#!/usr/bin/env python3
"""Convert one PDF/image into Markdown plus page results. Python 3.10+, no dependencies."""
import argparse
import json
import mimetypes
import os
from pathlib import Path
import sys
import time
import urllib.error
import urllib.request
import uuid


def convert(path, *, api_key=None, demo=False, base_url='https://api.pennyocr.com', timeout=120):
    path = Path(path)
    if path.suffix.lower() not in {'.pdf', '.png', '.jpg', '.jpeg', '.webp', '.tiff', '.tif'}:
        raise ValueError('Choose a PDF, PNG, JPEG, WebP or TIFF.')
    data = path.read_bytes()
    limit_mb = 10 if demo else 50
    if not data or len(data) > limit_mb * 1024 * 1024:
        raise ValueError(f'Choose a nonempty PDF/image no larger than {limit_mb} MB.')
    if not demo and not api_key:
        raise ValueError('Set PENNYOCR_API_KEY, or use --demo for the limited public trial.')
    boundary = 'pennyocr-' + uuid.uuid4().hex
    # Fixed form filename avoids interpolating local paths into HTTP headers.
    filename = 'document' + path.suffix.lower()
    mime = mimetypes.guess_type(filename)[0] or 'application/octet-stream'
    body = (f'--{boundary}\r\nContent-Disposition: form-data; name="file"; filename="{filename}"\r\n'
            f'Content-Type: {mime}\r\n\r\n').encode() + data + f'\r\n--{boundary}--\r\n'.encode()
    headers = {'Content-Type': f'multipart/form-data; boundary={boundary}', 'User-Agent': 'PennyOCR-Python-Example/1.0'}
    if not demo:
        headers['Authorization'] = 'Bearer ' + api_key
    endpoint = '/demo/ocr' if demo else '/v1/ocr'
    request = urllib.request.Request(base_url.rstrip('/') + endpoint + '?format=markdown', data=body, headers=headers, method='POST')
    started = time.monotonic()
    try:
        with urllib.request.urlopen(request, timeout=timeout) as response:
            result = json.load(response)
    except urllib.error.HTTPError as error:
        error.close()
        actions = {401: 'Check your API key.', 402: 'Buy credits or check your remaining free allowance.',
                   413: 'Reduce document size or page count.', 422: 'Check the format and readability.',
                   429: 'Wait before trying again.', 503: 'Try again later or contact support.'}
        raise RuntimeError(f'HTTP {error.code}. {actions.get(error.code, "Check the API status and request.")} No automatic retry was made.') from None
    if not isinstance(result, dict) or not isinstance(result.get('text'), str):
        raise RuntimeError('The API returned an unexpected response. No output files were written.')
    return result, round(time.monotonic() - started, 3)


def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument('document', type=Path)
    parser.add_argument('--output', type=Path, default=Path('ocr-output'))
    parser.add_argument('--demo', action='store_true', help='No key. Public quota, first page of PDFs only.')
    args = parser.parse_args()
    result, elapsed = convert(args.document, api_key=os.environ.get('PENNYOCR_API_KEY'), demo=args.demo)
    args.output.mkdir(parents=True, exist_ok=True)
    (args.output / 'document.md').write_text(result['text'], encoding='utf-8')
    (args.output / 'response.json').write_text(json.dumps(result, indent=2), encoding='utf-8')
    (args.output / 'timing.json').write_text(json.dumps({'elapsed_seconds': elapsed, 'mode': 'demo' if args.demo else 'authenticated'}, indent=2), encoding='utf-8')
    print(f'Markdown and JSON saved to {args.output}. Request completed in {elapsed:.3f}s.')
    if args.demo:
        print('Public demo: first PDF page only. Use your own API key without --demo for normal API limits and billing.')
    return 0


if __name__ == '__main__':
    try:
        sys.exit(main())
    except (OSError, ValueError, RuntimeError) as error:
        print(str(error), file=sys.stderr)
        sys.exit(1)
