1from urllib.request import urlopen
 2import shutil
 3
 4from . import constants
 5
 6
 7# download language data files to ~/tessdata if necessary
 8def download_lang_data(lang: str):
 9    constants.TESSDATA_DIR.mkdir(parents=True, exist_ok=True)
10
11    for lang_name in lang.split('+'):
12        filepath = constants.TESSDATA_DIR / '{}.traineddata'.format(lang_name)
13        if not filepath.is_file():
14            # download needed file
15            if lang_name[0].isupper():
16                url = constants.TESSDATA_SCRIPT_URL.format(lang_name)
17            else:
18                url = constants.TESSDATA_URL.format(lang_name)
19
20            with urlopen(url) as res, open(filepath, 'w+b') as f:
21                shutil.copyfileobj(res, f)