ClickHouse/docs/tools/test.py
2021-06-29 03:17:09 +03:00

53 lines
1.4 KiB
Python
Executable File

#!/usr/bin/env python3
import logging
import os
import sys
import bs4
import subprocess
def test_single_page(input_path, lang):
with open(input_path) as f:
soup = bs4.BeautifulSoup(
f,
features='html.parser'
)
anchor_points = set()
duplicate_anchor_points = 0
links_to_nowhere = 0
for tag in soup.find_all():
for anchor_point in [tag.attrs.get('name'), tag.attrs.get('id')]:
if anchor_point:
anchor_points.add(anchor_point)
for tag in soup.find_all():
href = tag.attrs.get('href')
if href and href.startswith('#') and href != '#':
if href[1:] not in anchor_points:
links_to_nowhere += 1
logging.info("Tag %s", tag)
logging.info('Link to nowhere: %s' % href)
if links_to_nowhere:
if lang == 'en' or lang == 'ru':
logging.error(f'Found {links_to_nowhere} links to nowhere in {lang}')
sys.exit(1)
else:
logging.warning(f'Found {links_to_nowhere} links to nowhere in {lang}')
if len(anchor_points) <= 10:
logging.error('Html parsing is probably broken')
sys.exit(1)
if __name__ == '__main__':
logging.basicConfig(
level=logging.DEBUG,
stream=sys.stderr
)
test_single_page(sys.argv[1], sys.argv[2])