import re from pathlib import Path from backend.core.notes_high_confidence_lexicon import HIGH_CONFIDENCE_LEXICON html = Path("frontend/index.html").read_text(encoding="utf-8") start = html.index("const highConfidence = [") end = html.index("];", start) + 2 block = html[start:end] frontend_entries = re.findall(r"\{\s*code:'([A-N]\d+)',\s*rx:/(.+)/i\s*\}", block) backend_entries = list(HIGH_CONFIDENCE_LEXICON) print("fe", len(frontend_entries), "be", len(backend_entries)) for i, (fe, be) in enumerate(zip(frontend_entries, backend_entries, strict=False)): if fe[0] != be[0] or fe[1] != be[1]: print(i, fe[0], be[0]) print(" FE:", fe[1]) print(" BE:", be[1])