Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Doc html #32

Open
wants to merge 8 commits into
base: trunk
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 32 additions & 0 deletions .github/scripts/check_html.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.


from bs4 import BeautifulSoup
from glob import glob

def is_valid_HTML_tag(html_string_to_check: str) -> bool:
soup = BeautifulSoup(html_string_to_check, 'html.parser')
return html_string_to_check == str(soup)

if __name__ == "__main__":
htmls = glob(pathname="**/*.html", recursive=True)
print("kkkk html", htmls)
for html in htmls:
with open(html, "r") as fp:
content = fp.read()
print("kkk check content", str(content))
if not is_valid_HTML_tag(content):
exit(1)
1 change: 1 addition & 0 deletions .github/scripts/requirements.txt
Original file line number Diff line number Diff line change
Expand Up @@ -15,3 +15,4 @@
PyYAML~=6.0
pytz==2024.2
requests==2.32.3
beautifulsoup4==4.10.0
7 changes: 7 additions & 0 deletions .github/workflows/build.yml
Original file line number Diff line number Diff line change
Expand Up @@ -143,6 +143,13 @@ jobs:
find ./site-docs/generated -type f -exec grep -L "." {} \; >&2
exit 1
fi
- name: Check html content
if: always()
run: |
echo "execute Check html content"
if [ "$(python .github/scripts/check_html.py)" -ne 0 ]; then
exit 1
fi

test:
needs: [validate, load-catalog]
Expand Down
1 change: 0 additions & 1 deletion docs/upgrade.html
Original file line number Diff line number Diff line change
Expand Up @@ -339,7 +339,6 @@ <h5><a id="upgrade_400_notable" href="#upgrade_400_notable">Notable changes in 4
This allows to not only collect the metric of the internally used clients of a Kafka Streams appliction via a broker-side plugin,
but also to collect the <a href="/{{version}}/documentation/#kafka_streams_monitoring">metrics</a> of the Kafka Streams runtime itself.
</li>
<li>
The default value of 'num.recovery.threads.per.data.dir' has been changed from 1 to 2. The impact of this is faster
recovery post unclean shutdown at the expense of extra IO cycles.
See <a href="https://cwiki.apache.org/confluence/display/KAFKA/KIP-1030%3A+Change+constraints+and+default+values+for+various+configurations">KIP-1030</a>
Expand Down
Loading