    $error_log = RESULTS_DIR . '/' . $job_id . '.error.log';

    $debug_info = [
        'job_id' => $job_id,
        'meta_exists' => file_exists($meta_file),
        'result_exists' => file_exists($result_file),
        'error_log_exists' => file_exists($error_log),
        'files' => []
    ];

    if (file_exists($meta_file)) {
        $debug_info['meta'] = json_decode(file_get_contents($meta_file), true);
    }

    if (file_exists($error_log)) {
        $debug_info['error_log'] = file_get_contents($error_log);
    }

    if (file_exists($result_file)) {
        $debug_info['result_size'] = filesize($result_file);
    }

    // Test Python
    $venv_python = '/Users/daveporter/Desktop/CODING-2024/PDF-Accessibility-checker/venv/bin/python3';
    exec($venv_python . ' --version 2>&1', $python_version);
    $debug_info['python_version'] = implode("\n", $python_version);

    success($debug_info);
}

/**
 * Serve page images
 */
function handleImage() {
    $job_id = $_GET['job_id'] ?? '';
    $page_num = $_GET['page'] ?? '';

    if (empty($job_id) || empty($page_num)) {
        error('Job ID and page number required');
    }

    // Find the image file
    $images_dir = RESULTS_DIR . '/' . $job_id . '.result_images';
    $image_file = $images_dir . '/page_' . intval($page_num) . '.png';

    if (!file_exists($image_file)) {
        http_response_code(404);
        header('Content-Type: application/json');
        echo json_encode(['success' => false, 'error' => 'Image not found']);
        exit;
    }

    // Serve the image
    header('Content-Type: image/png');
    header('Cache-Control: public, max-age=86400'); // Cache for 1 day
    readfile($image_file);
    exit;
}

/**
 * Auto-remediate PDF accessibility issues
 */
function handleRemediate() {
    $job_id = $_POST['job_id'] ?? '';

    if (empty($job_id)) {
        error('Job ID required');
    }

    $meta_file = RESULTS_DIR . '/' . $job_id . '.meta.json';
    $result_file = RESULTS_DIR . '/' . $job_id . '.result.json';

    if (!file_exists($meta_file) || !file_exists($result_file)) {
        error('Job not found');
    }

    $job_data = json_decode(file_get_contents($meta_file), true);
    $result_data = json_decode(file_get_contents($result_file), true);

    // Check if there are fixable issues
    if (!isset($result_data['auto_fixable_count']) || $result_data['auto_fixable_count'] == 0) {
        error('No auto-fixable issues found');
    }

    $original_pdf = $job_data['filepath'];
    $remediated_pdf = UPLOAD_DIR . '/' . $job_id . '_remediated.pdf';

    // Use absolute venv path
    $venv_python = '/Users/daveporter/Desktop/CODING-2024/PDF-Accessibility-checker/venv/bin/python3';
    $python_bin = file_exists($venv_python) ? $venv_python : 'python3';
    $remediation_script = __DIR__ . '/pdf_remediation.py';

    // Build command - apply all safe fixes
    $cmd = escapeshellcmd($python_bin . ' ' . $remediation_script) . ' ' .
           escapeshellarg($original_pdf) . ' ' .
           '--output ' . escapeshellarg($remediated_pdf) . ' ' .
           '--all';

    // Set PATH for poppler
    $env_path = getenv('PATH');
    $poppler_paths = '/opt/homebrew/bin:/usr/local/bin';
    putenv("PATH={$poppler_paths}:{$env_path}");

    // Run remediation
    $error_log = RESULTS_DIR . '/' . $job_id . '.remediation.log';
    $cmd .= ' > ' . escapeshellarg($error_log) . ' 2>&1';

    exec($cmd, $output, $return_code);

    // Check if remediation succeeded
    if ($return_code !== 0 || !file_exists($remediated_pdf)) {
        $log_content = file_exists($error_log) ? file_get_contents($error_log) : 'Unknown error';
        error('Remediation failed: ' . substr($log_content, -500));
    }

    // Store remediated file info
    $job_data['remediated_pdf'] = $remediated_pdf;
    $job_data['remediated_at'] = date('Y-m-d H:i:s');
    file_put_contents($meta_file, json_encode($job_data, JSON_PRETTY_PRINT));

    success([
        'job_id' => $job_id,
        'remediated_pdf' => basename($remediated_pdf),
        'original_filename' => $job_data['original_filename'],
        'fixes_applied' => $result_data['auto_fixable_count'],
        'download_url' => 'api.php?action=download&job_id=' . $job_id . '&type=remediated',
        'message' => 'PDF remediated successfully'
    ]);
}

/**
 * Download original or remediated PDF
 */
function handleDownload() {
    $job_id = $_GET['job_id'] ?? '';
    $type = $_GET['type'] ?? 'original'; // 'original' or 'remediated'

    if (empty($job_id)) {
        error('Job ID required');
    }

    $meta_file = RESULTS_DIR . '/' . $job_id . '.meta.json';

    if (!file_exists($meta_file)) {
        error('Job not found');
    }

    $job_data = json_decode(file_get_contents($meta_file), true);

    if ($type === 'remediated') {
        if (!isset($job_data['remediated_pdf']) || !file_exists($job_data['remediated_pdf'])) {
            error('Remediated PDF not found');
        }
        $file_path = $job_data['remediated_pdf'];
        $filename = pathinfo($job_data['original_filename'], PATHINFO_FILENAME) . '_fixed.pdf';
    } else {
        $file_path = $job_data['filepath'];
        $filename = $job_data['original_filename'];
    }

    // Serve the file
    header('Content-Type: application/pdf');
    header('Content-Disposition: attachment; filename="' . $filename . '"');
    header('Content-Length: ' . filesize($file_path));
    readfile($file_path);
    exit;
}

/**
 * Send success response
 */
function success($data) {
    echo json_encode([
        'success' => true,
        'data' => $data
    ]);
    exit;
}

/**
 * Send error response
 */
function error($message) {
    http_response_code(400);
    echo json_encode([
        'success' => false,
        'error' => $message
    ]);
    exit;
}