#!/usr/bin/env python3
"""Verify embedded legal HTML against the original PDFs (development: pypdf)."""
from pathlib import Path
import textwrap

from pypdf import PdfReader

ROOT = Path(__file__).resolve().parents[1]
page = (ROOT / 'index.html').read_text()

for name, filename, field in [
    ('impressum', 'impressum_buchhandlung_am_markt_de.pdf', 'imprint_html_de'),
    ('datenschutz', 'datenschutzerklaerung_buchhandlung_am_markt_de.pdf', 'privacy_html_de'),
]:
    source = PdfReader(ROOT / 'design/legal' / filename).get_fields()[field]['/V']
    source = source.replace('\r\n', '\n').replace('\r', '\n').strip()
    embedded = page.split(f'<!-- legal:{name}:start -->', 1)[1].split(f'<!-- legal:{name}:end -->', 1)[0]
    embedded = textwrap.dedent(embedded).strip()
    # The only markup addition is a focusable, labelled title for the dialog.
    embedded = embedded.replace(f'<h1 id="{name}-title" tabindex="-1">', '<h1>', 1)
    assert embedded == source, f'{name}: legal content differs from the supplied PDF'
    print(f'{name}: complete embedded HTML matches the supplied PDF ({len(source)} characters)')