Skip to content

HDDS-14976. xml_to_md.py does not handle generated XML files #10044

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.

Sign up for GitHub

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

Open
adoroszlai wants to merge 3 commits into
base: master
Choose a base branch
from
+15 −7
Open

HDDS-14976. xml_to_md.py does not handle generated XML files #10044

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
56f8b33
HDDS-14976. xml_to_md.py does not handle generated XML files
adoroszlai Apr 4, 2026
d9888ac
join multi-line default value
adoroszlai Apr 4, 2026
f34ee82
also trim name
adoroszlai Apr 5, 2026
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
22 changes: 15 additions & 7 deletions dev-support/ci/xml_to_md.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ def extract_xml_from_jar(jar_path, xml_filename):
xml_files = []
with zipfile.ZipFile(jar_path, 'r') as jar:
for file_info in jar.infolist():
if file_info.filename.endswith(xml_filename):
if file_info.filename.endswith(xml_filename) and 'network-topology-default.xml' != file_info.filename:
with jar.open(file_info.filename) as xml_file:
xml_files.append(xml_file.read())
return xml_files
Expand Down Expand Up @@ -65,8 +65,8 @@ def parse_xml_file(xml_content, properties):
tag = prop.findtext('tag', '')

properties[name] = Property(
name=name,
value=prop.findtext('value', ''),
name=name.strip(),
value=prop.findtext('value', '').strip(),
tag=tag,
description=' '.join(description.split()).strip()
)
Expand Down Expand Up @@ -107,13 +107,19 @@ def generate_markdown(properties):
"""

placeholder_pattern = re.compile(r'(\$)?\{([^}]+)\}')
multi_space_pattern = re.compile(r' +')

for prop in sorted(properties.values(), key=lambda p: p.name):
# Escape pipe characters and wrap {placeholders} in backticks
description = prop.description.replace('|', '\\|')
description = placeholder_pattern.sub(r'`\1{\2}`', description)
value = prop.value.replace('|', '\\|') if prop.value else ''
value = placeholder_pattern.sub(r'`\1{\2}`', value) if value else ''

value = prop.value
if value:
value = value.replace('|', '\\|')
value = placeholder_pattern.sub(r'`\1{\2}`', value)
value = value.replace('\n', ' ')
value = multi_space_pattern.sub(' ', value)

markdown += f"| `{prop.name}` | {value} | {prop.tag} | {description} |\n"

Expand All @@ -137,11 +143,13 @@ def main():
raise ValueError("SNAPSHOT directory not found in the specified base path.")

extract_path = os.path.join(snapshot_dir, 'share', 'ozone', 'lib')
xml_filename = 'ozone-default.xml'
xml_filename = '-default.xml'

property_map = {}
for file_name in os.listdir(extract_path):
if file_name.startswith('hdds-common-') and file_name.endswith('.jar'):
if (file_name.startswith('hdds-') or file_name.startswith('ozone-')) \
and not file_name.startswith('ozone-filesystem-hadoop') \
and file_name.endswith('.jar'):
jar_path = os.path.join(extract_path, file_name)
xml_contents = extract_xml_from_jar(jar_path, xml_filename)
for xml_content in xml_contents:
Expand Down