Function extract_text

scripts/developer-guide/run_languagetool.py:206–210

(html_path)

def extract_text(html_path):
    parser = TextExtractor()
    with open(html_path, "r", encoding="utf-8") as fh:
        parser.feed(fh.read())
    return normalize_whitespace(parser.text())


CHUNK_BYTES = 40_000